[ { "path": ".gitignore", "content": "*.pyc\n.ipynb_checkpoints\nlib/build\nlib/pycocotools/_mask.c\nlib/pycocotools/_mask.so\noutput\n.idea\n" }, { "path": "LICENSE", "content": "The MIT License (MIT)\n\nCopyright (c) 2017 Chen-Wei Xie\n\nPermission is hereby granted, free of charge, to any person obtaining a copy\nof this software and associated documentation files (the \"Software\"), to deal\nin the Software without restriction, including without limitation the rights\nto use, copy, modify, merge, publish, distribute, sublicense, and/or sell\ncopies of the Software, and to permit persons to whom the Software is\nfurnished to do so, subject to the following conditions:\n\nThe above copyright notice and this permission notice shall be included in\nall copies or substantial portions of the Software.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\nIMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\nFITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\nAUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\nLIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\nOUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE\nSOFTWARE.\n" }, { "path": "README.md", "content": "# Faster-RCNN-ResNet\n\nThis code extends [py-faster-rcnn](https://github.com/rbgirshick/py-faster-rcnn) by adding ResNet implementation\nand Online Hard Example Mining.\n\n\nThis is a ResNet Implementation for Faster-RCNN.\nThe faster rcnn code is based on [py-faster-rcnn](https://github.com/rbgirshick/py-faster-rcnn).\nThe ohem code is based on [ohem](https://github.com/abhi2610/ohem).\nTo reduce the memory usage, we use batchnorm layer in [Microsoft's caffe](https://github.com/Microsoft/caffe)\n\n# Modification\n1. The [caffe-fast-rcnn](https://github.com/Eniac-Xie/caffe-fast-rcnn.git) we use is a little different from the one [py-faster-rcnn](https://github.com/rbgirshick/py-faster-rcnn) use,\n it uses the batchnorm layer from [Microsoft's caffe](https://github.com/Microsoft/caffe) to reduce the memory usage.\n2. Using the in-place eltwise sum within the [PR](https://github.com/BVLC/caffe/pull/3708)\n3. To reduce the memory usage, we also release a pretrained ResNet-101 model in which batchnorm layer's parameters is\n merged into scale layer's, see tools/merge_bn_scale.py form more detail.\n4. Use Online-Hard-Example-Mining while training.\n\n# Installation\nThe usage is similar to [py-faster-rcnn](https://github.com/rbgirshick/py-faster-rcnn).\n\n1. Clone this repository\n ```Shell\n git clone https://github.com/Eniac-Xie/faster-rcnn-resnet.git\n ```\n We'll call the directory that you cloned faster-rcnn-resnet `ROOT`\n\n2. Clone the modified caffe-fast-rcnn\n\n ```Shell\n cd $ROOT/\n git clone https://github.com/Eniac-Xie/caffe-fast-rcnn.git\n ```\n\n3. Build Cython module\n\n ```Shell\n cd $ROOT/lib/\n make\n ```\n\n4. Build Caffe\n\n ```Shell\n cd $ROOT/caffe-fast-rcnn\n make all -j8\n make pycaffe\n ```\n# Result\n\n| | training data | test data | ohem | mAP@0.5 |\n|------------------------|:-------------------:|:---------------------:|:------:|:-------------:|\n|Faster-RCNN, ResNet-101 | VOC 07+12 trainval | VOC 07 test | False | 78.78% | \n|Faster-RCNN, ResNet-101 | VOC 07+12 trainval | VOC 07 test | True | 79.44% | \n\n\n# Testing\nDownload faster-rcnn-resnet weights from:\n\n[faster-rcnn-resnet without ohem (BaiduYun)](http://pan.baidu.com/s/1kUKXgVH)\n\n[faster-rcnn-resnet without ohem (OneDrive)](https://1drv.ms/u/s!AgkRygoHQVTXigHNLWT6gRbTHo2f)\n\n[faster-rcnn-resnet with ohem (BaiduYun)](http://pan.baidu.com/s/1o8CtJwI)\n\n[faster-rcnn-resnet with ohem (OneDrive)](https://1drv.ms/u/s!AgkRygoHQVTXigInqoym2V6z4CNA)\n\nthen you can do as follow:\n\n ```Shell\n cd $ROOT/\n sh experiments/scripts/train_resnet101_bn_scale_merged_0712_end2end.sh\n make\n ```\nor\n\n ```Shell\n cd $ROOT/\n sh experiments/scripts/train_resnet101_bn_scale_merged_0712_end2end_ohem.sh\n make\n ```\n\n# Training\nDownload resnet-101 pretrained model, note that we use a modified version in which batchnorm layer's parameters is\nmerged into scale layer's, you can download the model from [Baidu Yun](http://pan.baidu.com/s/1qX7VFjA) or [OneDrive](https://1drv.ms/u/s!AgkRygoHQVTXigBCR-5cnmAkfGfy)\n\nthen you can do as follow:\n ```Shell\n cd $ROOT/\n sh experiments/scripts/train_resnet101_bn_scale_merged_0712_end2end.sh\n ```\nor\n ```Shell\n cd $ROOT/\n sh experiments/scripts/train_resnet101_bn_scale_merged_0712_end2end_ohem.sh\n ```\n" }, { "path": "data/.gitignore", "content": "selective_search*\nimagenet_models*\nfast_rcnn_models*\nVOCdevkit*\ncache\n" }, { "path": "data/README.md", "content": "This directory holds (*after you download them*):\n- Caffe models pre-trained on ImageNet\n- Faster R-CNN models\n- Symlinks to datasets\n\nTo download Caffe models (ZF, VGG16) pre-trained on ImageNet, run:\n\n```\n./data/scripts/fetch_imagenet_models.sh\n```\n\nThis script will populate `data/imagenet_models`.\n\nTo download Faster R-CNN models trained on VOC 2007, run:\n\n```\n./data/scripts/fetch_faster_rcnn_models.sh\n```\n\nThis script will populate `data/faster_rcnn_models`.\n\nIn order to train and test with PASCAL VOC, you will need to establish symlinks.\nFrom the `data` directory (`cd data`):\n\n```\n# For VOC 2007\nln -s /your/path/to/VOC2007/VOCdevkit VOCdevkit2007\n\n# For VOC 2012\nln -s /your/path/to/VOC2012/VOCdevkit VOCdevkit2012\n```\n\nInstall the MS COCO dataset at /path/to/coco\n\n```\nln -s /path/to/coco coco\n```\n\nFor COCO with Fast R-CNN, place object proposals under `coco_proposals` (inside\nthe `data` directory). You can obtain proposals on COCO from Jan Hosang at\nhttps://www.mpi-inf.mpg.de/departments/computer-vision-and-multimodal-computing/research/object-recognition-and-scene-understanding/how-good-are-detection-proposals-really/.\nFor COCO, using MCG is recommended over selective search. MCG boxes can be downloaded\nfrom http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/mcg/.\nUse the tool `lib/datasets/tools/mcg_munge.py` to convert the downloaded MCG data\ninto the same file layout as those from Jan Hosang.\n\nSince you'll likely be experimenting with multiple installs of Fast/er R-CNN in\nparallel, you'll probably want to keep all of this data in a shared place and\nuse symlinks. On my system I create the following symlinks inside `data`:\n\nAnnotations for the 5k image 'minival' subset of COCO val2014 that I like to use\ncan be found at http://www.cs.berkeley.edu/~rbg/faster-rcnn-data/instances_minival2014.json.zip.\nAnnotations for COCO val2014 (set) minus minival (~35k images) can be found at\nhttp://www.cs.berkeley.edu/~rbg/faster-rcnn-data/instances_valminusminival2014.json.zip.\n\n```\n# data/cache holds various outputs created by the datasets package\nln -s /data/fast_rcnn_shared/cache\n\n# move the imagenet_models to shared location and symlink to them\nln -s /data/fast_rcnn_shared/imagenet_models\n\n# move the selective search data to a shared location and symlink to them\n# (only applicable to Fast R-CNN training)\nln -s /data/fast_rcnn_shared/selective_search_data\n\nln -s /data/VOC2007/VOCdevkit VOCdevkit2007\nln -s /data/VOC2012/VOCdevkit VOCdevkit2012\n```\n" }, { "path": "data/pylintrc", "content": "[TYPECHECK]\n\nignored-modules = numpy, numpy.random, cv2\n" }, { "path": "data/scripts/fetch_faster_rcnn_models.sh", "content": "#!/bin/bash\n\nDIR=\"$( cd \"$( dirname \"${BASH_SOURCE[0]}\" )/../\" && pwd )\"\ncd $DIR\n\nFILE=faster_rcnn_models.tgz\nURL=http://www.cs.berkeley.edu/~rbg/faster-rcnn-data/$FILE\nCHECKSUM=ac116844f66aefe29587214272054668\n\nif [ -f $FILE ]; then\n echo \"File already exists. Checking md5...\"\n os=`uname -s`\n if [ \"$os\" = \"Linux\" ]; then\n checksum=`md5sum $FILE | awk '{ print $1 }'`\n elif [ \"$os\" = \"Darwin\" ]; then\n checksum=`cat $FILE | md5`\n fi\n if [ \"$checksum\" = \"$CHECKSUM\" ]; then\n echo \"Checksum is correct. No need to download.\"\n exit 0\n else\n echo \"Checksum is incorrect. Need to download again.\"\n fi\nfi\n\necho \"Downloading Faster R-CNN demo models (695M)...\"\n\nwget $URL -O $FILE\n\necho \"Unzipping...\"\n\ntar zxvf $FILE\n\necho \"Done. Please run this command again to verify that checksum = $CHECKSUM.\"\n" }, { "path": "data/scripts/fetch_imagenet_models.sh", "content": "#!/bin/bash\n\nDIR=\"$( cd \"$( dirname \"${BASH_SOURCE[0]}\" )/../\" && pwd )\"\ncd $DIR\n\nFILE=imagenet_models.tgz\nURL=http://www.cs.berkeley.edu/~rbg/faster-rcnn-data/$FILE\nCHECKSUM=ed34ca912d6782edfb673a8c3a0bda6d\n\nif [ -f $FILE ]; then\n echo \"File already exists. Checking md5...\"\n os=`uname -s`\n if [ \"$os\" = \"Linux\" ]; then\n checksum=`md5sum $FILE | awk '{ print $1 }'`\n elif [ \"$os\" = \"Darwin\" ]; then\n checksum=`cat $FILE | md5`\n fi\n if [ \"$checksum\" = \"$CHECKSUM\" ]; then\n echo \"Checksum is correct. No need to download.\"\n exit 0\n else\n echo \"Checksum is incorrect. Need to download again.\"\n fi\nfi\n\necho \"Downloading pretrained ImageNet models (1G)...\"\n\nwget $URL -O $FILE\n\necho \"Unzipping...\"\n\ntar zxvf $FILE\n\necho \"Done. Please run this command again to verify that checksum = $CHECKSUM.\"\n" }, { "path": "data/scripts/fetch_selective_search_data.sh", "content": "#!/bin/bash\n\nDIR=\"$( cd \"$( dirname \"${BASH_SOURCE[0]}\" )/../\" && pwd )\"\ncd $DIR\n\nFILE=selective_search_data.tgz\nURL=http://www.cs.berkeley.edu/~rbg/fast-rcnn-data/$FILE\nCHECKSUM=7078c1db87a7851b31966b96774cd9b9\n\nif [ -f $FILE ]; then\n echo \"File already exists. Checking md5...\"\n os=`uname -s`\n if [ \"$os\" = \"Linux\" ]; then\n checksum=`md5sum $FILE | awk '{ print $1 }'`\n elif [ \"$os\" = \"Darwin\" ]; then\n checksum=`cat $FILE | md5`\n fi\n if [ \"$checksum\" = \"$CHECKSUM\" ]; then\n echo \"Checksum is correct. No need to download.\"\n exit 0\n else\n echo \"Checksum is incorrect. Need to download again.\"\n fi\nfi\n\necho \"Downloading precomputed selective search boxes (0.5G)...\"\n\nwget $URL -O $FILE\n\necho \"Unzipping...\"\n\ntar zxvf $FILE\n\necho \"Done. Please run this command again to verify that checksum = $CHECKSUM.\"\n" }, { "path": "experiments/README.md", "content": "Scripts are under `experiments/scripts`.\n\nEach script saves a log file under `experiments/logs`.\n\nConfiguration override files used in the experiments are stored in `experiments/cfgs`.\n" }, { "path": "experiments/cfgs/faster_rcnn_alt_opt.yml", "content": "EXP_DIR: faster_rcnn_alt_opt\nTRAIN:\n BG_THRESH_LO: 0.0\nTEST:\n HAS_RPN: True\n" }, { "path": "experiments/cfgs/faster_rcnn_end2end.yml", "content": "EXP_DIR: faster_rcnn_end2end\nTRAIN:\n HAS_RPN: True\n IMS_PER_BATCH: 1\n BBOX_NORMALIZE_TARGETS_PRECOMPUTED: True\n RPN_POSITIVE_OVERLAP: 0.7\n RPN_BATCHSIZE: 256\n PROPOSAL_METHOD: gt\n BG_THRESH_LO: 0.0\nTEST:\n HAS_RPN: True\n" }, { "path": "experiments/cfgs/faster_rcnn_end2end_ohem.yml", "content": "EXP_DIR: faster_rcnn_end2end_ohem\nTRAIN:\n HAS_RPN: True\n IMS_PER_BATCH: 1\n BBOX_NORMALIZE_TARGETS_PRECOMPUTED: True\n RPN_POSITIVE_OVERLAP: 0.7\n RPN_BATCHSIZE: 256\n PROPOSAL_METHOD: gt\n BG_THRESH_LO: 0.0\n BATCH_SIZE: 64\n RPN_POST_NMS_TOP_N: 700\n USE_OHEM: True\n ASPECT_GROUPING: False\nTEST:\n HAS_RPN: True\n" }, { "path": "experiments/logs/.gitignore", "content": "*.txt*\n" }, { "path": "experiments/scripts/fast_rcnn.sh", "content": "#!/bin/bash\n# Usage:\n# ./experiments/scripts/fast_rcnn.sh GPU NET DATASET [options args to {train,test}_net.py]\n# DATASET is either pascal_voc or coco.\n#\n# Example:\n# ./experiments/scripts/fast_rcnn.sh 0 VGG_CNN_M_1024 pascal_voc \\\n# --set EXP_DIR foobar RNG_SEED 42 TRAIN.SCALES \"[400, 500, 600, 700]\"\n\nset -x\nset -e\n\nexport PYTHONUNBUFFERED=\"True\"\n\nGPU_ID=$1\nNET=$2\nNET_lc=${NET,,}\nDATASET=$3\n\narray=( $@ )\nlen=${#array[@]}\nEXTRA_ARGS=${array[@]:3:$len}\nEXTRA_ARGS_SLUG=${EXTRA_ARGS// /_}\n\ncase $DATASET in\n pascal_voc)\n TRAIN_IMDB=\"voc_2007_trainval\"\n TEST_IMDB=\"voc_2007_test\"\n PT_DIR=\"pascal_voc\"\n ITERS=40000\n ;;\n coco)\n TRAIN_IMDB=\"coco_2014_train\"\n TEST_IMDB=\"coco_2014_minival\"\n PT_DIR=\"coco\"\n ITERS=280000\n ;;\n *)\n echo \"No dataset given\"\n exit\n ;;\nesac\n\nLOG=\"experiments/logs/fast_rcnn_${NET}_${EXTRA_ARGS_SLUG}.txt.`date +'%Y-%m-%d_%H-%M-%S'`\"\nexec &> >(tee -a \"$LOG\")\necho Logging output to \"$LOG\"\n\ntime ./tools/train_net.py --gpu ${GPU_ID} \\\n --solver models/${PT_DIR}/${NET}/fast_rcnn/solver.prototxt \\\n --weights data/imagenet_models/${NET}.v2.caffemodel \\\n --imdb ${TRAIN_IMDB} \\\n --iters ${ITERS} \\\n ${EXTRA_ARGS}\n\nset +x\nNET_FINAL=`grep -B 1 \"done solving\" ${LOG} | grep \"Wrote snapshot\" | awk '{print $4}'`\nset -x\n\ntime ./tools/test_net.py --gpu ${GPU_ID} \\\n --def models/${PT_DIR}/${NET}/fast_rcnn/test.prototxt \\\n --net ${NET_FINAL} \\\n --imdb ${TEST_IMDB} \\\n ${EXTRA_ARGS}\n" }, { "path": "experiments/scripts/faster_rcnn_alt_opt.sh", "content": "#!/bin/bash\n# Usage:\n# ./experiments/scripts/faster_rcnn_alt_opt.sh GPU NET DATASET [options args to {train,test}_net.py]\n# DATASET is only pascal_voc for now\n#\n# Example:\n# ./experiments/scripts/faster_rcnn_alt_opt.sh 0 VGG_CNN_M_1024 pascal_voc \\\n# --set EXP_DIR foobar RNG_SEED 42 TRAIN.SCALES \"[400, 500, 600, 700]\"\n\nset -x\nset -e\n\nexport PYTHONUNBUFFERED=\"True\"\n\nGPU_ID=$1\nNET=$2\nNET_lc=${NET,,}\nDATASET=$3\n\narray=( $@ )\nlen=${#array[@]}\nEXTRA_ARGS=${array[@]:3:$len}\nEXTRA_ARGS_SLUG=${EXTRA_ARGS// /_}\n\ncase $DATASET in\n pascal_voc)\n TRAIN_IMDB=\"voc_2007_trainval\"\n TEST_IMDB=\"voc_2007_test\"\n PT_DIR=\"pascal_voc\"\n ITERS=40000\n ;;\n coco)\n echo \"Not implemented: use experiments/scripts/faster_rcnn_end2end.sh for coco\"\n exit\n ;;\n *)\n echo \"No dataset given\"\n exit\n ;;\nesac\n\nLOG=\"experiments/logs/faster_rcnn_alt_opt_${NET}_${EXTRA_ARGS_SLUG}.txt.`date +'%Y-%m-%d_%H-%M-%S'`\"\nexec &> >(tee -a \"$LOG\")\necho Logging output to \"$LOG\"\n\ntime ./tools/train_faster_rcnn_alt_opt.py --gpu ${GPU_ID} \\\n --net_name ${NET} \\\n --weights data/imagenet_models/${NET}.v2.caffemodel \\\n --imdb ${TRAIN_IMDB} \\\n --cfg experiments/cfgs/faster_rcnn_alt_opt.yml \\\n ${EXTRA_ARGS}\n\nset +x\nNET_FINAL=`grep \"Final model:\" ${LOG} | awk '{print $3}'`\nset -x\n\ntime ./tools/test_net.py --gpu ${GPU_ID} \\\n --def models/${PT_DIR}/${NET}/faster_rcnn_alt_opt/faster_rcnn_test.pt \\\n --net ${NET_FINAL} \\\n --imdb ${TEST_IMDB} \\\n --cfg experiments/cfgs/faster_rcnn_alt_opt.yml \\\n ${EXTRA_ARGS}\n" }, { "path": "experiments/scripts/faster_rcnn_end2end.sh", "content": "#!/bin/bash\n# Usage:\n# ./experiments/scripts/faster_rcnn_end2end.sh GPU NET DATASET [options args to {train,test}_net.py]\n# DATASET is either pascal_voc or coco.\n#\n# Example:\n# ./experiments/scripts/faster_rcnn_end2end.sh 0 VGG_CNN_M_1024 pascal_voc \\\n# --set EXP_DIR foobar RNG_SEED 42 TRAIN.SCALES \"[400, 500, 600, 700]\"\n\nset -x\nset -e\n\nexport PYTHONUNBUFFERED=\"True\"\n\nGPU_ID=$1\nNET=$2\nNET_lc=${NET,,}\nDATASET=$3\n\narray=( $@ )\nlen=${#array[@]}\nEXTRA_ARGS=${array[@]:3:$len}\nEXTRA_ARGS_SLUG=${EXTRA_ARGS// /_}\n\ncase $DATASET in\n pascal_voc)\n TRAIN_IMDB=\"voc_2007_trainval\"\n TEST_IMDB=\"voc_2007_test\"\n PT_DIR=\"pascal_voc\"\n ITERS=70000\n ;;\n coco)\n # This is a very long and slow training schedule\n # You can probably use fewer iterations and reduce the\n # time to the LR drop (set in the solver to 350,000 iterations).\n TRAIN_IMDB=\"coco_2014_train\"\n TEST_IMDB=\"coco_2014_minival\"\n PT_DIR=\"coco\"\n ITERS=490000\n ;;\n *)\n echo \"No dataset given\"\n exit\n ;;\nesac\n\nLOG=\"experiments/logs/faster_rcnn_end2end_${NET}_${EXTRA_ARGS_SLUG}.txt.`date +'%Y-%m-%d_%H-%M-%S'`\"\nexec &> >(tee -a \"$LOG\")\necho Logging output to \"$LOG\"\n\ntime ./tools/train_net.py --gpu ${GPU_ID} \\\n --solver models/${PT_DIR}/${NET}/faster_rcnn_end2end/solver.prototxt \\\n --weights data/imagenet_models/${NET}.v2.caffemodel \\\n --imdb ${TRAIN_IMDB} \\\n --iters ${ITERS} \\\n --cfg experiments/cfgs/faster_rcnn_end2end.yml \\\n ${EXTRA_ARGS}\n\nset +x\nNET_FINAL=`grep -B 1 \"done solving\" ${LOG} | grep \"Wrote snapshot\" | awk '{print $4}'`\nset -x\n\ntime ./tools/test_net.py --gpu ${GPU_ID} \\\n --def models/${PT_DIR}/${NET}/faster_rcnn_end2end/test.prototxt \\\n --net ${NET_FINAL} \\\n --imdb ${TEST_IMDB} \\\n --cfg experiments/cfgs/faster_rcnn_end2end.yml \\\n ${EXTRA_ARGS}\n" }, { "path": "experiments/scripts/test_resnet101_bn_scale_merged_0712_end2end.sh", "content": "./tools/test_net.py --gpu 1 \\\n --def models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_end2end/test.prototxt \\\n --net output/faster_rcnn_end2end/voc_0712_trainval/resnet101_faster_rcnn_bn_scale_merged_end2end_iter_70000.caffemodel \\\n --imdb voc_0712_test \\\n --cfg experiments/cfgs/faster_rcnn_end2end.yml \\\n" }, { "path": "experiments/scripts/test_resnet101_bn_scale_merged_0712_end2end_ohem.sh", "content": "./tools/test_net.py --gpu 1 \\\n --def models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_end2end/test.prototxt \\\n --net output/faster_rcnn_end2end_ohem/voc_0712_trainval/resnet101_faster_rcnn_bn_scale_merged_end2end_ohem_iter_70000.caffemodel \\\n --imdb voc_0712_test \\\n --cfg experiments/cfgs/faster_rcnn_end2end.yml \\\n\n" }, { "path": "experiments/scripts/train_resnet101_bn_scale_merged_0712_end2end.sh", "content": "./tools/train_net.py --gpu 1 \\\n --solver models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_end2end/solver.prototxt \\\n --weights ResNet-101-BN-SCALE-Merged/ResNet101_BN_SCALE_Merged.caffemodel \\\n --imdb voc_0712_trainval \\\n --iters 70000 \\\n --cfg experiments/cfgs/faster_rcnn_end2end.yml" }, { "path": "experiments/scripts/train_resnet101_bn_scale_merged_0712_end2end_ohem.sh", "content": "./tools/train_net.py --gpu 1 \\\n --solver models/pascal_voc/ResNet101_BN_SCALE_Merged_OHEM/faster_rcnn_end2end_ohem/solver.prototxt \\\n --weights ResNet-101-BN-SCALE-Merged/ResNet101_BN_SCALE_Merged.caffemodel \\\n --imdb voc_0712_trainval \\\n --iters 70000 \\\n --cfg experiments/cfgs/faster_rcnn_end2end_ohem.yml" }, { "path": "lib/Makefile", "content": "all:\n\tpython setup.py build_ext --inplace\n\trm -rf build\n" }, { "path": "lib/datasets/VOCdevkit-matlab-wrapper/get_voc_opts.m", "content": "function VOCopts = get_voc_opts(path)\n\ntmp = pwd;\ncd(path);\ntry\n addpath('VOCcode');\n VOCinit;\ncatch\n rmpath('VOCcode');\n cd(tmp);\n error(sprintf('VOCcode directory not found under %s', path));\nend\nrmpath('VOCcode');\ncd(tmp);\n" }, { "path": "lib/datasets/VOCdevkit-matlab-wrapper/voc_eval.m", "content": "function res = voc_eval(path, comp_id, test_set, output_dir)\n\nVOCopts = get_voc_opts(path);\nVOCopts.testset = test_set;\n\nfor i = 1:length(VOCopts.classes)\n cls = VOCopts.classes{i};\n res(i) = voc_eval_cls(cls, VOCopts, comp_id, output_dir);\nend\n\nfprintf('\\n~~~~~~~~~~~~~~~~~~~~\\n');\nfprintf('Results:\\n');\naps = [res(:).ap]';\nfprintf('%.1f\\n', aps * 100);\nfprintf('%.1f\\n', mean(aps) * 100);\nfprintf('~~~~~~~~~~~~~~~~~~~~\\n');\n\nfunction res = voc_eval_cls(cls, VOCopts, comp_id, output_dir)\n\ntest_set = VOCopts.testset;\nyear = VOCopts.dataset(4:end);\n\naddpath(fullfile(VOCopts.datadir, 'VOCcode'));\n\nres_fn = sprintf(VOCopts.detrespath, comp_id, cls);\n\nrecall = [];\nprec = [];\nap = 0;\nap_auc = 0;\n\ndo_eval = (str2num(year) <= 2007) | ~strcmp(test_set, 'test');\nif do_eval\n % Bug in VOCevaldet requires that tic has been called first\n tic;\n [recall, prec, ap] = VOCevaldet(VOCopts, comp_id, cls, true);\n ap_auc = xVOCap(recall, prec);\n\n % force plot limits\n ylim([0 1]);\n xlim([0 1]);\n\n print(gcf, '-djpeg', '-r0', ...\n [output_dir '/' cls '_pr.jpg']);\nend\nfprintf('!!! %s : %.4f %.4f\\n', cls, ap, ap_auc);\n\nres.recall = recall;\nres.prec = prec;\nres.ap = ap;\nres.ap_auc = ap_auc;\n\nsave([output_dir '/' cls '_pr.mat'], ...\n 'res', 'recall', 'prec', 'ap', 'ap_auc');\n\nrmpath(fullfile(VOCopts.datadir, 'VOCcode'));\n" }, { "path": "lib/datasets/VOCdevkit-matlab-wrapper/xVOCap.m", "content": "function ap = xVOCap(rec,prec)\r\n% From the PASCAL VOC 2011 devkit\r\n\r\nmrec=[0 ; rec ; 1];\r\nmpre=[0 ; prec ; 0];\r\nfor i=numel(mpre)-1:-1:1\r\n mpre(i)=max(mpre(i),mpre(i+1));\r\nend\r\ni=find(mrec(2:end)~=mrec(1:end-1))+1;\r\nap=sum((mrec(i)-mrec(i-1)).*mpre(i));\r\n" }, { "path": "lib/datasets/__init__.py", "content": "# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n" }, { "path": "lib/datasets/coco.py", "content": "# --------------------------------------------------------\n# Fast/er R-CNN\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\nfrom datasets.imdb import imdb\nimport datasets.ds_utils as ds_utils\nfrom fast_rcnn.config import cfg\nimport os.path as osp\nimport sys\nimport os\nimport numpy as np\nimport scipy.sparse\nimport scipy.io as sio\nimport cPickle\nimport json\nimport uuid\n# COCO API\nfrom pycocotools.coco import COCO\nfrom pycocotools.cocoeval import COCOeval\nfrom pycocotools import mask as COCOmask\n\ndef _filter_crowd_proposals(roidb, crowd_thresh):\n \"\"\"\n Finds proposals that are inside crowd regions and marks them with\n overlap = -1 (for all gt rois), which means they will be excluded from\n training.\n \"\"\"\n for ix, entry in enumerate(roidb):\n overlaps = entry['gt_overlaps'].toarray()\n crowd_inds = np.where(overlaps.max(axis=1) == -1)[0]\n non_gt_inds = np.where(entry['gt_classes'] == 0)[0]\n if len(crowd_inds) == 0 or len(non_gt_inds) == 0:\n continue\n iscrowd = [int(True) for _ in xrange(len(crowd_inds))]\n crowd_boxes = ds_utils.xyxy_to_xywh(entry['boxes'][crowd_inds, :])\n non_gt_boxes = ds_utils.xyxy_to_xywh(entry['boxes'][non_gt_inds, :])\n ious = COCOmask.iou(non_gt_boxes, crowd_boxes, iscrowd)\n bad_inds = np.where(ious.max(axis=1) > crowd_thresh)[0]\n overlaps[non_gt_inds[bad_inds], :] = -1\n roidb[ix]['gt_overlaps'] = scipy.sparse.csr_matrix(overlaps)\n return roidb\n\nclass coco(imdb):\n def __init__(self, image_set, year):\n imdb.__init__(self, 'coco_' + year + '_' + image_set)\n # COCO specific config options\n self.config = {'top_k' : 2000,\n 'use_salt' : True,\n 'cleanup' : True,\n 'crowd_thresh' : 0.7,\n 'min_size' : 2}\n # name, paths\n self._year = year\n self._image_set = image_set\n self._data_path = osp.join(cfg.DATA_DIR, 'coco')\n # load COCO API, classes, class <-> id mappings\n self._COCO = COCO(self._get_ann_file())\n cats = self._COCO.loadCats(self._COCO.getCatIds())\n self._classes = tuple(['__background__'] + [c['name'] for c in cats])\n self._class_to_ind = dict(zip(self.classes, xrange(self.num_classes)))\n self._class_to_coco_cat_id = dict(zip([c['name'] for c in cats],\n self._COCO.getCatIds()))\n self._image_index = self._load_image_set_index()\n # Default to roidb handler\n self.set_proposal_method('selective_search')\n self.competition_mode(False)\n\n # Some image sets are \"views\" (i.e. subsets) into others.\n # For example, minival2014 is a random 5000 image subset of val2014.\n # This mapping tells us where the view's images and proposals come from.\n self._view_map = {\n 'minival2014' : 'val2014', # 5k val2014 subset\n 'valminusminival2014' : 'val2014', # val2014 \\setminus minival2014\n }\n coco_name = image_set + year # e.g., \"val2014\"\n self._data_name = (self._view_map[coco_name]\n if self._view_map.has_key(coco_name)\n else coco_name)\n # Dataset splits that have ground-truth annotations (test splits\n # do not have gt annotations)\n self._gt_splits = ('train', 'val', 'minival')\n\n def _get_ann_file(self):\n prefix = 'instances' if self._image_set.find('test') == -1 \\\n else 'image_info'\n return osp.join(self._data_path, 'annotations',\n prefix + '_' + self._image_set + self._year + '.json')\n\n def _load_image_set_index(self):\n \"\"\"\n Load image ids.\n \"\"\"\n image_ids = self._COCO.getImgIds()\n return image_ids\n\n def _get_widths(self):\n anns = self._COCO.loadImgs(self._image_index)\n widths = [ann['width'] for ann in anns]\n return widths\n\n def image_path_at(self, i):\n \"\"\"\n Return the absolute path to image i in the image sequence.\n \"\"\"\n return self.image_path_from_index(self._image_index[i])\n\n def image_path_from_index(self, index):\n \"\"\"\n Construct an image path from the image's \"index\" identifier.\n \"\"\"\n # Example image path for index=119993:\n # images/train2014/COCO_train2014_000000119993.jpg\n file_name = ('COCO_' + self._data_name + '_' +\n str(index).zfill(12) + '.jpg')\n image_path = osp.join(self._data_path, 'images',\n self._data_name, file_name)\n assert osp.exists(image_path), \\\n 'Path does not exist: {}'.format(image_path)\n return image_path\n\n def selective_search_roidb(self):\n return self._roidb_from_proposals('selective_search')\n\n def edge_boxes_roidb(self):\n return self._roidb_from_proposals('edge_boxes_AR')\n\n def mcg_roidb(self):\n return self._roidb_from_proposals('MCG')\n\n def _roidb_from_proposals(self, method):\n \"\"\"\n Creates a roidb from pre-computed proposals of a particular methods.\n \"\"\"\n top_k = self.config['top_k']\n cache_file = osp.join(self.cache_path, self.name +\n '_{:s}_top{:d}'.format(method, top_k) +\n '_roidb.pkl')\n\n if osp.exists(cache_file):\n with open(cache_file, 'rb') as fid:\n roidb = cPickle.load(fid)\n print '{:s} {:s} roidb loaded from {:s}'.format(self.name, method,\n cache_file)\n return roidb\n\n if self._image_set in self._gt_splits:\n gt_roidb = self.gt_roidb()\n method_roidb = self._load_proposals(method, gt_roidb)\n roidb = imdb.merge_roidbs(gt_roidb, method_roidb)\n # Make sure we don't use proposals that are contained in crowds\n roidb = _filter_crowd_proposals(roidb, self.config['crowd_thresh'])\n else:\n roidb = self._load_proposals(method, None)\n with open(cache_file, 'wb') as fid:\n cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)\n print 'wrote {:s} roidb to {:s}'.format(method, cache_file)\n return roidb\n\n def _load_proposals(self, method, gt_roidb):\n \"\"\"\n Load pre-computed proposals in the format provided by Jan Hosang:\n http://www.mpi-inf.mpg.de/departments/computer-vision-and-multimodal-\n computing/research/object-recognition-and-scene-understanding/how-\n good-are-detection-proposals-really/\n For MCG, use boxes from http://www.eecs.berkeley.edu/Research/Projects/\n CS/vision/grouping/mcg/ and convert the file layout using\n lib/datasets/tools/mcg_munge.py.\n \"\"\"\n box_list = []\n top_k = self.config['top_k']\n valid_methods = [\n 'MCG',\n 'selective_search',\n 'edge_boxes_AR',\n 'edge_boxes_70']\n assert method in valid_methods\n\n print 'Loading {} boxes'.format(method)\n for i, index in enumerate(self._image_index):\n if i % 1000 == 0:\n print '{:d} / {:d}'.format(i + 1, len(self._image_index))\n\n box_file = osp.join(\n cfg.DATA_DIR, 'coco_proposals', method, 'mat',\n self._get_box_file(index))\n\n raw_data = sio.loadmat(box_file)['boxes']\n boxes = np.maximum(raw_data - 1, 0).astype(np.uint16)\n if method == 'MCG':\n # Boxes from the MCG website are in (y1, x1, y2, x2) order\n boxes = boxes[:, (1, 0, 3, 2)]\n # Remove duplicate boxes and very small boxes and then take top k\n keep = ds_utils.unique_boxes(boxes)\n boxes = boxes[keep, :]\n keep = ds_utils.filter_small_boxes(boxes, self.config['min_size'])\n boxes = boxes[keep, :]\n boxes = boxes[:top_k, :]\n box_list.append(boxes)\n # Sanity check\n im_ann = self._COCO.loadImgs(index)[0]\n width = im_ann['width']\n height = im_ann['height']\n ds_utils.validate_boxes(boxes, width=width, height=height)\n return self.create_roidb_from_box_list(box_list, gt_roidb)\n\n def gt_roidb(self):\n \"\"\"\n Return the database of ground-truth regions of interest.\n This function loads/saves from/to a cache file to speed up future calls.\n \"\"\"\n cache_file = osp.join(self.cache_path, self.name + '_gt_roidb.pkl')\n if osp.exists(cache_file):\n with open(cache_file, 'rb') as fid:\n roidb = cPickle.load(fid)\n print '{} gt roidb loaded from {}'.format(self.name, cache_file)\n return roidb\n\n gt_roidb = [self._load_coco_annotation(index)\n for index in self._image_index]\n\n with open(cache_file, 'wb') as fid:\n cPickle.dump(gt_roidb, fid, cPickle.HIGHEST_PROTOCOL)\n print 'wrote gt roidb to {}'.format(cache_file)\n return gt_roidb\n\n def _load_coco_annotation(self, index):\n \"\"\"\n Loads COCO bounding-box instance annotations. Crowd instances are\n handled by marking their overlaps (with all categories) to -1. This\n overlap value means that crowd \"instances\" are excluded from training.\n \"\"\"\n im_ann = self._COCO.loadImgs(index)[0]\n width = im_ann['width']\n height = im_ann['height']\n\n annIds = self._COCO.getAnnIds(imgIds=index, iscrowd=None)\n objs = self._COCO.loadAnns(annIds)\n # Sanitize bboxes -- some are invalid\n valid_objs = []\n for obj in objs:\n x1 = np.max((0, obj['bbox'][0]))\n y1 = np.max((0, obj['bbox'][1]))\n x2 = np.min((width - 1, x1 + np.max((0, obj['bbox'][2] - 1))))\n y2 = np.min((height - 1, y1 + np.max((0, obj['bbox'][3] - 1))))\n if obj['area'] > 0 and x2 >= x1 and y2 >= y1:\n obj['clean_bbox'] = [x1, y1, x2, y2]\n valid_objs.append(obj)\n objs = valid_objs\n num_objs = len(objs)\n\n boxes = np.zeros((num_objs, 4), dtype=np.uint16)\n gt_classes = np.zeros((num_objs), dtype=np.int32)\n overlaps = np.zeros((num_objs, self.num_classes), dtype=np.float32)\n seg_areas = np.zeros((num_objs), dtype=np.float32)\n\n # Lookup table to map from COCO category ids to our internal class\n # indices\n coco_cat_id_to_class_ind = dict([(self._class_to_coco_cat_id[cls],\n self._class_to_ind[cls])\n for cls in self._classes[1:]])\n\n for ix, obj in enumerate(objs):\n cls = coco_cat_id_to_class_ind[obj['category_id']]\n boxes[ix, :] = obj['clean_bbox']\n gt_classes[ix] = cls\n seg_areas[ix] = obj['area']\n if obj['iscrowd']:\n # Set overlap to -1 for all classes for crowd objects\n # so they will be excluded during training\n overlaps[ix, :] = -1.0\n else:\n overlaps[ix, cls] = 1.0\n\n ds_utils.validate_boxes(boxes, width=width, height=height)\n overlaps = scipy.sparse.csr_matrix(overlaps)\n return {'boxes' : boxes,\n 'gt_classes': gt_classes,\n 'gt_overlaps' : overlaps,\n 'flipped' : False,\n 'seg_areas' : seg_areas}\n\n def _get_box_file(self, index):\n # first 14 chars / first 22 chars / all chars + .mat\n # COCO_val2014_0/COCO_val2014_000000447/COCO_val2014_000000447991.mat\n file_name = ('COCO_' + self._data_name +\n '_' + str(index).zfill(12) + '.mat')\n return osp.join(file_name[:14], file_name[:22], file_name)\n\n def _print_detection_eval_metrics(self, coco_eval):\n IoU_lo_thresh = 0.5\n IoU_hi_thresh = 0.95\n def _get_thr_ind(coco_eval, thr):\n ind = np.where((coco_eval.params.iouThrs > thr - 1e-5) &\n (coco_eval.params.iouThrs < thr + 1e-5))[0][0]\n iou_thr = coco_eval.params.iouThrs[ind]\n assert np.isclose(iou_thr, thr)\n return ind\n\n ind_lo = _get_thr_ind(coco_eval, IoU_lo_thresh)\n ind_hi = _get_thr_ind(coco_eval, IoU_hi_thresh)\n # precision has dims (iou, recall, cls, area range, max dets)\n # area range index 0: all area ranges\n # max dets index 2: 100 per image\n precision = \\\n coco_eval.eval['precision'][ind_lo:(ind_hi + 1), :, :, 0, 2]\n ap_default = np.mean(precision[precision > -1])\n print ('~~~~ Mean and per-category AP @ IoU=[{:.2f},{:.2f}] '\n '~~~~').format(IoU_lo_thresh, IoU_hi_thresh)\n print '{:.1f}'.format(100 * ap_default)\n for cls_ind, cls in enumerate(self.classes):\n if cls == '__background__':\n continue\n # minus 1 because of __background__\n precision = coco_eval.eval['precision'][ind_lo:(ind_hi + 1), :, cls_ind - 1, 0, 2]\n ap = np.mean(precision[precision > -1])\n print '{:.1f}'.format(100 * ap)\n\n print '~~~~ Summary metrics ~~~~'\n coco_eval.summarize()\n\n def _do_detection_eval(self, res_file, output_dir):\n ann_type = 'bbox'\n coco_dt = self._COCO.loadRes(res_file)\n coco_eval = COCOeval(self._COCO, coco_dt)\n coco_eval.params.useSegm = (ann_type == 'segm')\n coco_eval.evaluate()\n coco_eval.accumulate()\n self._print_detection_eval_metrics(coco_eval)\n eval_file = osp.join(output_dir, 'detection_results.pkl')\n with open(eval_file, 'wb') as fid:\n cPickle.dump(coco_eval, fid, cPickle.HIGHEST_PROTOCOL)\n print 'Wrote COCO eval results to: {}'.format(eval_file)\n\n def _coco_results_one_category(self, boxes, cat_id):\n results = []\n for im_ind, index in enumerate(self.image_index):\n dets = boxes[im_ind].astype(np.float)\n if dets == []:\n continue\n scores = dets[:, -1]\n xs = dets[:, 0]\n ys = dets[:, 1]\n ws = dets[:, 2] - xs + 1\n hs = dets[:, 3] - ys + 1\n results.extend(\n [{'image_id' : index,\n 'category_id' : cat_id,\n 'bbox' : [xs[k], ys[k], ws[k], hs[k]],\n 'score' : scores[k]} for k in xrange(dets.shape[0])])\n return results\n\n def _write_coco_results_file(self, all_boxes, res_file):\n # [{\"image_id\": 42,\n # \"category_id\": 18,\n # \"bbox\": [258.15,41.29,348.26,243.78],\n # \"score\": 0.236}, ...]\n results = []\n for cls_ind, cls in enumerate(self.classes):\n if cls == '__background__':\n continue\n print 'Collecting {} results ({:d}/{:d})'.format(cls, cls_ind,\n self.num_classes - 1)\n coco_cat_id = self._class_to_coco_cat_id[cls]\n results.extend(self._coco_results_one_category(all_boxes[cls_ind],\n coco_cat_id))\n print 'Writing results json to {}'.format(res_file)\n with open(res_file, 'w') as fid:\n json.dump(results, fid)\n\n def evaluate_detections(self, all_boxes, output_dir):\n res_file = osp.join(output_dir, ('detections_' +\n self._image_set +\n self._year +\n '_results'))\n if self.config['use_salt']:\n res_file += '_{}'.format(str(uuid.uuid4()))\n res_file += '.json'\n self._write_coco_results_file(all_boxes, res_file)\n # Only do evaluation on non-test sets\n if self._image_set.find('test') == -1:\n self._do_detection_eval(res_file, output_dir)\n # Optionally cleanup results json file\n if self.config['cleanup']:\n os.remove(res_file)\n\n def competition_mode(self, on):\n if on:\n self.config['use_salt'] = False\n self.config['cleanup'] = False\n else:\n self.config['use_salt'] = True\n self.config['cleanup'] = True\n" }, { "path": "lib/datasets/ds_utils.py", "content": "# --------------------------------------------------------\n# Fast/er R-CNN\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\nimport numpy as np\n\ndef unique_boxes(boxes, scale=1.0):\n \"\"\"Return indices of unique boxes.\"\"\"\n v = np.array([1, 1e3, 1e6, 1e9])\n hashes = np.round(boxes * scale).dot(v)\n _, index = np.unique(hashes, return_index=True)\n return np.sort(index)\n\ndef xywh_to_xyxy(boxes):\n \"\"\"Convert [x y w h] box format to [x1 y1 x2 y2] format.\"\"\"\n return np.hstack((boxes[:, 0:2], boxes[:, 0:2] + boxes[:, 2:4] - 1))\n\ndef xyxy_to_xywh(boxes):\n \"\"\"Convert [x1 y1 x2 y2] box format to [x y w h] format.\"\"\"\n return np.hstack((boxes[:, 0:2], boxes[:, 2:4] - boxes[:, 0:2] + 1))\n\ndef validate_boxes(boxes, width=0, height=0):\n \"\"\"Check that a set of boxes are valid.\"\"\"\n x1 = boxes[:, 0]\n y1 = boxes[:, 1]\n x2 = boxes[:, 2]\n y2 = boxes[:, 3]\n assert (x1 >= 0).all()\n assert (y1 >= 0).all()\n assert (x2 >= x1).all()\n assert (y2 >= y1).all()\n assert (x2 < width).all()\n assert (y2 < height).all()\n\ndef filter_small_boxes(boxes, min_size):\n w = boxes[:, 2] - boxes[:, 0]\n h = boxes[:, 3] - boxes[:, 1]\n keep = np.where((w >= min_size) & (h > min_size))[0]\n return keep\n" }, { "path": "lib/datasets/factory.py", "content": "# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\n\"\"\"Factory method for easily getting imdbs by name.\"\"\"\n\n__sets = {}\n\nfrom datasets.pascal_voc import pascal_voc\nfrom datasets.coco import coco\nimport numpy as np\n\n# Set up voc__ using selective search \"fast\" mode\nfor year in ['2007', '2012', '0712']:\n for split in ['train', 'val', 'trainval', 'test']:\n name = 'voc_{}_{}'.format(year, split)\n __sets[name] = (lambda split=split, year=year: pascal_voc(split, year))\n\n# Set up coco_2014_\nfor year in ['2014']:\n for split in ['train', 'val', 'minival', 'valminusminival']:\n name = 'coco_{}_{}'.format(year, split)\n __sets[name] = (lambda split=split, year=year: coco(split, year))\n\n# Set up coco_2015_\nfor year in ['2015']:\n for split in ['test', 'test-dev']:\n name = 'coco_{}_{}'.format(year, split)\n __sets[name] = (lambda split=split, year=year: coco(split, year))\n\ndef get_imdb(name):\n \"\"\"Get an imdb (image database) by name.\"\"\"\n if not __sets.has_key(name):\n raise KeyError('Unknown dataset: {}'.format(name))\n return __sets[name]()\n\ndef list_imdbs():\n \"\"\"List all registered imdbs.\"\"\"\n return __sets.keys()\n" }, { "path": "lib/datasets/imdb.py", "content": "# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\nimport os\nimport os.path as osp\nimport PIL\nfrom utils.cython_bbox import bbox_overlaps\nimport numpy as np\nimport scipy.sparse\nfrom fast_rcnn.config import cfg\n\nclass imdb(object):\n \"\"\"Image database.\"\"\"\n\n def __init__(self, name):\n self._name = name\n self._num_classes = 0\n self._classes = []\n self._image_index = []\n self._obj_proposer = 'selective_search'\n self._roidb = None\n self._roidb_handler = self.default_roidb\n # Use this dict for storing dataset specific config options\n self.config = {}\n\n @property\n def name(self):\n return self._name\n\n @property\n def num_classes(self):\n return len(self._classes)\n\n @property\n def classes(self):\n return self._classes\n\n @property\n def image_index(self):\n return self._image_index\n\n @property\n def roidb_handler(self):\n return self._roidb_handler\n\n @roidb_handler.setter\n def roidb_handler(self, val):\n self._roidb_handler = val\n\n def set_proposal_method(self, method):\n method = eval('self.' + method + '_roidb')\n self.roidb_handler = method\n\n @property\n def roidb(self):\n # A roidb is a list of dictionaries, each with the following keys:\n # boxes\n # gt_overlaps\n # gt_classes\n # flipped\n if self._roidb is not None:\n return self._roidb\n self._roidb = self.roidb_handler()\n return self._roidb\n\n @property\n def cache_path(self):\n cache_path = osp.abspath(osp.join(cfg.DATA_DIR, 'cache'))\n if not os.path.exists(cache_path):\n os.makedirs(cache_path)\n return cache_path\n\n @property\n def num_images(self):\n return len(self.image_index)\n\n def image_path_at(self, i):\n raise NotImplementedError\n\n def default_roidb(self):\n raise NotImplementedError\n\n def evaluate_detections(self, all_boxes, output_dir=None):\n \"\"\"\n all_boxes is a list of length number-of-classes.\n Each list element is a list of length number-of-images.\n Each of those list elements is either an empty list []\n or a numpy array of detection.\n\n all_boxes[class][image] = [] or np.array of shape #dets x 5\n \"\"\"\n raise NotImplementedError\n\n def _get_widths(self):\n return [PIL.Image.open(self.image_path_at(i)).size[0]\n for i in xrange(self.num_images)]\n\n def append_flipped_images(self):\n num_images = self.num_images\n widths = self._get_widths()\n for i in xrange(num_images):\n boxes = self.roidb[i]['boxes'].copy()\n oldx1 = boxes[:, 0].copy()\n oldx2 = boxes[:, 2].copy()\n boxes[:, 0] = widths[i] - oldx2 - 1\n boxes[:, 2] = widths[i] - oldx1 - 1\n assert (boxes[:, 2] >= boxes[:, 0]).all()\n entry = {'boxes' : boxes,\n 'gt_overlaps' : self.roidb[i]['gt_overlaps'],\n 'gt_classes' : self.roidb[i]['gt_classes'],\n 'flipped' : True}\n self.roidb.append(entry)\n self._image_index = self._image_index * 2\n\n def evaluate_recall(self, candidate_boxes=None, thresholds=None,\n area='all', limit=None):\n \"\"\"Evaluate detection proposal recall metrics.\n\n Returns:\n results: dictionary of results with keys\n 'ar': average recall\n 'recalls': vector recalls at each IoU overlap threshold\n 'thresholds': vector of IoU overlap thresholds\n 'gt_overlaps': vector of all ground-truth overlaps\n \"\"\"\n # Record max overlap value for each gt box\n # Return vector of overlap values\n areas = { 'all': 0, 'small': 1, 'medium': 2, 'large': 3,\n '96-128': 4, '128-256': 5, '256-512': 6, '512-inf': 7}\n area_ranges = [ [0**2, 1e5**2], # all\n [0**2, 32**2], # small\n [32**2, 96**2], # medium\n [96**2, 1e5**2], # large\n [96**2, 128**2], # 96-128\n [128**2, 256**2], # 128-256\n [256**2, 512**2], # 256-512\n [512**2, 1e5**2], # 512-inf\n ]\n assert areas.has_key(area), 'unknown area range: {}'.format(area)\n area_range = area_ranges[areas[area]]\n gt_overlaps = np.zeros(0)\n num_pos = 0\n for i in xrange(self.num_images):\n # Checking for max_overlaps == 1 avoids including crowd annotations\n # (...pretty hacking :/)\n max_gt_overlaps = self.roidb[i]['gt_overlaps'].toarray().max(axis=1)\n gt_inds = np.where((self.roidb[i]['gt_classes'] > 0) &\n (max_gt_overlaps == 1))[0]\n gt_boxes = self.roidb[i]['boxes'][gt_inds, :]\n gt_areas = self.roidb[i]['seg_areas'][gt_inds]\n valid_gt_inds = np.where((gt_areas >= area_range[0]) &\n (gt_areas <= area_range[1]))[0]\n gt_boxes = gt_boxes[valid_gt_inds, :]\n num_pos += len(valid_gt_inds)\n\n if candidate_boxes is None:\n # If candidate_boxes is not supplied, the default is to use the\n # non-ground-truth boxes from this roidb\n non_gt_inds = np.where(self.roidb[i]['gt_classes'] == 0)[0]\n boxes = self.roidb[i]['boxes'][non_gt_inds, :]\n else:\n boxes = candidate_boxes[i]\n if boxes.shape[0] == 0:\n continue\n if limit is not None and boxes.shape[0] > limit:\n boxes = boxes[:limit, :]\n\n overlaps = bbox_overlaps(boxes.astype(np.float),\n gt_boxes.astype(np.float))\n\n _gt_overlaps = np.zeros((gt_boxes.shape[0]))\n for j in xrange(gt_boxes.shape[0]):\n # find which proposal box maximally covers each gt box\n argmax_overlaps = overlaps.argmax(axis=0)\n # and get the iou amount of coverage for each gt box\n max_overlaps = overlaps.max(axis=0)\n # find which gt box is 'best' covered (i.e. 'best' = most iou)\n gt_ind = max_overlaps.argmax()\n gt_ovr = max_overlaps.max()\n assert(gt_ovr >= 0)\n # find the proposal box that covers the best covered gt box\n box_ind = argmax_overlaps[gt_ind]\n # record the iou coverage of this gt box\n _gt_overlaps[j] = overlaps[box_ind, gt_ind]\n assert(_gt_overlaps[j] == gt_ovr)\n # mark the proposal box and the gt box as used\n overlaps[box_ind, :] = -1\n overlaps[:, gt_ind] = -1\n # append recorded iou coverage level\n gt_overlaps = np.hstack((gt_overlaps, _gt_overlaps))\n\n gt_overlaps = np.sort(gt_overlaps)\n if thresholds is None:\n step = 0.05\n thresholds = np.arange(0.5, 0.95 + 1e-5, step)\n recalls = np.zeros_like(thresholds)\n # compute recall for each iou threshold\n for i, t in enumerate(thresholds):\n recalls[i] = (gt_overlaps >= t).sum() / float(num_pos)\n # ar = 2 * np.trapz(recalls, thresholds)\n ar = recalls.mean()\n return {'ar': ar, 'recalls': recalls, 'thresholds': thresholds,\n 'gt_overlaps': gt_overlaps}\n\n def create_roidb_from_box_list(self, box_list, gt_roidb):\n assert len(box_list) == self.num_images, \\\n 'Number of boxes must match number of ground-truth images'\n roidb = []\n for i in xrange(self.num_images):\n boxes = box_list[i]\n num_boxes = boxes.shape[0]\n overlaps = np.zeros((num_boxes, self.num_classes), dtype=np.float32)\n\n if gt_roidb is not None and gt_roidb[i]['boxes'].size > 0:\n gt_boxes = gt_roidb[i]['boxes']\n gt_classes = gt_roidb[i]['gt_classes']\n gt_overlaps = bbox_overlaps(boxes.astype(np.float),\n gt_boxes.astype(np.float))\n argmaxes = gt_overlaps.argmax(axis=1)\n maxes = gt_overlaps.max(axis=1)\n I = np.where(maxes > 0)[0]\n overlaps[I, gt_classes[argmaxes[I]]] = maxes[I]\n\n overlaps = scipy.sparse.csr_matrix(overlaps)\n roidb.append({\n 'boxes' : boxes,\n 'gt_classes' : np.zeros((num_boxes,), dtype=np.int32),\n 'gt_overlaps' : overlaps,\n 'flipped' : False,\n 'seg_areas' : np.zeros((num_boxes,), dtype=np.float32),\n })\n return roidb\n\n @staticmethod\n def merge_roidbs(a, b):\n assert len(a) == len(b)\n for i in xrange(len(a)):\n a[i]['boxes'] = np.vstack((a[i]['boxes'], b[i]['boxes']))\n a[i]['gt_classes'] = np.hstack((a[i]['gt_classes'],\n b[i]['gt_classes']))\n a[i]['gt_overlaps'] = scipy.sparse.vstack([a[i]['gt_overlaps'],\n b[i]['gt_overlaps']])\n a[i]['seg_areas'] = np.hstack((a[i]['seg_areas'],\n b[i]['seg_areas']))\n return a\n\n def competition_mode(self, on):\n \"\"\"Turn competition mode on or off.\"\"\"\n pass\n" }, { "path": "lib/datasets/pascal_voc.py", "content": "# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\nimport os\nfrom datasets.imdb import imdb\nimport datasets.ds_utils as ds_utils\nimport xml.etree.ElementTree as ET\nimport numpy as np\nimport scipy.sparse\nimport scipy.io as sio\nimport utils.cython_bbox\nimport cPickle\nimport subprocess\nimport uuid\nfrom voc_eval import voc_eval\nfrom fast_rcnn.config import cfg\n\nclass pascal_voc(imdb):\n def __init__(self, image_set, year, devkit_path=None):\n imdb.__init__(self, 'voc_' + year + '_' + image_set)\n self._year = year\n self._image_set = image_set\n self._devkit_path = self._get_default_path() if devkit_path is None \\\n else devkit_path\n self._data_path = os.path.join(self._devkit_path, 'VOC' + self._year)\n self._classes = ('__background__', # always index 0\n 'aeroplane', 'bicycle', 'bird', 'boat',\n 'bottle', 'bus', 'car', 'cat', 'chair',\n 'cow', 'diningtable', 'dog', 'horse',\n 'motorbike', 'person', 'pottedplant',\n 'sheep', 'sofa', 'train', 'tvmonitor')\n self._class_to_ind = dict(zip(self.classes, xrange(self.num_classes)))\n self._image_ext = '.jpg'\n self._image_index = self._load_image_set_index()\n # Default to roidb handler\n self._roidb_handler = self.selective_search_roidb\n self._salt = str(uuid.uuid4())\n self._comp_id = 'comp4'\n\n # PASCAL specific config options\n self.config = {'cleanup' : True,\n 'use_salt' : True,\n 'use_diff' : False,\n 'matlab_eval' : False,\n 'rpn_file' : None,\n 'min_size' : 2}\n\n assert os.path.exists(self._devkit_path), \\\n 'VOCdevkit path does not exist: {}'.format(self._devkit_path)\n assert os.path.exists(self._data_path), \\\n 'Path does not exist: {}'.format(self._data_path)\n\n def image_path_at(self, i):\n \"\"\"\n Return the absolute path to image i in the image sequence.\n \"\"\"\n return self.image_path_from_index(self._image_index[i])\n\n def image_path_from_index(self, index):\n \"\"\"\n Construct an image path from the image's \"index\" identifier.\n \"\"\"\n image_path = os.path.join(self._data_path, 'JPEGImages',\n index + self._image_ext)\n assert os.path.exists(image_path), \\\n 'Path does not exist: {}'.format(image_path)\n return image_path\n\n def _load_image_set_index(self):\n \"\"\"\n Load the indexes listed in this dataset's image set file.\n \"\"\"\n # Example path to image set file:\n # self._devkit_path + /VOCdevkit2007/VOC2007/ImageSets/Main/val.txt\n image_set_file = os.path.join(self._data_path, 'ImageSets', 'Main',\n self._image_set + '.txt')\n assert os.path.exists(image_set_file), \\\n 'Path does not exist: {}'.format(image_set_file)\n with open(image_set_file) as f:\n image_index = [x.strip() for x in f.readlines()]\n return image_index\n\n def _get_default_path(self):\n \"\"\"\n Return the default path where PASCAL VOC is expected to be installed.\n \"\"\"\n return os.path.join(cfg.DATA_DIR, 'VOCdevkit' + self._year)\n\n def gt_roidb(self):\n \"\"\"\n Return the database of ground-truth regions of interest.\n\n This function loads/saves from/to a cache file to speed up future calls.\n \"\"\"\n cache_file = os.path.join(self.cache_path, self.name + '_gt_roidb.pkl')\n if os.path.exists(cache_file):\n with open(cache_file, 'rb') as fid:\n roidb = cPickle.load(fid)\n print '{} gt roidb loaded from {}'.format(self.name, cache_file)\n return roidb\n\n gt_roidb = [self._load_pascal_annotation(index)\n for index in self.image_index]\n with open(cache_file, 'wb') as fid:\n cPickle.dump(gt_roidb, fid, cPickle.HIGHEST_PROTOCOL)\n print 'wrote gt roidb to {}'.format(cache_file)\n\n return gt_roidb\n\n def selective_search_roidb(self):\n \"\"\"\n Return the database of selective search regions of interest.\n Ground-truth ROIs are also included.\n\n This function loads/saves from/to a cache file to speed up future calls.\n \"\"\"\n cache_file = os.path.join(self.cache_path,\n self.name + '_selective_search_roidb.pkl')\n\n if os.path.exists(cache_file):\n with open(cache_file, 'rb') as fid:\n roidb = cPickle.load(fid)\n print '{} ss roidb loaded from {}'.format(self.name, cache_file)\n return roidb\n\n if int(self._year) == 2007 or self._image_set != 'test':\n gt_roidb = self.gt_roidb()\n ss_roidb = self._load_selective_search_roidb(gt_roidb)\n roidb = imdb.merge_roidbs(gt_roidb, ss_roidb)\n else:\n roidb = self._load_selective_search_roidb(None)\n with open(cache_file, 'wb') as fid:\n cPickle.dump(roidb, fid, cPickle.HIGHEST_PROTOCOL)\n print 'wrote ss roidb to {}'.format(cache_file)\n\n return roidb\n\n def rpn_roidb(self):\n if int(self._year) == 2007 or self._image_set != 'test':\n gt_roidb = self.gt_roidb()\n rpn_roidb = self._load_rpn_roidb(gt_roidb)\n roidb = imdb.merge_roidbs(gt_roidb, rpn_roidb)\n else:\n roidb = self._load_rpn_roidb(None)\n\n return roidb\n\n def _load_rpn_roidb(self, gt_roidb):\n filename = self.config['rpn_file']\n print 'loading {}'.format(filename)\n assert os.path.exists(filename), \\\n 'rpn data not found at: {}'.format(filename)\n with open(filename, 'rb') as f:\n box_list = cPickle.load(f)\n return self.create_roidb_from_box_list(box_list, gt_roidb)\n\n def _load_selective_search_roidb(self, gt_roidb):\n filename = os.path.abspath(os.path.join(cfg.DATA_DIR,\n 'selective_search_data',\n self.name + '.mat'))\n assert os.path.exists(filename), \\\n 'Selective search data not found at: {}'.format(filename)\n raw_data = sio.loadmat(filename)['boxes'].ravel()\n\n box_list = []\n for i in xrange(raw_data.shape[0]):\n boxes = raw_data[i][:, (1, 0, 3, 2)] - 1\n keep = ds_utils.unique_boxes(boxes)\n boxes = boxes[keep, :]\n keep = ds_utils.filter_small_boxes(boxes, self.config['min_size'])\n boxes = boxes[keep, :]\n box_list.append(boxes)\n\n return self.create_roidb_from_box_list(box_list, gt_roidb)\n\n def _load_pascal_annotation(self, index):\n \"\"\"\n Load image and bounding boxes info from XML file in the PASCAL VOC\n format.\n \"\"\"\n filename = os.path.join(self._data_path, 'Annotations', index + '.xml')\n tree = ET.parse(filename)\n objs = tree.findall('object')\n if not self.config['use_diff']:\n # Exclude the samples labeled as difficult\n non_diff_objs = [\n obj for obj in objs if int(obj.find('difficult').text) == 0]\n # if len(non_diff_objs) != len(objs):\n # print 'Removed {} difficult objects'.format(\n # len(objs) - len(non_diff_objs))\n objs = non_diff_objs\n num_objs = len(objs)\n\n boxes = np.zeros((num_objs, 4), dtype=np.uint16)\n gt_classes = np.zeros((num_objs), dtype=np.int32)\n overlaps = np.zeros((num_objs, self.num_classes), dtype=np.float32)\n # \"Seg\" area for pascal is just the box area\n seg_areas = np.zeros((num_objs), dtype=np.float32)\n\n # Load object bounding boxes into a data frame.\n for ix, obj in enumerate(objs):\n bbox = obj.find('bndbox')\n # Make pixel indexes 0-based\n x1 = float(bbox.find('xmin').text) - 1\n y1 = float(bbox.find('ymin').text) - 1\n x2 = float(bbox.find('xmax').text) - 1\n y2 = float(bbox.find('ymax').text) - 1\n cls = self._class_to_ind[obj.find('name').text.lower().strip()]\n boxes[ix, :] = [x1, y1, x2, y2]\n gt_classes[ix] = cls\n overlaps[ix, cls] = 1.0\n seg_areas[ix] = (x2 - x1 + 1) * (y2 - y1 + 1)\n\n overlaps = scipy.sparse.csr_matrix(overlaps)\n\n return {'boxes' : boxes,\n 'gt_classes': gt_classes,\n 'gt_overlaps' : overlaps,\n 'flipped' : False,\n 'seg_areas' : seg_areas}\n\n def _get_comp_id(self):\n comp_id = (self._comp_id + '_' + self._salt if self.config['use_salt']\n else self._comp_id)\n return comp_id\n\n def _get_voc_results_file_template(self):\n # VOCdevkit/results/VOC2007/Main/_det_test_aeroplane.txt\n filename = self._get_comp_id() + '_det_' + self._image_set + '_{:s}.txt'\n path = os.path.join(\n self._devkit_path,\n 'results',\n 'VOC' + self._year,\n 'Main',\n filename)\n return path\n\n def _write_voc_results_file(self, all_boxes):\n for cls_ind, cls in enumerate(self.classes):\n if cls == '__background__':\n continue\n print 'Writing {} VOC results file'.format(cls)\n filename = self._get_voc_results_file_template().format(cls)\n with open(filename, 'wt') as f:\n for im_ind, index in enumerate(self.image_index):\n dets = all_boxes[cls_ind][im_ind]\n if dets == []:\n continue\n # the VOCdevkit expects 1-based indices\n for k in xrange(dets.shape[0]):\n f.write('{:s} {:.3f} {:.1f} {:.1f} {:.1f} {:.1f}\\n'.\n format(index, dets[k, -1],\n dets[k, 0] + 1, dets[k, 1] + 1,\n dets[k, 2] + 1, dets[k, 3] + 1))\n\n def _do_python_eval(self, output_dir = 'output'):\n annopath = os.path.join(\n self._devkit_path,\n 'VOC' + self._year,\n 'Annotations',\n '{:s}.xml')\n imagesetfile = os.path.join(\n self._devkit_path,\n 'VOC' + self._year,\n 'ImageSets',\n 'Main',\n self._image_set + '.txt')\n cachedir = os.path.join(self._devkit_path, 'annotations_cache')\n aps = []\n # The PASCAL VOC metric changed in 2010\n use_07_metric = True if int(self._year) < 2010 else False\n print 'VOC07 metric? ' + ('Yes' if use_07_metric else 'No')\n if not os.path.isdir(output_dir):\n os.mkdir(output_dir)\n for i, cls in enumerate(self._classes):\n if cls == '__background__':\n continue\n filename = self._get_voc_results_file_template().format(cls)\n rec, prec, ap = voc_eval(\n filename, annopath, imagesetfile, cls, cachedir, ovthresh=0.5,\n use_07_metric=use_07_metric)\n aps += [ap]\n print('AP for {} = {:.4f}'.format(cls, ap))\n with open(os.path.join(output_dir, cls + '_pr.pkl'), 'w') as f:\n cPickle.dump({'rec': rec, 'prec': prec, 'ap': ap}, f)\n print('Mean AP = {:.4f}'.format(np.mean(aps)))\n print('~~~~~~~~')\n print('Results:')\n for ap in aps:\n print('{:.3f}'.format(ap))\n print('{:.3f}'.format(np.mean(aps)))\n print('~~~~~~~~')\n print('')\n print('--------------------------------------------------------------')\n print('Results computed with the **unofficial** Python eval code.')\n print('Results should be very close to the official MATLAB eval code.')\n print('Recompute with `./tools/reval.py --matlab ...` for your paper.')\n print('-- Thanks, The Management')\n print('--------------------------------------------------------------')\n\n def _do_matlab_eval(self, output_dir='output'):\n print '-----------------------------------------------------'\n print 'Computing results with the official MATLAB eval code.'\n print '-----------------------------------------------------'\n path = os.path.join(cfg.ROOT_DIR, 'lib', 'datasets',\n 'VOCdevkit-matlab-wrapper')\n cmd = 'cd {} && '.format(path)\n cmd += '{:s} -nodisplay -nodesktop '.format(cfg.MATLAB)\n cmd += '-r \"dbstop if error; '\n cmd += 'voc_eval(\\'{:s}\\',\\'{:s}\\',\\'{:s}\\',\\'{:s}\\'); quit;\"' \\\n .format(self._devkit_path, self._get_comp_id(),\n self._image_set, output_dir)\n print('Running:\\n{}'.format(cmd))\n status = subprocess.call(cmd, shell=True)\n\n def evaluate_detections(self, all_boxes, output_dir):\n self._write_voc_results_file(all_boxes)\n self._do_python_eval(output_dir)\n if self.config['matlab_eval']:\n self._do_matlab_eval(output_dir)\n if self.config['cleanup']:\n for cls in self._classes:\n if cls == '__background__':\n continue\n filename = self._get_voc_results_file_template().format(cls)\n os.remove(filename)\n\n def competition_mode(self, on):\n if on:\n self.config['use_salt'] = False\n self.config['cleanup'] = False\n else:\n self.config['use_salt'] = True\n self.config['cleanup'] = True\n\nif __name__ == '__main__':\n from datasets.pascal_voc import pascal_voc\n d = pascal_voc('trainval', '2007')\n res = d.roidb\n from IPython import embed; embed()\n" }, { "path": "lib/datasets/tools/mcg_munge.py", "content": "import os\nimport sys\n\n\"\"\"Hacky tool to convert file system layout of MCG boxes downloaded from\nhttp://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/mcg/\nso that it's consistent with those computed by Jan Hosang (see:\nhttp://www.mpi-inf.mpg.de/departments/computer-vision-and-multimodal-\n computing/research/object-recognition-and-scene-understanding/how-\n good-are-detection-proposals-really/)\n\nNB: Boxes from the MCG website are in (y1, x1, y2, x2) order.\nBoxes from Hosang et al. are in (x1, y1, x2, y2) order.\n\"\"\"\n\ndef munge(src_dir):\n # stored as: ./MCG-COCO-val2014-boxes/COCO_val2014_000000193401.mat\n # want: ./MCG/mat/COCO_val2014_0/COCO_val2014_000000141/COCO_val2014_000000141334.mat\n\n files = os.listdir(src_dir)\n for fn in files:\n base, ext = os.path.splitext(fn)\n # first 14 chars / first 22 chars / all chars + .mat\n # COCO_val2014_0/COCO_val2014_000000447/COCO_val2014_000000447991.mat\n first = base[:14]\n second = base[:22]\n dst_dir = os.path.join('MCG', 'mat', first, second)\n if not os.path.exists(dst_dir):\n os.makedirs(dst_dir)\n src = os.path.join(src_dir, fn)\n dst = os.path.join(dst_dir, fn)\n print 'MV: {} -> {}'.format(src, dst)\n os.rename(src, dst)\n\nif __name__ == '__main__':\n # src_dir should look something like:\n # src_dir = 'MCG-COCO-val2014-boxes'\n src_dir = sys.argv[1]\n munge(src_dir)\n" }, { "path": "lib/datasets/voc_eval.py", "content": "# --------------------------------------------------------\n# Fast/er R-CNN\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Bharath Hariharan\n# --------------------------------------------------------\n\nimport xml.etree.ElementTree as ET\nimport os\nimport cPickle\nimport numpy as np\n\ndef parse_rec(filename):\n \"\"\" Parse a PASCAL VOC xml file \"\"\"\n tree = ET.parse(filename)\n objects = []\n for obj in tree.findall('object'):\n obj_struct = {}\n obj_struct['name'] = obj.find('name').text\n obj_struct['pose'] = obj.find('pose').text\n obj_struct['truncated'] = int(obj.find('truncated').text)\n obj_struct['difficult'] = int(obj.find('difficult').text)\n bbox = obj.find('bndbox')\n obj_struct['bbox'] = [int(bbox.find('xmin').text),\n int(bbox.find('ymin').text),\n int(bbox.find('xmax').text),\n int(bbox.find('ymax').text)]\n objects.append(obj_struct)\n\n return objects\n\ndef voc_ap(rec, prec, use_07_metric=False):\n \"\"\" ap = voc_ap(rec, prec, [use_07_metric])\n Compute VOC AP given precision and recall.\n If use_07_metric is true, uses the\n VOC 07 11 point method (default:False).\n \"\"\"\n if use_07_metric:\n # 11 point metric\n ap = 0.\n for t in np.arange(0., 1.1, 0.1):\n if np.sum(rec >= t) == 0:\n p = 0\n else:\n p = np.max(prec[rec >= t])\n ap = ap + p / 11.\n else:\n # correct AP calculation\n # first append sentinel values at the end\n mrec = np.concatenate(([0.], rec, [1.]))\n mpre = np.concatenate(([0.], prec, [0.]))\n\n # compute the precision envelope\n for i in range(mpre.size - 1, 0, -1):\n mpre[i - 1] = np.maximum(mpre[i - 1], mpre[i])\n\n # to calculate area under PR curve, look for points\n # where X axis (recall) changes value\n i = np.where(mrec[1:] != mrec[:-1])[0]\n\n # and sum (\\Delta recall) * prec\n ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1])\n return ap\n\ndef voc_eval(detpath,\n annopath,\n imagesetfile,\n classname,\n cachedir,\n ovthresh=0.5,\n use_07_metric=False):\n \"\"\"rec, prec, ap = voc_eval(detpath,\n annopath,\n imagesetfile,\n classname,\n [ovthresh],\n [use_07_metric])\n\n Top level function that does the PASCAL VOC evaluation.\n\n detpath: Path to detections\n detpath.format(classname) should produce the detection results file.\n annopath: Path to annotations\n annopath.format(imagename) should be the xml annotations file.\n imagesetfile: Text file containing the list of images, one image per line.\n classname: Category name (duh)\n cachedir: Directory for caching the annotations\n [ovthresh]: Overlap threshold (default = 0.5)\n [use_07_metric]: Whether to use VOC07's 11 point AP computation\n (default False)\n \"\"\"\n # assumes detections are in detpath.format(classname)\n # assumes annotations are in annopath.format(imagename)\n # assumes imagesetfile is a text file with each line an image name\n # cachedir caches the annotations in a pickle file\n\n # first load gt\n if not os.path.isdir(cachedir):\n os.mkdir(cachedir)\n cachefile = os.path.join(cachedir, 'annots.pkl')\n # read list of images\n with open(imagesetfile, 'r') as f:\n lines = f.readlines()\n imagenames = [x.strip() for x in lines]\n\n if not os.path.isfile(cachefile):\n # load annots\n recs = {}\n for i, imagename in enumerate(imagenames):\n recs[imagename] = parse_rec(annopath.format(imagename))\n if i % 100 == 0:\n print 'Reading annotation for {:d}/{:d}'.format(\n i + 1, len(imagenames))\n # save\n print 'Saving cached annotations to {:s}'.format(cachefile)\n with open(cachefile, 'w') as f:\n cPickle.dump(recs, f)\n else:\n # load\n with open(cachefile, 'r') as f:\n recs = cPickle.load(f)\n\n # extract gt objects for this class\n class_recs = {}\n npos = 0\n for imagename in imagenames:\n R = [obj for obj in recs[imagename] if obj['name'] == classname]\n bbox = np.array([x['bbox'] for x in R])\n difficult = np.array([x['difficult'] for x in R]).astype(np.bool)\n det = [False] * len(R)\n npos = npos + sum(~difficult)\n class_recs[imagename] = {'bbox': bbox,\n 'difficult': difficult,\n 'det': det}\n\n # read dets\n detfile = detpath.format(classname)\n with open(detfile, 'r') as f:\n lines = f.readlines()\n\n splitlines = [x.strip().split(' ') for x in lines]\n image_ids = [x[0] for x in splitlines]\n confidence = np.array([float(x[1]) for x in splitlines])\n BB = np.array([[float(z) for z in x[2:]] for x in splitlines])\n\n # sort by confidence\n sorted_ind = np.argsort(-confidence)\n sorted_scores = np.sort(-confidence)\n BB = BB[sorted_ind, :]\n image_ids = [image_ids[x] for x in sorted_ind]\n\n # go down dets and mark TPs and FPs\n nd = len(image_ids)\n tp = np.zeros(nd)\n fp = np.zeros(nd)\n for d in range(nd):\n R = class_recs[image_ids[d]]\n bb = BB[d, :].astype(float)\n ovmax = -np.inf\n BBGT = R['bbox'].astype(float)\n\n if BBGT.size > 0:\n # compute overlaps\n # intersection\n ixmin = np.maximum(BBGT[:, 0], bb[0])\n iymin = np.maximum(BBGT[:, 1], bb[1])\n ixmax = np.minimum(BBGT[:, 2], bb[2])\n iymax = np.minimum(BBGT[:, 3], bb[3])\n iw = np.maximum(ixmax - ixmin + 1., 0.)\n ih = np.maximum(iymax - iymin + 1., 0.)\n inters = iw * ih\n\n # union\n uni = ((bb[2] - bb[0] + 1.) * (bb[3] - bb[1] + 1.) +\n (BBGT[:, 2] - BBGT[:, 0] + 1.) *\n (BBGT[:, 3] - BBGT[:, 1] + 1.) - inters)\n\n overlaps = inters / uni\n ovmax = np.max(overlaps)\n jmax = np.argmax(overlaps)\n\n if ovmax > ovthresh:\n if not R['difficult'][jmax]:\n if not R['det'][jmax]:\n tp[d] = 1.\n R['det'][jmax] = 1\n else:\n fp[d] = 1.\n else:\n fp[d] = 1.\n\n # compute precision recall\n fp = np.cumsum(fp)\n tp = np.cumsum(tp)\n rec = tp / float(npos)\n # avoid divide by zero in case the first detection matches a difficult\n # ground truth\n prec = tp / np.maximum(tp + fp, np.finfo(np.float64).eps)\n ap = voc_ap(rec, prec, use_07_metric)\n\n return rec, prec, ap\n" }, { "path": "lib/fast_rcnn/__init__.py", "content": "# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n" }, { "path": "lib/fast_rcnn/bbox_transform.py", "content": "# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\nimport numpy as np\n\ndef bbox_transform(ex_rois, gt_rois):\n ex_widths = ex_rois[:, 2] - ex_rois[:, 0] + 1.0\n ex_heights = ex_rois[:, 3] - ex_rois[:, 1] + 1.0\n ex_ctr_x = ex_rois[:, 0] + 0.5 * ex_widths\n ex_ctr_y = ex_rois[:, 1] + 0.5 * ex_heights\n\n gt_widths = gt_rois[:, 2] - gt_rois[:, 0] + 1.0\n gt_heights = gt_rois[:, 3] - gt_rois[:, 1] + 1.0\n gt_ctr_x = gt_rois[:, 0] + 0.5 * gt_widths\n gt_ctr_y = gt_rois[:, 1] + 0.5 * gt_heights\n\n targets_dx = (gt_ctr_x - ex_ctr_x) / ex_widths\n targets_dy = (gt_ctr_y - ex_ctr_y) / ex_heights\n targets_dw = np.log(gt_widths / ex_widths)\n targets_dh = np.log(gt_heights / ex_heights)\n\n targets = np.vstack(\n (targets_dx, targets_dy, targets_dw, targets_dh)).transpose()\n return targets\n\ndef bbox_transform_inv(boxes, deltas):\n if boxes.shape[0] == 0:\n return np.zeros((0, deltas.shape[1]), dtype=deltas.dtype)\n\n boxes = boxes.astype(deltas.dtype, copy=False)\n\n widths = boxes[:, 2] - boxes[:, 0] + 1.0\n heights = boxes[:, 3] - boxes[:, 1] + 1.0\n ctr_x = boxes[:, 0] + 0.5 * widths\n ctr_y = boxes[:, 1] + 0.5 * heights\n\n dx = deltas[:, 0::4]\n dy = deltas[:, 1::4]\n dw = deltas[:, 2::4]\n dh = deltas[:, 3::4]\n\n pred_ctr_x = dx * widths[:, np.newaxis] + ctr_x[:, np.newaxis]\n pred_ctr_y = dy * heights[:, np.newaxis] + ctr_y[:, np.newaxis]\n pred_w = np.exp(dw) * widths[:, np.newaxis]\n pred_h = np.exp(dh) * heights[:, np.newaxis]\n\n pred_boxes = np.zeros(deltas.shape, dtype=deltas.dtype)\n # x1\n pred_boxes[:, 0::4] = pred_ctr_x - 0.5 * pred_w\n # y1\n pred_boxes[:, 1::4] = pred_ctr_y - 0.5 * pred_h\n # x2\n pred_boxes[:, 2::4] = pred_ctr_x + 0.5 * pred_w\n # y2\n pred_boxes[:, 3::4] = pred_ctr_y + 0.5 * pred_h\n\n return pred_boxes\n\ndef clip_boxes(boxes, im_shape):\n \"\"\"\n Clip boxes to image boundaries.\n \"\"\"\n\n # x1 >= 0\n boxes[:, 0::4] = np.maximum(np.minimum(boxes[:, 0::4], im_shape[1] - 1), 0)\n # y1 >= 0\n boxes[:, 1::4] = np.maximum(np.minimum(boxes[:, 1::4], im_shape[0] - 1), 0)\n # x2 < im_shape[1]\n boxes[:, 2::4] = np.maximum(np.minimum(boxes[:, 2::4], im_shape[1] - 1), 0)\n # y2 < im_shape[0]\n boxes[:, 3::4] = np.maximum(np.minimum(boxes[:, 3::4], im_shape[0] - 1), 0)\n return boxes\n" }, { "path": "lib/fast_rcnn/config.py", "content": "# --------------------------------------------------------\n# Fast R-CNN\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\n\"\"\"Fast R-CNN config system.\n\nThis file specifies default config options for Fast R-CNN. You should not\nchange values in this file. Instead, you should write a config file (in yaml)\nand use cfg_from_file(yaml_file) to load it and override the default options.\n\nMost tools in $ROOT/tools take a --cfg option to specify an override file.\n - See tools/{train,test}_net.py for example code that uses cfg_from_file()\n - See experiments/cfgs/*.yml for example YAML config override files\n\"\"\"\n\nimport os\nimport os.path as osp\nimport numpy as np\n# `pip install easydict` if you don't have it\nfrom easydict import EasyDict as edict\n\n__C = edict()\n# Consumers can get config by:\n# from fast_rcnn_config import cfg\ncfg = __C\n\n#\n# Training options\n#\n\n__C.TRAIN = edict()\n\n# Scales to use during training (can list multiple scales)\n# Each scale is the pixel size of an image's shortest side\n__C.TRAIN.SCALES = (600,)\n\n# Max pixel size of the longest side of a scaled input image\n__C.TRAIN.MAX_SIZE = 1000\n\n# Images to use per minibatch\n__C.TRAIN.IMS_PER_BATCH = 2\n\n# Minibatch size (number of regions of interest [ROIs])\n__C.TRAIN.BATCH_SIZE = 128\n\n# Fraction of minibatch that is labeled foreground (i.e. class > 0)\n__C.TRAIN.FG_FRACTION = 0.25\n\n# Overlap threshold for a ROI to be considered foreground (if >= FG_THRESH)\n__C.TRAIN.FG_THRESH = 0.5\n\n# Overlap threshold for a ROI to be considered background (class = 0 if\n# overlap in [LO, HI))\n__C.TRAIN.BG_THRESH_HI = 0.5\n__C.TRAIN.BG_THRESH_LO = 0.1\n\n# Use horizontally-flipped images during training?\n__C.TRAIN.USE_FLIPPED = True\n\n# Train bounding-box regressors\n__C.TRAIN.BBOX_REG = True\n\n# Overlap required between a ROI and ground-truth box in order for that ROI to\n# be used as a bounding-box regression training example\n__C.TRAIN.BBOX_THRESH = 0.5\n\n# Iterations between snapshots\n__C.TRAIN.SNAPSHOT_ITERS = 10000\n\n# solver.prototxt specifies the snapshot path prefix, this adds an optional\n# infix to yield the path: [_]_iters_XYZ.caffemodel\n__C.TRAIN.SNAPSHOT_INFIX = ''\n\n# Use a prefetch thread in roi_data_layer.layer\n# So far I haven't found this useful; likely more engineering work is required\n__C.TRAIN.USE_PREFETCH = False\n\n# Normalize the targets (subtract empirical mean, divide by empirical stddev)\n__C.TRAIN.BBOX_NORMALIZE_TARGETS = True\n# Deprecated (inside weights)\n__C.TRAIN.BBOX_INSIDE_WEIGHTS = (1.0, 1.0, 1.0, 1.0)\n# Normalize the targets using \"precomputed\" (or made up) means and stdevs\n# (BBOX_NORMALIZE_TARGETS must also be True)\n__C.TRAIN.BBOX_NORMALIZE_TARGETS_PRECOMPUTED = False\n__C.TRAIN.BBOX_NORMALIZE_MEANS = (0.0, 0.0, 0.0, 0.0)\n__C.TRAIN.BBOX_NORMALIZE_STDS = (0.1, 0.1, 0.2, 0.2)\n\n# Train using these proposals\n__C.TRAIN.PROPOSAL_METHOD = 'selective_search'\n\n# Make minibatches from images that have similar aspect ratios (i.e. both\n# tall and thin or both short and wide) in order to avoid wasting computation\n# on zero-padding.\n__C.TRAIN.ASPECT_GROUPING = True\n\n# Use RPN to detect objects\n__C.TRAIN.HAS_RPN = False\n# IOU >= thresh: positive example\n__C.TRAIN.RPN_POSITIVE_OVERLAP = 0.7\n# IOU < thresh: negative example\n__C.TRAIN.RPN_NEGATIVE_OVERLAP = 0.3\n# If an anchor statisfied by positive and negative conditions set to negative\n__C.TRAIN.RPN_CLOBBER_POSITIVES = False\n# Max number of foreground examples\n__C.TRAIN.RPN_FG_FRACTION = 0.5\n# Total number of examples\n__C.TRAIN.RPN_BATCHSIZE = 256\n# NMS threshold used on RPN proposals\n__C.TRAIN.RPN_NMS_THRESH = 0.7\n# Number of top scoring boxes to keep before apply NMS to RPN proposals\n__C.TRAIN.RPN_PRE_NMS_TOP_N = 12000\n# Number of top scoring boxes to keep after applying NMS to RPN proposals\n__C.TRAIN.RPN_POST_NMS_TOP_N = 2000\n# Proposal height and width both need to be greater than RPN_MIN_SIZE (at orig image scale)\n__C.TRAIN.RPN_MIN_SIZE = 16\n# Deprecated (outside weights)\n__C.TRAIN.RPN_BBOX_INSIDE_WEIGHTS = (1.0, 1.0, 1.0, 1.0)\n# Give the positive RPN examples weight of p * 1 / {num positives}\n# and give negatives a weight of (1 - p)\n# Set to -1.0 to use uniform example weighting\n__C.TRAIN.RPN_POSITIVE_WEIGHT = -1.0\n\n# Parameters for \"Online Hard-example Mining Algorithm\"\n__C.TRAIN.USE_OHEM = False\n# For diversity and de-duplication\n__C.TRAIN.OHEM_USE_NMS = True\n__C.TRAIN.OHEM_NMS_THRESH = 0.7\n\n#\n# Testing options\n#\n\n__C.TEST = edict()\n\n# Scales to use during testing (can list multiple scales)\n# Each scale is the pixel size of an image's shortest side\n__C.TEST.SCALES = (600,)\n\n# Max pixel size of the longest side of a scaled input image\n__C.TEST.MAX_SIZE = 1000\n\n# Overlap threshold used for non-maximum suppression (suppress boxes with\n# IoU >= this threshold)\n__C.TEST.NMS = 0.3\n\n# Experimental: treat the (K+1) units in the cls_score layer as linear\n# predictors (trained, eg, with one-vs-rest SVMs).\n__C.TEST.SVM = False\n\n# Test using bounding-box regressors\n__C.TEST.BBOX_REG = True\n\n# Propose boxes\n__C.TEST.HAS_RPN = False\n\n# Test using these proposals\n__C.TEST.PROPOSAL_METHOD = 'selective_search'\n\n## NMS threshold used on RPN proposals\n__C.TEST.RPN_NMS_THRESH = 0.7\n## Number of top scoring boxes to keep before apply NMS to RPN proposals\n__C.TEST.RPN_PRE_NMS_TOP_N = 6000\n## Number of top scoring boxes to keep after applying NMS to RPN proposals\n__C.TEST.RPN_POST_NMS_TOP_N = 300\n# Proposal height and width both need to be greater than RPN_MIN_SIZE (at orig image scale)\n__C.TEST.RPN_MIN_SIZE = 16\n\n\n#\n# MISC\n#\n\n# The mapping from image coordinates to feature map coordinates might cause\n# some boxes that are distinct in image space to become identical in feature\n# coordinates. If DEDUP_BOXES > 0, then DEDUP_BOXES is used as the scale factor\n# for identifying duplicate boxes.\n# 1/16 is correct for {Alex,Caffe}Net, VGG_CNN_M_1024, and VGG16\n__C.DEDUP_BOXES = 1./16.\n\n# Pixel mean values (BGR order) as a (1, 1, 3) array\n# We use the same pixel mean for all networks even though it's not exactly what\n# they were trained with\n__C.PIXEL_MEANS = np.array([[[102.9801, 115.9465, 122.7717]]])\n\n# For reproducibility\n__C.RNG_SEED = 3\n\n# A small number that's used many times\n__C.EPS = 1e-14\n\n# Root directory of project\n__C.ROOT_DIR = osp.abspath(osp.join(osp.dirname(__file__), '..', '..'))\n\n# Data directory\n__C.DATA_DIR = osp.abspath(osp.join(__C.ROOT_DIR, 'data'))\n\n# Model directory\n__C.MODELS_DIR = osp.abspath(osp.join(__C.ROOT_DIR, 'models', 'pascal_voc'))\n\n# Name (or path to) the matlab executable\n__C.MATLAB = 'matlab'\n\n# Place outputs under an experiments directory\n__C.EXP_DIR = 'default'\n\n# Use GPU implementation of non-maximum suppression\n__C.USE_GPU_NMS = True\n\n# Default GPU device id\n__C.GPU_ID = 0\n\n\ndef get_output_dir(imdb, net=None):\n \"\"\"Return the directory where experimental artifacts are placed.\n If the directory does not exist, it is created.\n\n A canonical path is built using the name from an imdb and a network\n (if not None).\n \"\"\"\n outdir = osp.abspath(osp.join(__C.ROOT_DIR, 'output', __C.EXP_DIR, imdb.name))\n if net is not None:\n outdir = osp.join(outdir, net.name)\n if not os.path.exists(outdir):\n os.makedirs(outdir)\n return outdir\n\ndef _merge_a_into_b(a, b):\n \"\"\"Merge config dictionary a into config dictionary b, clobbering the\n options in b whenever they are also specified in a.\n \"\"\"\n if type(a) is not edict:\n return\n\n for k, v in a.iteritems():\n # a must specify keys that are in b\n if not b.has_key(k):\n raise KeyError('{} is not a valid config key'.format(k))\n\n # the types must match, too\n old_type = type(b[k])\n if old_type is not type(v):\n if isinstance(b[k], np.ndarray):\n v = np.array(v, dtype=b[k].dtype)\n else:\n raise ValueError(('Type mismatch ({} vs. {}) '\n 'for config key: {}').format(type(b[k]),\n type(v), k))\n\n # recursively merge dicts\n if type(v) is edict:\n try:\n _merge_a_into_b(a[k], b[k])\n except:\n print('Error under config key: {}'.format(k))\n raise\n else:\n b[k] = v\n\ndef cfg_from_file(filename):\n \"\"\"Load a config file and merge it into the default options.\"\"\"\n import yaml\n with open(filename, 'r') as f:\n yaml_cfg = edict(yaml.load(f))\n\n _merge_a_into_b(yaml_cfg, __C)\n\ndef cfg_from_list(cfg_list):\n \"\"\"Set config keys via list (e.g., from command line).\"\"\"\n from ast import literal_eval\n assert len(cfg_list) % 2 == 0\n for k, v in zip(cfg_list[0::2], cfg_list[1::2]):\n key_list = k.split('.')\n d = __C\n for subkey in key_list[:-1]:\n assert d.has_key(subkey)\n d = d[subkey]\n subkey = key_list[-1]\n assert d.has_key(subkey)\n try:\n value = literal_eval(v)\n except:\n # handle the case when v is a string literal\n value = v\n assert type(value) == type(d[subkey]), \\\n 'type {} does not match original type {}'.format(\n type(value), type(d[subkey]))\n d[subkey] = value\n" }, { "path": "lib/fast_rcnn/nms_wrapper.py", "content": "# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\nfrom fast_rcnn.config import cfg\nfrom nms.gpu_nms import gpu_nms\nfrom nms.cpu_nms import cpu_nms\n\ndef nms(dets, thresh, force_cpu=False):\n \"\"\"Dispatch to either CPU or GPU NMS implementations.\"\"\"\n\n if dets.shape[0] == 0:\n return []\n if cfg.USE_GPU_NMS and not force_cpu:\n return gpu_nms(dets, thresh, device_id=cfg.GPU_ID)\n else:\n return cpu_nms(dets, thresh)\n" }, { "path": "lib/fast_rcnn/test.py", "content": "# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\n\"\"\"Test a Fast R-CNN network on an imdb (image database).\"\"\"\n\nfrom fast_rcnn.config import cfg, get_output_dir\nfrom fast_rcnn.bbox_transform import clip_boxes, bbox_transform_inv\nimport argparse\nfrom utils.timer import Timer\nimport numpy as np\nimport cv2\nimport caffe\nfrom fast_rcnn.nms_wrapper import nms\nimport cPickle\nfrom utils.blob import im_list_to_blob\nimport os\n\ndef _get_image_blob(im):\n \"\"\"Converts an image into a network input.\n\n Arguments:\n im (ndarray): a color image in BGR order\n\n Returns:\n blob (ndarray): a data blob holding an image pyramid\n im_scale_factors (list): list of image scales (relative to im) used\n in the image pyramid\n \"\"\"\n im_orig = im.astype(np.float32, copy=True)\n im_orig -= cfg.PIXEL_MEANS\n\n im_shape = im_orig.shape\n im_size_min = np.min(im_shape[0:2])\n im_size_max = np.max(im_shape[0:2])\n\n processed_ims = []\n im_scale_factors = []\n\n for target_size in cfg.TEST.SCALES:\n im_scale = float(target_size) / float(im_size_min)\n # Prevent the biggest axis from being more than MAX_SIZE\n if np.round(im_scale * im_size_max) > cfg.TEST.MAX_SIZE:\n im_scale = float(cfg.TEST.MAX_SIZE) / float(im_size_max)\n im = cv2.resize(im_orig, None, None, fx=im_scale, fy=im_scale,\n interpolation=cv2.INTER_LINEAR)\n im_scale_factors.append(im_scale)\n processed_ims.append(im)\n\n # Create a blob to hold the input images\n blob = im_list_to_blob(processed_ims)\n\n return blob, np.array(im_scale_factors)\n\ndef _get_rois_blob(im_rois, im_scale_factors):\n \"\"\"Converts RoIs into network inputs.\n\n Arguments:\n im_rois (ndarray): R x 4 matrix of RoIs in original image coordinates\n im_scale_factors (list): scale factors as returned by _get_image_blob\n\n Returns:\n blob (ndarray): R x 5 matrix of RoIs in the image pyramid\n \"\"\"\n rois, levels = _project_im_rois(im_rois, im_scale_factors)\n rois_blob = np.hstack((levels, rois))\n return rois_blob.astype(np.float32, copy=False)\n\ndef _project_im_rois(im_rois, scales):\n \"\"\"Project image RoIs into the image pyramid built by _get_image_blob.\n\n Arguments:\n im_rois (ndarray): R x 4 matrix of RoIs in original image coordinates\n scales (list): scale factors as returned by _get_image_blob\n\n Returns:\n rois (ndarray): R x 4 matrix of projected RoI coordinates\n levels (list): image pyramid levels used by each projected RoI\n \"\"\"\n im_rois = im_rois.astype(np.float, copy=False)\n\n if len(scales) > 1:\n widths = im_rois[:, 2] - im_rois[:, 0] + 1\n heights = im_rois[:, 3] - im_rois[:, 1] + 1\n\n areas = widths * heights\n scaled_areas = areas[:, np.newaxis] * (scales[np.newaxis, :] ** 2)\n diff_areas = np.abs(scaled_areas - 224 * 224)\n levels = diff_areas.argmin(axis=1)[:, np.newaxis]\n else:\n levels = np.zeros((im_rois.shape[0], 1), dtype=np.int)\n\n rois = im_rois * scales[levels]\n\n return rois, levels\n\ndef _get_blobs(im, rois):\n \"\"\"Convert an image and RoIs within that image into network inputs.\"\"\"\n blobs = {'data' : None, 'rois' : None}\n blobs['data'], im_scale_factors = _get_image_blob(im)\n if not cfg.TEST.HAS_RPN:\n blobs['rois'] = _get_rois_blob(rois, im_scale_factors)\n return blobs, im_scale_factors\n\ndef im_detect(net, im, boxes=None):\n \"\"\"Detect object classes in an image given object proposals.\n\n Arguments:\n net (caffe.Net): Fast R-CNN network to use\n im (ndarray): color image to test (in BGR order)\n boxes (ndarray): R x 4 array of object proposals or None (for RPN)\n\n Returns:\n scores (ndarray): R x K array of object class scores (K includes\n background as object category 0)\n boxes (ndarray): R x (4*K) array of predicted bounding boxes\n \"\"\"\n blobs, im_scales = _get_blobs(im, boxes)\n\n # When mapping from image ROIs to feature map ROIs, there's some aliasing\n # (some distinct image ROIs get mapped to the same feature ROI).\n # Here, we identify duplicate feature ROIs, so we only compute features\n # on the unique subset.\n if cfg.DEDUP_BOXES > 0 and not cfg.TEST.HAS_RPN:\n v = np.array([1, 1e3, 1e6, 1e9, 1e12])\n hashes = np.round(blobs['rois'] * cfg.DEDUP_BOXES).dot(v)\n _, index, inv_index = np.unique(hashes, return_index=True,\n return_inverse=True)\n blobs['rois'] = blobs['rois'][index, :]\n boxes = boxes[index, :]\n\n if cfg.TEST.HAS_RPN:\n im_blob = blobs['data']\n blobs['im_info'] = np.array(\n [[im_blob.shape[2], im_blob.shape[3], im_scales[0]]],\n dtype=np.float32)\n\n # reshape network inputs\n net.blobs['data'].reshape(*(blobs['data'].shape))\n if cfg.TEST.HAS_RPN:\n net.blobs['im_info'].reshape(*(blobs['im_info'].shape))\n else:\n net.blobs['rois'].reshape(*(blobs['rois'].shape))\n\n # do forward\n forward_kwargs = {'data': blobs['data'].astype(np.float32, copy=False)}\n if cfg.TEST.HAS_RPN:\n forward_kwargs['im_info'] = blobs['im_info'].astype(np.float32, copy=False)\n else:\n forward_kwargs['rois'] = blobs['rois'].astype(np.float32, copy=False)\n blobs_out = net.forward(**forward_kwargs)\n\n if cfg.TEST.HAS_RPN:\n assert len(im_scales) == 1, \"Only single-image batch implemented\"\n rois = net.blobs['rois'].data.copy()\n # unscale back to raw image space\n boxes = rois[:, 1:5] / im_scales[0]\n\n if cfg.TEST.SVM:\n # use the raw scores before softmax under the assumption they\n # were trained as linear SVMs\n scores = net.blobs['cls_score'].data\n else:\n # use softmax estimated probabilities\n scores = blobs_out['cls_prob']\n\n if cfg.TEST.BBOX_REG:\n # Apply bounding-box regression deltas\n box_deltas = blobs_out['bbox_pred']\n pred_boxes = bbox_transform_inv(boxes, box_deltas)\n pred_boxes = clip_boxes(pred_boxes, im.shape)\n else:\n # Simply repeat the boxes, once for each class\n pred_boxes = np.tile(boxes, (1, scores.shape[1]))\n\n if cfg.DEDUP_BOXES > 0 and not cfg.TEST.HAS_RPN:\n # Map scores and predictions back to the original set of boxes\n scores = scores[inv_index, :]\n pred_boxes = pred_boxes[inv_index, :]\n\n return scores, pred_boxes\n\ndef vis_detections(im, class_name, dets, thresh=0.3):\n \"\"\"Visual debugging of detections.\"\"\"\n import matplotlib.pyplot as plt\n im = im[:, :, (2, 1, 0)]\n for i in xrange(np.minimum(10, dets.shape[0])):\n bbox = dets[i, :4]\n score = dets[i, -1]\n if score > thresh:\n plt.cla()\n plt.imshow(im)\n plt.gca().add_patch(\n plt.Rectangle((bbox[0], bbox[1]),\n bbox[2] - bbox[0],\n bbox[3] - bbox[1], fill=False,\n edgecolor='g', linewidth=3)\n )\n plt.title('{} {:.3f}'.format(class_name, score))\n plt.show()\n\ndef apply_nms(all_boxes, thresh):\n \"\"\"Apply non-maximum suppression to all predicted boxes output by the\n test_net method.\n \"\"\"\n num_classes = len(all_boxes)\n num_images = len(all_boxes[0])\n nms_boxes = [[[] for _ in xrange(num_images)]\n for _ in xrange(num_classes)]\n for cls_ind in xrange(num_classes):\n for im_ind in xrange(num_images):\n dets = all_boxes[cls_ind][im_ind]\n if dets == []:\n continue\n # CPU NMS is much faster than GPU NMS when the number of boxes\n # is relative small (e.g., < 10k)\n # TODO(rbg): autotune NMS dispatch\n keep = nms(dets, thresh, force_cpu=True)\n if len(keep) == 0:\n continue\n nms_boxes[cls_ind][im_ind] = dets[keep, :].copy()\n return nms_boxes\n\ndef test_net(net, imdb, max_per_image=100, thresh=0.05, vis=False):\n \"\"\"Test a Fast R-CNN network on an image database.\"\"\"\n num_images = len(imdb.image_index)\n # all detections are collected into:\n # all_boxes[cls][image] = N x 5 array of detections in\n # (x1, y1, x2, y2, score)\n all_boxes = [[[] for _ in xrange(num_images)]\n for _ in xrange(imdb.num_classes)]\n\n output_dir = get_output_dir(imdb, net)\n\n # timers\n _t = {'im_detect' : Timer(), 'misc' : Timer()}\n\n if not cfg.TEST.HAS_RPN:\n roidb = imdb.roidb\n\n for i in xrange(num_images):\n # filter out any ground truth boxes\n if cfg.TEST.HAS_RPN:\n box_proposals = None\n else:\n # The roidb may contain ground-truth rois (for example, if the roidb\n # comes from the training or val split). We only want to evaluate\n # detection on the *non*-ground-truth rois. We select those the rois\n # that have the gt_classes field set to 0, which means there's no\n # ground truth.\n box_proposals = roidb[i]['boxes'][roidb[i]['gt_classes'] == 0]\n\n im = cv2.imread(imdb.image_path_at(i))\n _t['im_detect'].tic()\n scores, boxes = im_detect(net, im, box_proposals)\n _t['im_detect'].toc()\n\n _t['misc'].tic()\n # skip j = 0, because it's the background class\n for j in xrange(1, imdb.num_classes):\n inds = np.where(scores[:, j] > thresh)[0]\n cls_scores = scores[inds, j]\n cls_boxes = boxes[inds, j*4:(j+1)*4]\n cls_dets = np.hstack((cls_boxes, cls_scores[:, np.newaxis])) \\\n .astype(np.float32, copy=False)\n keep = nms(cls_dets, cfg.TEST.NMS)\n cls_dets = cls_dets[keep, :]\n if vis:\n vis_detections(im, imdb.classes[j], cls_dets)\n all_boxes[j][i] = cls_dets\n\n # Limit to max_per_image detections *over all classes*\n if max_per_image > 0:\n image_scores = np.hstack([all_boxes[j][i][:, -1]\n for j in xrange(1, imdb.num_classes)])\n if len(image_scores) > max_per_image:\n image_thresh = np.sort(image_scores)[-max_per_image]\n for j in xrange(1, imdb.num_classes):\n keep = np.where(all_boxes[j][i][:, -1] >= image_thresh)[0]\n all_boxes[j][i] = all_boxes[j][i][keep, :]\n _t['misc'].toc()\n\n print 'im_detect: {:d}/{:d} {:.3f}s {:.3f}s' \\\n .format(i + 1, num_images, _t['im_detect'].average_time,\n _t['misc'].average_time)\n\n det_file = os.path.join(output_dir, 'detections.pkl')\n with open(det_file, 'wb') as f:\n cPickle.dump(all_boxes, f, cPickle.HIGHEST_PROTOCOL)\n\n print 'Evaluating detections'\n imdb.evaluate_detections(all_boxes, output_dir)\n" }, { "path": "lib/fast_rcnn/train.py", "content": "# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\n\"\"\"Train a Fast R-CNN network.\"\"\"\n\nimport caffe\nfrom fast_rcnn.config import cfg\nimport roi_data_layer.roidb as rdl_roidb\nfrom utils.timer import Timer\nimport numpy as np\nimport os\n\nfrom caffe.proto import caffe_pb2\nimport google.protobuf as pb2\n\nclass SolverWrapper(object):\n \"\"\"A simple wrapper around Caffe's solver.\n This wrapper gives us control over he snapshotting process, which we\n use to unnormalize the learned bounding-box regression weights.\n \"\"\"\n\n def __init__(self, solver_prototxt, roidb, output_dir,\n pretrained_model=None):\n \"\"\"Initialize the SolverWrapper.\"\"\"\n self.output_dir = output_dir\n\n if (cfg.TRAIN.HAS_RPN and cfg.TRAIN.BBOX_REG and\n cfg.TRAIN.BBOX_NORMALIZE_TARGETS):\n # RPN can only use precomputed normalization because there are no\n # fixed statistics to compute a priori\n assert cfg.TRAIN.BBOX_NORMALIZE_TARGETS_PRECOMPUTED\n\n if cfg.TRAIN.BBOX_REG:\n print 'Computing bounding-box regression targets...'\n self.bbox_means, self.bbox_stds = \\\n rdl_roidb.add_bbox_regression_targets(roidb)\n print 'done'\n\n self.solver = caffe.SGDSolver(solver_prototxt)\n if pretrained_model is not None:\n print ('Loading pretrained model '\n 'weights from {:s}').format(pretrained_model)\n self.solver.net.copy_from(pretrained_model)\n\n self.solver_param = caffe_pb2.SolverParameter()\n with open(solver_prototxt, 'rt') as f:\n pb2.text_format.Merge(f.read(), self.solver_param)\n\n self.solver.net.layers[0].set_roidb(roidb)\n\n def snapshot(self):\n \"\"\"Take a snapshot of the network after unnormalizing the learned\n bounding-box regression weights. This enables easy use at test-time.\n \"\"\"\n net = self.solver.net\n\n scale_bbox_params = (cfg.TRAIN.BBOX_REG and\n cfg.TRAIN.BBOX_NORMALIZE_TARGETS and\n net.params.has_key('bbox_pred'))\n\n if scale_bbox_params:\n # save original values\n orig_0 = net.params['bbox_pred'][0].data.copy()\n orig_1 = net.params['bbox_pred'][1].data.copy()\n\n # scale and shift with bbox reg unnormalization; then save snapshot\n net.params['bbox_pred'][0].data[...] = \\\n (net.params['bbox_pred'][0].data *\n self.bbox_stds[:, np.newaxis])\n net.params['bbox_pred'][1].data[...] = \\\n (net.params['bbox_pred'][1].data *\n self.bbox_stds + self.bbox_means)\n\n infix = ('_' + cfg.TRAIN.SNAPSHOT_INFIX\n if cfg.TRAIN.SNAPSHOT_INFIX != '' else '')\n filename = (self.solver_param.snapshot_prefix + infix +\n '_iter_{:d}'.format(self.solver.iter) + '.caffemodel')\n filename = os.path.join(self.output_dir, filename)\n\n net.save(str(filename))\n print 'Wrote snapshot to: {:s}'.format(filename)\n\n if scale_bbox_params:\n # restore net to original state\n net.params['bbox_pred'][0].data[...] = orig_0\n net.params['bbox_pred'][1].data[...] = orig_1\n return filename\n\n def train_model(self, max_iters):\n \"\"\"Network training loop.\"\"\"\n last_snapshot_iter = -1\n timer = Timer()\n model_paths = []\n while self.solver.iter < max_iters:\n # Make one SGD update\n timer.tic()\n self.solver.step(1)\n timer.toc()\n if self.solver.iter % (10 * self.solver_param.display) == 0:\n print 'speed: {:.3f}s / iter'.format(timer.average_time)\n\n if self.solver.iter % cfg.TRAIN.SNAPSHOT_ITERS == 0:\n last_snapshot_iter = self.solver.iter\n model_paths.append(self.snapshot())\n\n if last_snapshot_iter != self.solver.iter:\n model_paths.append(self.snapshot())\n return model_paths\n\ndef get_training_roidb(imdb):\n \"\"\"Returns a roidb (Region of Interest database) for use in training.\"\"\"\n if cfg.TRAIN.USE_FLIPPED:\n print 'Appending horizontally-flipped training examples...'\n imdb.append_flipped_images()\n print 'done'\n\n print 'Preparing training data...'\n rdl_roidb.prepare_roidb(imdb)\n print 'done'\n\n return imdb.roidb\n\ndef filter_roidb(roidb):\n \"\"\"Remove roidb entries that have no usable RoIs.\"\"\"\n\n def is_valid(entry):\n # Valid images have:\n # (1) At least one foreground RoI OR\n # (2) At least one background RoI\n overlaps = entry['max_overlaps']\n # find boxes with sufficient overlap\n fg_inds = np.where(overlaps >= cfg.TRAIN.FG_THRESH)[0]\n # Select background RoIs as those within [BG_THRESH_LO, BG_THRESH_HI)\n bg_inds = np.where((overlaps < cfg.TRAIN.BG_THRESH_HI) &\n (overlaps >= cfg.TRAIN.BG_THRESH_LO))[0]\n # image is only valid if such boxes exist\n valid = len(fg_inds) > 0 or len(bg_inds) > 0\n return valid\n\n num = len(roidb)\n filtered_roidb = [entry for entry in roidb if is_valid(entry)]\n num_after = len(filtered_roidb)\n print 'Filtered {} roidb entries: {} -> {}'.format(num - num_after,\n num, num_after)\n return filtered_roidb\n\ndef train_net(solver_prototxt, roidb, output_dir,\n pretrained_model=None, max_iters=40000):\n \"\"\"Train a Fast R-CNN network.\"\"\"\n\n roidb = filter_roidb(roidb)\n sw = SolverWrapper(solver_prototxt, roidb, output_dir,\n pretrained_model=pretrained_model)\n\n print 'Solving...'\n model_paths = sw.train_model(max_iters)\n print 'done solving'\n return model_paths\n" }, { "path": "lib/nms/.gitignore", "content": "*.c\n*.cpp\n*.so\n" }, { "path": "lib/nms/__init__.py", "content": "" }, { "path": "lib/nms/cpu_nms.pyx", "content": "# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\nimport numpy as np\ncimport numpy as np\n\ncdef inline np.float32_t max(np.float32_t a, np.float32_t b):\n return a if a >= b else b\n\ncdef inline np.float32_t min(np.float32_t a, np.float32_t b):\n return a if a <= b else b\n\ndef cpu_nms(np.ndarray[np.float32_t, ndim=2] dets, np.float thresh):\n cdef np.ndarray[np.float32_t, ndim=1] x1 = dets[:, 0]\n cdef np.ndarray[np.float32_t, ndim=1] y1 = dets[:, 1]\n cdef np.ndarray[np.float32_t, ndim=1] x2 = dets[:, 2]\n cdef np.ndarray[np.float32_t, ndim=1] y2 = dets[:, 3]\n cdef np.ndarray[np.float32_t, ndim=1] scores = dets[:, 4]\n\n cdef np.ndarray[np.float32_t, ndim=1] areas = (x2 - x1 + 1) * (y2 - y1 + 1)\n cdef np.ndarray[np.int_t, ndim=1] order = scores.argsort()[::-1]\n\n cdef int ndets = dets.shape[0]\n cdef np.ndarray[np.int_t, ndim=1] suppressed = \\\n np.zeros((ndets), dtype=np.int)\n\n # nominal indices\n cdef int _i, _j\n # sorted indices\n cdef int i, j\n # temp variables for box i's (the box currently under consideration)\n cdef np.float32_t ix1, iy1, ix2, iy2, iarea\n # variables for computing overlap with box j (lower scoring box)\n cdef np.float32_t xx1, yy1, xx2, yy2\n cdef np.float32_t w, h\n cdef np.float32_t inter, ovr\n\n keep = []\n for _i in range(ndets):\n i = order[_i]\n if suppressed[i] == 1:\n continue\n keep.append(i)\n ix1 = x1[i]\n iy1 = y1[i]\n ix2 = x2[i]\n iy2 = y2[i]\n iarea = areas[i]\n for _j in range(_i + 1, ndets):\n j = order[_j]\n if suppressed[j] == 1:\n continue\n xx1 = max(ix1, x1[j])\n yy1 = max(iy1, y1[j])\n xx2 = min(ix2, x2[j])\n yy2 = min(iy2, y2[j])\n w = max(0.0, xx2 - xx1 + 1)\n h = max(0.0, yy2 - yy1 + 1)\n inter = w * h\n ovr = inter / (iarea + areas[j] - inter)\n if ovr >= thresh:\n suppressed[j] = 1\n\n return keep\n" }, { "path": "lib/nms/gpu_nms.hpp", "content": "void _nms(int* keep_out, int* num_out, const float* boxes_host, int boxes_num,\n int boxes_dim, float nms_overlap_thresh, int device_id);\n" }, { "path": "lib/nms/gpu_nms.pyx", "content": "# --------------------------------------------------------\n# Faster R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\nimport numpy as np\ncimport numpy as np\n\nassert sizeof(int) == sizeof(np.int32_t)\n\ncdef extern from \"gpu_nms.hpp\":\n void _nms(np.int32_t*, int*, np.float32_t*, int, int, float, int)\n\ndef gpu_nms(np.ndarray[np.float32_t, ndim=2] dets, np.float thresh,\n np.int32_t device_id=0):\n cdef int boxes_num = dets.shape[0]\n cdef int boxes_dim = dets.shape[1]\n cdef int num_out\n cdef np.ndarray[np.int32_t, ndim=1] \\\n keep = np.zeros(boxes_num, dtype=np.int32)\n cdef np.ndarray[np.float32_t, ndim=1] \\\n scores = dets[:, 4]\n cdef np.ndarray[np.int_t, ndim=1] \\\n order = scores.argsort()[::-1]\n cdef np.ndarray[np.float32_t, ndim=2] \\\n sorted_dets = dets[order, :]\n _nms(&keep[0], &num_out, &sorted_dets[0, 0], boxes_num, boxes_dim, thresh, device_id)\n keep = keep[:num_out]\n return list(order[keep])\n" }, { "path": "lib/nms/nms_kernel.cu", "content": "// ------------------------------------------------------------------\n// Faster R-CNN\n// Copyright (c) 2015 Microsoft\n// Licensed under The MIT License [see fast-rcnn/LICENSE for details]\n// Written by Shaoqing Ren\n// ------------------------------------------------------------------\n\n#include \"gpu_nms.hpp\"\n#include \n#include \n\n#define CUDA_CHECK(condition) \\\n /* Code block avoids redefinition of cudaError_t error */ \\\n do { \\\n cudaError_t error = condition; \\\n if (error != cudaSuccess) { \\\n std::cout << cudaGetErrorString(error) << std::endl; \\\n } \\\n } while (0)\n\n#define DIVUP(m,n) ((m) / (n) + ((m) % (n) > 0))\nint const threadsPerBlock = sizeof(unsigned long long) * 8;\n\n__device__ inline float devIoU(float const * const a, float const * const b) {\n float left = max(a[0], b[0]), right = min(a[2], b[2]);\n float top = max(a[1], b[1]), bottom = min(a[3], b[3]);\n float width = max(right - left + 1, 0.f), height = max(bottom - top + 1, 0.f);\n float interS = width * height;\n float Sa = (a[2] - a[0] + 1) * (a[3] - a[1] + 1);\n float Sb = (b[2] - b[0] + 1) * (b[3] - b[1] + 1);\n return interS / (Sa + Sb - interS);\n}\n\n__global__ void nms_kernel(const int n_boxes, const float nms_overlap_thresh,\n const float *dev_boxes, unsigned long long *dev_mask) {\n const int row_start = blockIdx.y;\n const int col_start = blockIdx.x;\n\n // if (row_start > col_start) return;\n\n const int row_size =\n min(n_boxes - row_start * threadsPerBlock, threadsPerBlock);\n const int col_size =\n min(n_boxes - col_start * threadsPerBlock, threadsPerBlock);\n\n __shared__ float block_boxes[threadsPerBlock * 5];\n if (threadIdx.x < col_size) {\n block_boxes[threadIdx.x * 5 + 0] =\n dev_boxes[(threadsPerBlock * col_start + threadIdx.x) * 5 + 0];\n block_boxes[threadIdx.x * 5 + 1] =\n dev_boxes[(threadsPerBlock * col_start + threadIdx.x) * 5 + 1];\n block_boxes[threadIdx.x * 5 + 2] =\n dev_boxes[(threadsPerBlock * col_start + threadIdx.x) * 5 + 2];\n block_boxes[threadIdx.x * 5 + 3] =\n dev_boxes[(threadsPerBlock * col_start + threadIdx.x) * 5 + 3];\n block_boxes[threadIdx.x * 5 + 4] =\n dev_boxes[(threadsPerBlock * col_start + threadIdx.x) * 5 + 4];\n }\n __syncthreads();\n\n if (threadIdx.x < row_size) {\n const int cur_box_idx = threadsPerBlock * row_start + threadIdx.x;\n const float *cur_box = dev_boxes + cur_box_idx * 5;\n int i = 0;\n unsigned long long t = 0;\n int start = 0;\n if (row_start == col_start) {\n start = threadIdx.x + 1;\n }\n for (i = start; i < col_size; i++) {\n if (devIoU(cur_box, block_boxes + i * 5) > nms_overlap_thresh) {\n t |= 1ULL << i;\n }\n }\n const int col_blocks = DIVUP(n_boxes, threadsPerBlock);\n dev_mask[cur_box_idx * col_blocks + col_start] = t;\n }\n}\n\nvoid _set_device(int device_id) {\n int current_device;\n CUDA_CHECK(cudaGetDevice(¤t_device));\n if (current_device == device_id) {\n return;\n }\n // The call to cudaSetDevice must come before any calls to Get, which\n // may perform initialization using the GPU.\n CUDA_CHECK(cudaSetDevice(device_id));\n}\n\nvoid _nms(int* keep_out, int* num_out, const float* boxes_host, int boxes_num,\n int boxes_dim, float nms_overlap_thresh, int device_id) {\n _set_device(device_id);\n\n float* boxes_dev = NULL;\n unsigned long long* mask_dev = NULL;\n\n const int col_blocks = DIVUP(boxes_num, threadsPerBlock);\n\n CUDA_CHECK(cudaMalloc(&boxes_dev,\n boxes_num * boxes_dim * sizeof(float)));\n CUDA_CHECK(cudaMemcpy(boxes_dev,\n boxes_host,\n boxes_num * boxes_dim * sizeof(float),\n cudaMemcpyHostToDevice));\n\n CUDA_CHECK(cudaMalloc(&mask_dev,\n boxes_num * col_blocks * sizeof(unsigned long long)));\n\n dim3 blocks(DIVUP(boxes_num, threadsPerBlock),\n DIVUP(boxes_num, threadsPerBlock));\n dim3 threads(threadsPerBlock);\n nms_kernel<<>>(boxes_num,\n nms_overlap_thresh,\n boxes_dev,\n mask_dev);\n\n std::vector mask_host(boxes_num * col_blocks);\n CUDA_CHECK(cudaMemcpy(&mask_host[0],\n mask_dev,\n sizeof(unsigned long long) * boxes_num * col_blocks,\n cudaMemcpyDeviceToHost));\n\n std::vector remv(col_blocks);\n memset(&remv[0], 0, sizeof(unsigned long long) * col_blocks);\n\n int num_to_keep = 0;\n for (int i = 0; i < boxes_num; i++) {\n int nblock = i / threadsPerBlock;\n int inblock = i % threadsPerBlock;\n\n if (!(remv[nblock] & (1ULL << inblock))) {\n keep_out[num_to_keep++] = i;\n unsigned long long *p = &mask_host[0] + i * col_blocks;\n for (int j = nblock; j < col_blocks; j++) {\n remv[j] |= p[j];\n }\n }\n }\n *num_out = num_to_keep;\n\n CUDA_CHECK(cudaFree(boxes_dev));\n CUDA_CHECK(cudaFree(mask_dev));\n}\n" }, { "path": "lib/nms/py_cpu_nms.py", "content": "# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\nimport numpy as np\n\ndef py_cpu_nms(dets, thresh):\n \"\"\"Pure Python NMS baseline.\"\"\"\n x1 = dets[:, 0]\n y1 = dets[:, 1]\n x2 = dets[:, 2]\n y2 = dets[:, 3]\n scores = dets[:, 4]\n\n areas = (x2 - x1 + 1) * (y2 - y1 + 1)\n order = scores.argsort()[::-1]\n\n keep = []\n while order.size > 0:\n i = order[0]\n keep.append(i)\n xx1 = np.maximum(x1[i], x1[order[1:]])\n yy1 = np.maximum(y1[i], y1[order[1:]])\n xx2 = np.minimum(x2[i], x2[order[1:]])\n yy2 = np.minimum(y2[i], y2[order[1:]])\n\n w = np.maximum(0.0, xx2 - xx1 + 1)\n h = np.maximum(0.0, yy2 - yy1 + 1)\n inter = w * h\n ovr = inter / (areas[i] + areas[order[1:]] - inter)\n\n inds = np.where(ovr <= thresh)[0]\n order = order[inds + 1]\n\n return keep\n" }, { "path": "lib/pycocotools/UPSTREAM_REV", "content": "https://github.com/pdollar/coco/commit/3ac47c77ebd5a1ed4254a98b7fbf2ef4765a3574\n" }, { "path": "lib/pycocotools/__init__.py", "content": "__author__ = 'tylin'\n" }, { "path": "lib/pycocotools/_mask.pyx", "content": "# distutils: language = c\n# distutils: sources = ../MatlabAPI/private/maskApi.c\n\n#**************************************************************************\n# Microsoft COCO Toolbox. version 2.0\n# Data, paper, and tutorials available at: http://mscoco.org/\n# Code written by Piotr Dollar and Tsung-Yi Lin, 2015.\n# Licensed under the Simplified BSD License [see coco/license.txt]\n#**************************************************************************\n\n__author__ = 'tsungyi'\n\n# import both Python-level and C-level symbols of Numpy\n# the API uses Numpy to interface C and Python\nimport numpy as np\ncimport numpy as np\nfrom libc.stdlib cimport malloc, free\n\n# intialized Numpy. must do.\nnp.import_array()\n\n# import numpy C function\n# we use PyArray_ENABLEFLAGS to make Numpy ndarray responsible to memoery management\ncdef extern from \"numpy/arrayobject.h\":\n void PyArray_ENABLEFLAGS(np.ndarray arr, int flags)\n\n# Declare the prototype of the C functions in MaskApi.h\ncdef extern from \"maskApi.h\":\n ctypedef unsigned int uint\n ctypedef unsigned long siz\n ctypedef unsigned char byte\n ctypedef double* BB\n ctypedef struct RLE:\n siz h,\n siz w,\n siz m,\n uint* cnts,\n void rlesInit( RLE **R, siz n )\n void rleEncode( RLE *R, const byte *M, siz h, siz w, siz n )\n void rleDecode( const RLE *R, byte *mask, siz n )\n void rleMerge( const RLE *R, RLE *M, siz n, bint intersect )\n void rleArea( const RLE *R, siz n, uint *a )\n void rleIou( RLE *dt, RLE *gt, siz m, siz n, byte *iscrowd, double *o )\n void bbIou( BB dt, BB gt, siz m, siz n, byte *iscrowd, double *o )\n void rleToBbox( const RLE *R, BB bb, siz n )\n void rleFrBbox( RLE *R, const BB bb, siz h, siz w, siz n )\n void rleFrPoly( RLE *R, const double *xy, siz k, siz h, siz w )\n char* rleToString( const RLE *R )\n void rleFrString( RLE *R, char *s, siz h, siz w )\n\n# python class to wrap RLE array in C\n# the class handles the memory allocation and deallocation\ncdef class RLEs:\n cdef RLE *_R\n cdef siz _n\n\n def __cinit__(self, siz n =0):\n rlesInit(&self._R, n)\n self._n = n\n\n # free the RLE array here\n def __dealloc__(self):\n if self._R is not NULL:\n for i in range(self._n):\n free(self._R[i].cnts)\n free(self._R)\n def __getattr__(self, key):\n if key == 'n':\n return self._n\n raise AttributeError(key)\n\n# python class to wrap Mask array in C\n# the class handles the memory allocation and deallocation\ncdef class Masks:\n cdef byte *_mask\n cdef siz _h\n cdef siz _w\n cdef siz _n\n\n def __cinit__(self, h, w, n):\n self._mask = malloc(h*w*n* sizeof(byte))\n self._h = h\n self._w = w\n self._n = n\n # def __dealloc__(self):\n # the memory management of _mask has been passed to np.ndarray\n # it doesn't need to be freed here\n\n # called when passing into np.array() and return an np.ndarray in column-major order\n def __array__(self):\n cdef np.npy_intp shape[1]\n shape[0] = self._h*self._w*self._n\n # Create a 1D array, and reshape it to fortran/Matlab column-major array\n ndarray = np.PyArray_SimpleNewFromData(1, shape, np.NPY_UINT8, self._mask).reshape((self._h, self._w, self._n), order='F')\n # The _mask allocated by Masks is now handled by ndarray\n PyArray_ENABLEFLAGS(ndarray, np.NPY_OWNDATA)\n return ndarray\n\n# internal conversion from Python RLEs object to compressed RLE format\ndef _toString(RLEs Rs):\n cdef siz n = Rs.n\n cdef bytes py_string\n cdef char* c_string\n objs = []\n for i in range(n):\n c_string = rleToString( &Rs._R[i] )\n py_string = c_string\n objs.append({\n 'size': [Rs._R[i].h, Rs._R[i].w],\n 'counts': py_string\n })\n free(c_string)\n return objs\n\n# internal conversion from compressed RLE format to Python RLEs object\ndef _frString(rleObjs):\n cdef siz n = len(rleObjs)\n Rs = RLEs(n)\n cdef bytes py_string\n cdef char* c_string\n for i, obj in enumerate(rleObjs):\n py_string = str(obj['counts'])\n c_string = py_string\n rleFrString( &Rs._R[i], c_string, obj['size'][0], obj['size'][1] )\n return Rs\n\n# encode mask to RLEs objects\n# list of RLE string can be generated by RLEs member function\ndef encode(np.ndarray[np.uint8_t, ndim=3, mode='fortran'] mask):\n h, w, n = mask.shape[0], mask.shape[1], mask.shape[2]\n cdef RLEs Rs = RLEs(n)\n rleEncode(Rs._R,mask.data,h,w,n)\n objs = _toString(Rs)\n return objs\n\n# decode mask from compressed list of RLE string or RLEs object\ndef decode(rleObjs):\n cdef RLEs Rs = _frString(rleObjs)\n h, w, n = Rs._R[0].h, Rs._R[0].w, Rs._n\n masks = Masks(h, w, n)\n rleDecode( Rs._R, masks._mask, n );\n return np.array(masks)\n\ndef merge(rleObjs, bint intersect=0):\n cdef RLEs Rs = _frString(rleObjs)\n cdef RLEs R = RLEs(1)\n rleMerge(Rs._R, R._R, Rs._n, intersect)\n obj = _toString(R)[0]\n return obj\n\ndef area(rleObjs):\n cdef RLEs Rs = _frString(rleObjs)\n cdef uint* _a = malloc(Rs._n* sizeof(uint))\n rleArea(Rs._R, Rs._n, _a)\n cdef np.npy_intp shape[1]\n shape[0] = Rs._n\n a = np.array((Rs._n, ), dtype=np.uint8)\n a = np.PyArray_SimpleNewFromData(1, shape, np.NPY_UINT32, _a)\n PyArray_ENABLEFLAGS(a, np.NPY_OWNDATA)\n return a\n\n# iou computation. support function overload (RLEs-RLEs and bbox-bbox).\ndef iou( dt, gt, pyiscrowd ):\n def _preproc(objs):\n if len(objs) == 0:\n return objs\n if type(objs) == np.ndarray:\n if len(objs.shape) == 1:\n objs = objs.reshape((objs[0], 1))\n # check if it's Nx4 bbox\n if not len(objs.shape) == 2 or not objs.shape[1] == 4:\n raise Exception('numpy ndarray input is only for *bounding boxes* and should have Nx4 dimension')\n objs = objs.astype(np.double)\n elif type(objs) == list:\n # check if list is in box format and convert it to np.ndarray\n isbox = np.all(np.array([(len(obj)==4) and ((type(obj)==list) or (type(obj)==np.ndarray)) for obj in objs]))\n isrle = np.all(np.array([type(obj) == dict for obj in objs]))\n if isbox:\n objs = np.array(objs, dtype=np.double)\n if len(objs.shape) == 1:\n objs = objs.reshape((1,objs.shape[0]))\n elif isrle:\n objs = _frString(objs)\n else:\n raise Exception('list input can be bounding box (Nx4) or RLEs ([RLE])')\n else:\n raise Exception('unrecognized type. The following type: RLEs (rle), np.ndarray (box), and list (box) are supported.')\n return objs\n def _rleIou(RLEs dt, RLEs gt, np.ndarray[np.uint8_t, ndim=1] iscrowd, siz m, siz n, np.ndarray[np.double_t, ndim=1] _iou):\n rleIou( dt._R, gt._R, m, n, iscrowd.data, _iou.data )\n def _bbIou(np.ndarray[np.double_t, ndim=2] dt, np.ndarray[np.double_t, ndim=2] gt, np.ndarray[np.uint8_t, ndim=1] iscrowd, siz m, siz n, np.ndarray[np.double_t, ndim=1] _iou):\n bbIou( dt.data, gt.data, m, n, iscrowd.data, _iou.data )\n def _len(obj):\n cdef siz N = 0\n if type(obj) == RLEs:\n N = obj.n\n elif len(obj)==0:\n pass\n elif type(obj) == np.ndarray:\n N = obj.shape[0]\n return N\n # convert iscrowd to numpy array\n cdef np.ndarray[np.uint8_t, ndim=1] iscrowd = np.array(pyiscrowd, dtype=np.uint8)\n # simple type checking\n cdef siz m, n\n dt = _preproc(dt)\n gt = _preproc(gt)\n m = _len(dt)\n n = _len(gt)\n if m == 0 or n == 0:\n return []\n if not type(dt) == type(gt):\n raise Exception('The dt and gt should have the same data type, either RLEs, list or np.ndarray')\n\n # define local variables\n cdef double* _iou = 0\n cdef np.npy_intp shape[1]\n # check type and assign iou function\n if type(dt) == RLEs:\n _iouFun = _rleIou\n elif type(dt) == np.ndarray:\n _iouFun = _bbIou\n else:\n raise Exception('input data type not allowed.')\n _iou = malloc(m*n* sizeof(double))\n iou = np.zeros((m*n, ), dtype=np.double)\n shape[0] = m*n\n iou = np.PyArray_SimpleNewFromData(1, shape, np.NPY_DOUBLE, _iou)\n PyArray_ENABLEFLAGS(iou, np.NPY_OWNDATA)\n _iouFun(dt, gt, iscrowd, m, n, iou)\n return iou.reshape((m,n), order='F')\n\ndef toBbox( rleObjs ):\n cdef RLEs Rs = _frString(rleObjs)\n cdef siz n = Rs.n\n cdef BB _bb = malloc(4*n* sizeof(double))\n rleToBbox( Rs._R, _bb, n )\n cdef np.npy_intp shape[1]\n shape[0] = 4*n\n bb = np.array((1,4*n), dtype=np.double)\n bb = np.PyArray_SimpleNewFromData(1, shape, np.NPY_DOUBLE, _bb).reshape((n, 4))\n PyArray_ENABLEFLAGS(bb, np.NPY_OWNDATA)\n return bb\n\ndef frBbox(np.ndarray[np.double_t, ndim=2] bb, siz h, siz w ):\n cdef siz n = bb.shape[0]\n Rs = RLEs(n)\n rleFrBbox( Rs._R, bb.data, h, w, n )\n objs = _toString(Rs)\n return objs\n\ndef frPoly( poly, siz h, siz w ):\n cdef np.ndarray[np.double_t, ndim=1] np_poly\n n = len(poly)\n Rs = RLEs(n)\n for i, p in enumerate(poly):\n np_poly = np.array(p, dtype=np.double, order='F')\n rleFrPoly( &Rs._R[i], np_poly.data, len(np_poly)/2, h, w )\n objs = _toString(Rs)\n return objs\n\ndef frUncompressedRLE(ucRles, siz h, siz w):\n cdef np.ndarray[np.uint32_t, ndim=1] cnts\n cdef RLE R\n cdef uint *data\n n = len(ucRles)\n objs = []\n for i in range(n):\n Rs = RLEs(1)\n cnts = np.array(ucRles[i]['counts'], dtype=np.uint32)\n # time for malloc can be saved here but it's fine\n data = malloc(len(cnts)* sizeof(uint))\n for j in range(len(cnts)):\n data[j] = cnts[j]\n R = RLE(ucRles[i]['size'][0], ucRles[i]['size'][1], len(cnts), data)\n Rs._R[0] = R\n objs.append(_toString(Rs)[0])\n return objs\n\ndef frPyObjects(pyobj, siz h, w):\n if type(pyobj) == np.ndarray:\n objs = frBbox(pyobj, h, w )\n elif type(pyobj) == list and len(pyobj[0]) == 4:\n objs = frBbox(pyobj, h, w )\n elif type(pyobj) == list and len(pyobj[0]) > 4:\n objs = frPoly(pyobj, h, w )\n elif type(pyobj) == list and type(pyobj[0]) == dict:\n objs = frUncompressedRLE(pyobj, h, w)\n else:\n raise Exception('input type is not supported.')\n return objs\n" }, { "path": "lib/pycocotools/coco.py", "content": "__author__ = 'tylin'\n__version__ = '1.0.1'\n# Interface for accessing the Microsoft COCO dataset.\n\n# Microsoft COCO is a large image dataset designed for object detection,\n# segmentation, and caption generation. pycocotools is a Python API that\n# assists in loading, parsing and visualizing the annotations in COCO.\n# Please visit http://mscoco.org/ for more information on COCO, including\n# for the data, paper, and tutorials. The exact format of the annotations\n# is also described on the COCO website. For example usage of the pycocotools\n# please see pycocotools_demo.ipynb. In addition to this API, please download both\n# the COCO images and annotations in order to run the demo.\n\n# An alternative to using the API is to load the annotations directly\n# into Python dictionary\n# Using the API provides additional utility functions. Note that this API\n# supports both *instance* and *caption* annotations. In the case of\n# captions not all functions are defined (e.g. categories are undefined).\n\n# The following API functions are defined:\n# COCO - COCO api class that loads COCO annotation file and prepare data structures.\n# decodeMask - Decode binary mask M encoded via run-length encoding.\n# encodeMask - Encode binary mask M using run-length encoding.\n# getAnnIds - Get ann ids that satisfy given filter conditions.\n# getCatIds - Get cat ids that satisfy given filter conditions.\n# getImgIds - Get img ids that satisfy given filter conditions.\n# loadAnns - Load anns with the specified ids.\n# loadCats - Load cats with the specified ids.\n# loadImgs - Load imgs with the specified ids.\n# segToMask - Convert polygon segmentation to binary mask.\n# showAnns - Display the specified annotations.\n# loadRes - Load algorithm results and create API for accessing them.\n# download - Download COCO images from mscoco.org server.\n# Throughout the API \"ann\"=annotation, \"cat\"=category, and \"img\"=image.\n# Help on each functions can be accessed by: \"help COCO>function\".\n\n# See also COCO>decodeMask,\n# COCO>encodeMask, COCO>getAnnIds, COCO>getCatIds,\n# COCO>getImgIds, COCO>loadAnns, COCO>loadCats,\n# COCO>loadImgs, COCO>segToMask, COCO>showAnns\n\n# Microsoft COCO Toolbox. version 2.0\n# Data, paper, and tutorials available at: http://mscoco.org/\n# Code written by Piotr Dollar and Tsung-Yi Lin, 2014.\n# Licensed under the Simplified BSD License [see bsd.txt]\n\nimport json\nimport datetime\nimport time\nimport matplotlib.pyplot as plt\nfrom matplotlib.collections import PatchCollection\nfrom matplotlib.patches import Polygon\nimport numpy as np\nfrom skimage.draw import polygon\nimport urllib\nimport copy\nimport itertools\nimport mask\nimport os\n\nclass COCO:\n def __init__(self, annotation_file=None):\n \"\"\"\n Constructor of Microsoft COCO helper class for reading and visualizing annotations.\n :param annotation_file (str): location of annotation file\n :param image_folder (str): location to the folder that hosts images.\n :return:\n \"\"\"\n # load dataset\n self.dataset = {}\n self.anns = []\n self.imgToAnns = {}\n self.catToImgs = {}\n self.imgs = {}\n self.cats = {}\n if not annotation_file == None:\n print 'loading annotations into memory...'\n tic = time.time()\n dataset = json.load(open(annotation_file, 'r'))\n print 'Done (t=%0.2fs)'%(time.time()- tic)\n self.dataset = dataset\n self.createIndex()\n\n def createIndex(self):\n # create index\n print 'creating index...'\n anns = {}\n imgToAnns = {}\n catToImgs = {}\n cats = {}\n imgs = {}\n if 'annotations' in self.dataset:\n imgToAnns = {ann['image_id']: [] for ann in self.dataset['annotations']}\n anns = {ann['id']: [] for ann in self.dataset['annotations']}\n for ann in self.dataset['annotations']:\n imgToAnns[ann['image_id']] += [ann]\n anns[ann['id']] = ann\n\n if 'images' in self.dataset:\n imgs = {im['id']: {} for im in self.dataset['images']}\n for img in self.dataset['images']:\n imgs[img['id']] = img\n\n if 'categories' in self.dataset:\n cats = {cat['id']: [] for cat in self.dataset['categories']}\n for cat in self.dataset['categories']:\n cats[cat['id']] = cat\n catToImgs = {cat['id']: [] for cat in self.dataset['categories']}\n if 'annotations' in self.dataset:\n for ann in self.dataset['annotations']:\n catToImgs[ann['category_id']] += [ann['image_id']]\n\n print 'index created!'\n\n # create class members\n self.anns = anns\n self.imgToAnns = imgToAnns\n self.catToImgs = catToImgs\n self.imgs = imgs\n self.cats = cats\n\n def info(self):\n \"\"\"\n Print information about the annotation file.\n :return:\n \"\"\"\n for key, value in self.dataset['info'].items():\n print '%s: %s'%(key, value)\n\n def getAnnIds(self, imgIds=[], catIds=[], areaRng=[], iscrowd=None):\n \"\"\"\n Get ann ids that satisfy given filter conditions. default skips that filter\n :param imgIds (int array) : get anns for given imgs\n catIds (int array) : get anns for given cats\n areaRng (float array) : get anns for given area range (e.g. [0 inf])\n iscrowd (boolean) : get anns for given crowd label (False or True)\n :return: ids (int array) : integer array of ann ids\n \"\"\"\n imgIds = imgIds if type(imgIds) == list else [imgIds]\n catIds = catIds if type(catIds) == list else [catIds]\n\n if len(imgIds) == len(catIds) == len(areaRng) == 0:\n anns = self.dataset['annotations']\n else:\n if not len(imgIds) == 0:\n # this can be changed by defaultdict\n lists = [self.imgToAnns[imgId] for imgId in imgIds if imgId in self.imgToAnns]\n anns = list(itertools.chain.from_iterable(lists))\n else:\n anns = self.dataset['annotations']\n anns = anns if len(catIds) == 0 else [ann for ann in anns if ann['category_id'] in catIds]\n anns = anns if len(areaRng) == 0 else [ann for ann in anns if ann['area'] > areaRng[0] and ann['area'] < areaRng[1]]\n if not iscrowd == None:\n ids = [ann['id'] for ann in anns if ann['iscrowd'] == iscrowd]\n else:\n ids = [ann['id'] for ann in anns]\n return ids\n\n def getCatIds(self, catNms=[], supNms=[], catIds=[]):\n \"\"\"\n filtering parameters. default skips that filter.\n :param catNms (str array) : get cats for given cat names\n :param supNms (str array) : get cats for given supercategory names\n :param catIds (int array) : get cats for given cat ids\n :return: ids (int array) : integer array of cat ids\n \"\"\"\n catNms = catNms if type(catNms) == list else [catNms]\n supNms = supNms if type(supNms) == list else [supNms]\n catIds = catIds if type(catIds) == list else [catIds]\n\n if len(catNms) == len(supNms) == len(catIds) == 0:\n cats = self.dataset['categories']\n else:\n cats = self.dataset['categories']\n cats = cats if len(catNms) == 0 else [cat for cat in cats if cat['name'] in catNms]\n cats = cats if len(supNms) == 0 else [cat for cat in cats if cat['supercategory'] in supNms]\n cats = cats if len(catIds) == 0 else [cat for cat in cats if cat['id'] in catIds]\n ids = [cat['id'] for cat in cats]\n return ids\n\n def getImgIds(self, imgIds=[], catIds=[]):\n '''\n Get img ids that satisfy given filter conditions.\n :param imgIds (int array) : get imgs for given ids\n :param catIds (int array) : get imgs with all given cats\n :return: ids (int array) : integer array of img ids\n '''\n imgIds = imgIds if type(imgIds) == list else [imgIds]\n catIds = catIds if type(catIds) == list else [catIds]\n\n if len(imgIds) == len(catIds) == 0:\n ids = self.imgs.keys()\n else:\n ids = set(imgIds)\n for i, catId in enumerate(catIds):\n if i == 0 and len(ids) == 0:\n ids = set(self.catToImgs[catId])\n else:\n ids &= set(self.catToImgs[catId])\n return list(ids)\n\n def loadAnns(self, ids=[]):\n \"\"\"\n Load anns with the specified ids.\n :param ids (int array) : integer ids specifying anns\n :return: anns (object array) : loaded ann objects\n \"\"\"\n if type(ids) == list:\n return [self.anns[id] for id in ids]\n elif type(ids) == int:\n return [self.anns[ids]]\n\n def loadCats(self, ids=[]):\n \"\"\"\n Load cats with the specified ids.\n :param ids (int array) : integer ids specifying cats\n :return: cats (object array) : loaded cat objects\n \"\"\"\n if type(ids) == list:\n return [self.cats[id] for id in ids]\n elif type(ids) == int:\n return [self.cats[ids]]\n\n def loadImgs(self, ids=[]):\n \"\"\"\n Load anns with the specified ids.\n :param ids (int array) : integer ids specifying img\n :return: imgs (object array) : loaded img objects\n \"\"\"\n if type(ids) == list:\n return [self.imgs[id] for id in ids]\n elif type(ids) == int:\n return [self.imgs[ids]]\n\n def showAnns(self, anns):\n \"\"\"\n Display the specified annotations.\n :param anns (array of object): annotations to display\n :return: None\n \"\"\"\n if len(anns) == 0:\n return 0\n if 'segmentation' in anns[0]:\n datasetType = 'instances'\n elif 'caption' in anns[0]:\n datasetType = 'captions'\n if datasetType == 'instances':\n ax = plt.gca()\n polygons = []\n color = []\n for ann in anns:\n c = np.random.random((1, 3)).tolist()[0]\n if type(ann['segmentation']) == list:\n # polygon\n for seg in ann['segmentation']:\n poly = np.array(seg).reshape((len(seg)/2, 2))\n polygons.append(Polygon(poly, True,alpha=0.4))\n color.append(c)\n else:\n # mask\n t = self.imgs[ann['image_id']]\n if type(ann['segmentation']['counts']) == list:\n rle = mask.frPyObjects([ann['segmentation']], t['height'], t['width'])\n else:\n rle = [ann['segmentation']]\n m = mask.decode(rle)\n img = np.ones( (m.shape[0], m.shape[1], 3) )\n if ann['iscrowd'] == 1:\n color_mask = np.array([2.0,166.0,101.0])/255\n if ann['iscrowd'] == 0:\n color_mask = np.random.random((1, 3)).tolist()[0]\n for i in range(3):\n img[:,:,i] = color_mask[i]\n ax.imshow(np.dstack( (img, m*0.5) ))\n p = PatchCollection(polygons, facecolors=color, edgecolors=(0,0,0,1), linewidths=3, alpha=0.4)\n ax.add_collection(p)\n elif datasetType == 'captions':\n for ann in anns:\n print ann['caption']\n\n def loadRes(self, resFile):\n \"\"\"\n Load result file and return a result api object.\n :param resFile (str) : file name of result file\n :return: res (obj) : result api object\n \"\"\"\n res = COCO()\n res.dataset['images'] = [img for img in self.dataset['images']]\n # res.dataset['info'] = copy.deepcopy(self.dataset['info'])\n # res.dataset['licenses'] = copy.deepcopy(self.dataset['licenses'])\n\n print 'Loading and preparing results... '\n tic = time.time()\n anns = json.load(open(resFile))\n assert type(anns) == list, 'results in not an array of objects'\n annsImgIds = [ann['image_id'] for ann in anns]\n assert set(annsImgIds) == (set(annsImgIds) & set(self.getImgIds())), \\\n 'Results do not correspond to current coco set'\n if 'caption' in anns[0]:\n imgIds = set([img['id'] for img in res.dataset['images']]) & set([ann['image_id'] for ann in anns])\n res.dataset['images'] = [img for img in res.dataset['images'] if img['id'] in imgIds]\n for id, ann in enumerate(anns):\n ann['id'] = id+1\n elif 'bbox' in anns[0] and not anns[0]['bbox'] == []:\n res.dataset['categories'] = copy.deepcopy(self.dataset['categories'])\n for id, ann in enumerate(anns):\n bb = ann['bbox']\n x1, x2, y1, y2 = [bb[0], bb[0]+bb[2], bb[1], bb[1]+bb[3]]\n if not 'segmentation' in ann:\n ann['segmentation'] = [[x1, y1, x1, y2, x2, y2, x2, y1]]\n ann['area'] = bb[2]*bb[3]\n ann['id'] = id+1\n ann['iscrowd'] = 0\n elif 'segmentation' in anns[0]:\n res.dataset['categories'] = copy.deepcopy(self.dataset['categories'])\n for id, ann in enumerate(anns):\n # now only support compressed RLE format as segmentation results\n ann['area'] = mask.area([ann['segmentation']])[0]\n if not 'bbox' in ann:\n ann['bbox'] = mask.toBbox([ann['segmentation']])[0]\n ann['id'] = id+1\n ann['iscrowd'] = 0\n print 'DONE (t=%0.2fs)'%(time.time()- tic)\n\n res.dataset['annotations'] = anns\n res.createIndex()\n return res\n\n def download( self, tarDir = None, imgIds = [] ):\n '''\n Download COCO images from mscoco.org server.\n :param tarDir (str): COCO results directory name\n imgIds (list): images to be downloaded\n :return:\n '''\n if tarDir is None:\n print 'Please specify target directory'\n return -1\n if len(imgIds) == 0:\n imgs = self.imgs.values()\n else:\n imgs = self.loadImgs(imgIds)\n N = len(imgs)\n if not os.path.exists(tarDir):\n os.makedirs(tarDir)\n for i, img in enumerate(imgs):\n tic = time.time()\n fname = os.path.join(tarDir, img['file_name'])\n if not os.path.exists(fname):\n urllib.urlretrieve(img['coco_url'], fname)\n print 'downloaded %d/%d images (t=%.1fs)'%(i, N, time.time()- tic)\n" }, { "path": "lib/pycocotools/cocoeval.py", "content": "__author__ = 'tsungyi'\n\nimport numpy as np\nimport datetime\nimport time\nfrom collections import defaultdict\nimport mask\nimport copy\n\nclass COCOeval:\n # Interface for evaluating detection on the Microsoft COCO dataset.\n #\n # The usage for CocoEval is as follows:\n # cocoGt=..., cocoDt=... # load dataset and results\n # E = CocoEval(cocoGt,cocoDt); # initialize CocoEval object\n # E.params.recThrs = ...; # set parameters as desired\n # E.evaluate(); # run per image evaluation\n # E.accumulate(); # accumulate per image results\n # E.summarize(); # display summary metrics of results\n # For example usage see evalDemo.m and http://mscoco.org/.\n #\n # The evaluation parameters are as follows (defaults in brackets):\n # imgIds - [all] N img ids to use for evaluation\n # catIds - [all] K cat ids to use for evaluation\n # iouThrs - [.5:.05:.95] T=10 IoU thresholds for evaluation\n # recThrs - [0:.01:1] R=101 recall thresholds for evaluation\n # areaRng - [...] A=4 object area ranges for evaluation\n # maxDets - [1 10 100] M=3 thresholds on max detections per image\n # useSegm - [1] if true evaluate against ground-truth segments\n # useCats - [1] if true use category labels for evaluation # Note: if useSegm=0 the evaluation is run on bounding boxes.\n # Note: if useCats=0 category labels are ignored as in proposal scoring.\n # Note: multiple areaRngs [Ax2] and maxDets [Mx1] can be specified.\n #\n # evaluate(): evaluates detections on every image and every category and\n # concats the results into the \"evalImgs\" with fields:\n # dtIds - [1xD] id for each of the D detections (dt)\n # gtIds - [1xG] id for each of the G ground truths (gt)\n # dtMatches - [TxD] matching gt id at each IoU or 0\n # gtMatches - [TxG] matching dt id at each IoU or 0\n # dtScores - [1xD] confidence of each dt\n # gtIgnore - [1xG] ignore flag for each gt\n # dtIgnore - [TxD] ignore flag for each dt at each IoU\n #\n # accumulate(): accumulates the per-image, per-category evaluation\n # results in \"evalImgs\" into the dictionary \"eval\" with fields:\n # params - parameters used for evaluation\n # date - date evaluation was performed\n # counts - [T,R,K,A,M] parameter dimensions (see above)\n # precision - [TxRxKxAxM] precision for every evaluation setting\n # recall - [TxKxAxM] max recall for every evaluation setting\n # Note: precision and recall==-1 for settings with no gt objects.\n #\n # See also coco, mask, pycocoDemo, pycocoEvalDemo\n #\n # Microsoft COCO Toolbox. version 2.0\n # Data, paper, and tutorials available at: http://mscoco.org/\n # Code written by Piotr Dollar and Tsung-Yi Lin, 2015.\n # Licensed under the Simplified BSD License [see coco/license.txt]\n def __init__(self, cocoGt=None, cocoDt=None):\n '''\n Initialize CocoEval using coco APIs for gt and dt\n :param cocoGt: coco object with ground truth annotations\n :param cocoDt: coco object with detection results\n :return: None\n '''\n self.cocoGt = cocoGt # ground truth COCO API\n self.cocoDt = cocoDt # detections COCO API\n self.params = {} # evaluation parameters\n self.evalImgs = defaultdict(list) # per-image per-category evaluation results [KxAxI] elements\n self.eval = {} # accumulated evaluation results\n self._gts = defaultdict(list) # gt for evaluation\n self._dts = defaultdict(list) # dt for evaluation\n self.params = Params() # parameters\n self._paramsEval = {} # parameters for evaluation\n self.stats = [] # result summarization\n self.ious = {} # ious between all gts and dts\n if not cocoGt is None:\n self.params.imgIds = sorted(cocoGt.getImgIds())\n self.params.catIds = sorted(cocoGt.getCatIds())\n\n\n def _prepare(self):\n '''\n Prepare ._gts and ._dts for evaluation based on params\n :return: None\n '''\n #\n def _toMask(objs, coco):\n # modify segmentation by reference\n for obj in objs:\n t = coco.imgs[obj['image_id']]\n if type(obj['segmentation']) == list:\n if type(obj['segmentation'][0]) == dict:\n print 'debug'\n obj['segmentation'] = mask.frPyObjects(obj['segmentation'],t['height'],t['width'])\n if len(obj['segmentation']) == 1:\n obj['segmentation'] = obj['segmentation'][0]\n else:\n # an object can have multiple polygon regions\n # merge them into one RLE mask\n obj['segmentation'] = mask.merge(obj['segmentation'])\n elif type(obj['segmentation']) == dict and type(obj['segmentation']['counts']) == list:\n obj['segmentation'] = mask.frPyObjects([obj['segmentation']],t['height'],t['width'])[0]\n elif type(obj['segmentation']) == dict and \\\n type(obj['segmentation']['counts'] == unicode or type(obj['segmentation']['counts']) == str):\n pass\n else:\n raise Exception('segmentation format not supported.')\n p = self.params\n if p.useCats:\n gts=self.cocoGt.loadAnns(self.cocoGt.getAnnIds(imgIds=p.imgIds, catIds=p.catIds))\n dts=self.cocoDt.loadAnns(self.cocoDt.getAnnIds(imgIds=p.imgIds, catIds=p.catIds))\n else:\n gts=self.cocoGt.loadAnns(self.cocoGt.getAnnIds(imgIds=p.imgIds))\n dts=self.cocoDt.loadAnns(self.cocoDt.getAnnIds(imgIds=p.imgIds))\n\n if p.useSegm:\n _toMask(gts, self.cocoGt)\n _toMask(dts, self.cocoDt)\n self._gts = defaultdict(list) # gt for evaluation\n self._dts = defaultdict(list) # dt for evaluation\n for gt in gts:\n self._gts[gt['image_id'], gt['category_id']].append(gt)\n for dt in dts:\n self._dts[dt['image_id'], dt['category_id']].append(dt)\n self.evalImgs = defaultdict(list) # per-image per-category evaluation results\n self.eval = {} # accumulated evaluation results\n\n def evaluate(self):\n '''\n Run per image evaluation on given images and store results (a list of dict) in self.evalImgs\n :return: None\n '''\n tic = time.time()\n print 'Running per image evaluation... '\n p = self.params\n p.imgIds = list(np.unique(p.imgIds))\n if p.useCats:\n p.catIds = list(np.unique(p.catIds))\n p.maxDets = sorted(p.maxDets)\n self.params=p\n\n self._prepare()\n # loop through images, area range, max detection number\n catIds = p.catIds if p.useCats else [-1]\n\n computeIoU = self.computeIoU\n self.ious = {(imgId, catId): computeIoU(imgId, catId) \\\n for imgId in p.imgIds\n for catId in catIds}\n\n evaluateImg = self.evaluateImg\n maxDet = p.maxDets[-1]\n self.evalImgs = [evaluateImg(imgId, catId, areaRng, maxDet)\n for catId in catIds\n for areaRng in p.areaRng\n for imgId in p.imgIds\n ]\n self._paramsEval = copy.deepcopy(self.params)\n toc = time.time()\n print 'DONE (t=%0.2fs).'%(toc-tic)\n\n def computeIoU(self, imgId, catId):\n p = self.params\n if p.useCats:\n gt = self._gts[imgId,catId]\n dt = self._dts[imgId,catId]\n else:\n gt = [_ for cId in p.catIds for _ in self._gts[imgId,cId]]\n dt = [_ for cId in p.catIds for _ in self._dts[imgId,cId]]\n if len(gt) == 0 and len(dt) ==0:\n return []\n dt = sorted(dt, key=lambda x: -x['score'])\n if len(dt) > p.maxDets[-1]:\n dt=dt[0:p.maxDets[-1]]\n\n if p.useSegm:\n g = [g['segmentation'] for g in gt]\n d = [d['segmentation'] for d in dt]\n else:\n g = [g['bbox'] for g in gt]\n d = [d['bbox'] for d in dt]\n\n # compute iou between each dt and gt region\n iscrowd = [int(o['iscrowd']) for o in gt]\n ious = mask.iou(d,g,iscrowd)\n return ious\n\n def evaluateImg(self, imgId, catId, aRng, maxDet):\n '''\n perform evaluation for single category and image\n :return: dict (single image results)\n '''\n #\n p = self.params\n if p.useCats:\n gt = self._gts[imgId,catId]\n dt = self._dts[imgId,catId]\n else:\n gt = [_ for cId in p.catIds for _ in self._gts[imgId,cId]]\n dt = [_ for cId in p.catIds for _ in self._dts[imgId,cId]]\n if len(gt) == 0 and len(dt) ==0:\n return None\n\n for g in gt:\n if 'ignore' not in g:\n g['ignore'] = 0\n if g['iscrowd'] == 1 or g['ignore'] or (g['area']aRng[1]):\n g['_ignore'] = 1\n else:\n g['_ignore'] = 0\n\n # sort dt highest score first, sort gt ignore last\n # gt = sorted(gt, key=lambda x: x['_ignore'])\n gtind = [ind for (ind, g) in sorted(enumerate(gt), key=lambda (ind, g): g['_ignore']) ]\n\n gt = [gt[ind] for ind in gtind]\n dt = sorted(dt, key=lambda x: -x['score'])[0:maxDet]\n iscrowd = [int(o['iscrowd']) for o in gt]\n # load computed ious\n N_iou = len(self.ious[imgId, catId])\n ious = self.ious[imgId, catId][0:maxDet, np.array(gtind)] if N_iou >0 else self.ious[imgId, catId]\n\n T = len(p.iouThrs)\n G = len(gt)\n D = len(dt)\n gtm = np.zeros((T,G))\n dtm = np.zeros((T,D))\n gtIg = np.array([g['_ignore'] for g in gt])\n dtIg = np.zeros((T,D))\n if not len(ious)==0:\n for tind, t in enumerate(p.iouThrs):\n for dind, d in enumerate(dt):\n # information about best match so far (m=-1 -> unmatched)\n iou = min([t,1-1e-10])\n m = -1\n for gind, g in enumerate(gt):\n # if this gt already matched, and not a crowd, continue\n if gtm[tind,gind]>0 and not iscrowd[gind]:\n continue\n # if dt matched to reg gt, and on ignore gt, stop\n if m>-1 and gtIg[m]==0 and gtIg[gind]==1:\n break\n # continue to next gt unless better match made\n if ious[dind,gind] < iou:\n continue\n # match successful and best so far, store appropriately\n iou=ious[dind,gind]\n m=gind\n # if match made store id of match for both dt and gt\n if m ==-1:\n continue\n dtIg[tind,dind] = gtIg[m]\n dtm[tind,dind] = gt[m]['id']\n gtm[tind,m] = d['id']\n # set unmatched detections outside of area range to ignore\n a = np.array([d['area']aRng[1] for d in dt]).reshape((1, len(dt)))\n dtIg = np.logical_or(dtIg, np.logical_and(dtm==0, np.repeat(a,T,0)))\n # store results for given image and category\n return {\n 'image_id': imgId,\n 'category_id': catId,\n 'aRng': aRng,\n 'maxDet': maxDet,\n 'dtIds': [d['id'] for d in dt],\n 'gtIds': [g['id'] for g in gt],\n 'dtMatches': dtm,\n 'gtMatches': gtm,\n 'dtScores': [d['score'] for d in dt],\n 'gtIgnore': gtIg,\n 'dtIgnore': dtIg,\n }\n\n def accumulate(self, p = None):\n '''\n Accumulate per image evaluation results and store the result in self.eval\n :param p: input params for evaluation\n :return: None\n '''\n print 'Accumulating evaluation results... '\n tic = time.time()\n if not self.evalImgs:\n print 'Please run evaluate() first'\n # allows input customized parameters\n if p is None:\n p = self.params\n p.catIds = p.catIds if p.useCats == 1 else [-1]\n T = len(p.iouThrs)\n R = len(p.recThrs)\n K = len(p.catIds) if p.useCats else 1\n A = len(p.areaRng)\n M = len(p.maxDets)\n precision = -np.ones((T,R,K,A,M)) # -1 for the precision of absent categories\n recall = -np.ones((T,K,A,M))\n\n # create dictionary for future indexing\n _pe = self._paramsEval\n catIds = _pe.catIds if _pe.useCats else [-1]\n setK = set(catIds)\n setA = set(map(tuple, _pe.areaRng))\n setM = set(_pe.maxDets)\n setI = set(_pe.imgIds)\n # get inds to evaluate\n k_list = [n for n, k in enumerate(p.catIds) if k in setK]\n m_list = [m for n, m in enumerate(p.maxDets) if m in setM]\n a_list = [n for n, a in enumerate(map(lambda x: tuple(x), p.areaRng)) if a in setA]\n i_list = [n for n, i in enumerate(p.imgIds) if i in setI]\n # K0 = len(_pe.catIds)\n I0 = len(_pe.imgIds)\n A0 = len(_pe.areaRng)\n # retrieve E at each category, area range, and max number of detections\n for k, k0 in enumerate(k_list):\n Nk = k0*A0*I0\n for a, a0 in enumerate(a_list):\n Na = a0*I0\n for m, maxDet in enumerate(m_list):\n E = [self.evalImgs[Nk+Na+i] for i in i_list]\n E = filter(None, E)\n if len(E) == 0:\n continue\n dtScores = np.concatenate([e['dtScores'][0:maxDet] for e in E])\n\n # different sorting method generates slightly different results.\n # mergesort is used to be consistent as Matlab implementation.\n inds = np.argsort(-dtScores, kind='mergesort')\n\n dtm = np.concatenate([e['dtMatches'][:,0:maxDet] for e in E], axis=1)[:,inds]\n dtIg = np.concatenate([e['dtIgnore'][:,0:maxDet] for e in E], axis=1)[:,inds]\n gtIg = np.concatenate([e['gtIgnore'] for e in E])\n npig = len([ig for ig in gtIg if ig == 0])\n if npig == 0:\n continue\n tps = np.logical_and( dtm, np.logical_not(dtIg) )\n fps = np.logical_and(np.logical_not(dtm), np.logical_not(dtIg) )\n\n tp_sum = np.cumsum(tps, axis=1).astype(dtype=np.float)\n fp_sum = np.cumsum(fps, axis=1).astype(dtype=np.float)\n for t, (tp, fp) in enumerate(zip(tp_sum, fp_sum)):\n tp = np.array(tp)\n fp = np.array(fp)\n nd = len(tp)\n rc = tp / npig\n pr = tp / (fp+tp+np.spacing(1))\n q = np.zeros((R,))\n\n if nd:\n recall[t,k,a,m] = rc[-1]\n else:\n recall[t,k,a,m] = 0\n\n # numpy is slow without cython optimization for accessing elements\n # use python array gets significant speed improvement\n pr = pr.tolist(); q = q.tolist()\n\n for i in range(nd-1, 0, -1):\n if pr[i] > pr[i-1]:\n pr[i-1] = pr[i]\n\n inds = np.searchsorted(rc, p.recThrs)\n try:\n for ri, pi in enumerate(inds):\n q[ri] = pr[pi]\n except:\n pass\n precision[t,:,k,a,m] = np.array(q)\n self.eval = {\n 'params': p,\n 'counts': [T, R, K, A, M],\n 'date': datetime.datetime.now().strftime(\"%Y-%m-%d %H:%M:%S\"),\n 'precision': precision,\n 'recall': recall,\n }\n toc = time.time()\n print 'DONE (t=%0.2fs).'%( toc-tic )\n\n def summarize(self):\n '''\n Compute and display summary metrics for evaluation results.\n Note this functin can *only* be applied on the default parameter setting\n '''\n def _summarize( ap=1, iouThr=None, areaRng='all', maxDets=100 ):\n p = self.params\n iStr = ' {:<18} {} @[ IoU={:<9} | area={:>6} | maxDets={:>3} ] = {}'\n titleStr = 'Average Precision' if ap == 1 else 'Average Recall'\n typeStr = '(AP)' if ap==1 else '(AR)'\n iouStr = '%0.2f:%0.2f'%(p.iouThrs[0], p.iouThrs[-1]) if iouThr is None else '%0.2f'%(iouThr)\n areaStr = areaRng\n maxDetsStr = '%d'%(maxDets)\n\n aind = [i for i, aRng in enumerate(['all', 'small', 'medium', 'large']) if aRng == areaRng]\n mind = [i for i, mDet in enumerate([1, 10, 100]) if mDet == maxDets]\n if ap == 1:\n # dimension of precision: [TxRxKxAxM]\n s = self.eval['precision']\n # IoU\n if iouThr is not None:\n t = np.where(iouThr == p.iouThrs)[0]\n s = s[t]\n # areaRng\n s = s[:,:,:,aind,mind]\n else:\n # dimension of recall: [TxKxAxM]\n s = self.eval['recall']\n s = s[:,:,aind,mind]\n if len(s[s>-1])==0:\n mean_s = -1\n else:\n mean_s = np.mean(s[s>-1])\n print iStr.format(titleStr, typeStr, iouStr, areaStr, maxDetsStr, '%.3f'%(float(mean_s)))\n return mean_s\n\n if not self.eval:\n raise Exception('Please run accumulate() first')\n self.stats = np.zeros((12,))\n self.stats[0] = _summarize(1)\n self.stats[1] = _summarize(1,iouThr=.5)\n self.stats[2] = _summarize(1,iouThr=.75)\n self.stats[3] = _summarize(1,areaRng='small')\n self.stats[4] = _summarize(1,areaRng='medium')\n self.stats[5] = _summarize(1,areaRng='large')\n self.stats[6] = _summarize(0,maxDets=1)\n self.stats[7] = _summarize(0,maxDets=10)\n self.stats[8] = _summarize(0,maxDets=100)\n self.stats[9] = _summarize(0,areaRng='small')\n self.stats[10] = _summarize(0,areaRng='medium')\n self.stats[11] = _summarize(0,areaRng='large')\n\n def __str__(self):\n self.summarize()\n\nclass Params:\n '''\n Params for coco evaluation api\n '''\n def __init__(self):\n self.imgIds = []\n self.catIds = []\n # np.arange causes trouble. the data point on arange is slightly larger than the true value\n self.iouThrs = np.linspace(.5, 0.95, np.round((0.95-.5)/.05)+1, endpoint=True)\n self.recThrs = np.linspace(.0, 1.00, np.round((1.00-.0)/.01)+1, endpoint=True)\n self.maxDets = [1,10,100]\n self.areaRng = [ [0**2,1e5**2], [0**2, 32**2], [32**2, 96**2], [96**2, 1e5**2] ]\n self.useSegm = 0\n self.useCats = 1" }, { "path": "lib/pycocotools/license.txt", "content": "Copyright (c) 2014, Piotr Dollar and Tsung-Yi Lin\nAll rights reserved.\n\nRedistribution and use in source and binary forms, with or without\nmodification, are permitted provided that the following conditions are met: \n\n1. Redistributions of source code must retain the above copyright notice, this\n list of conditions and the following disclaimer. \n2. Redistributions in binary form must reproduce the above copyright notice,\n this list of conditions and the following disclaimer in the documentation\n and/or other materials provided with the distribution. \n\nTHIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS \"AS IS\" AND\nANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED\nWARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE\nDISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR\nANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES\n(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;\nLOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND\nON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT\n(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS\nSOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.\n\nThe views and conclusions contained in the software and documentation are those\nof the authors and should not be interpreted as representing official policies, \neither expressed or implied, of the FreeBSD Project.\n" }, { "path": "lib/pycocotools/mask.py", "content": "__author__ = 'tsungyi'\n\nimport pycocotools._mask as _mask\n\n# Interface for manipulating masks stored in RLE format.\n#\n# RLE is a simple yet efficient format for storing binary masks. RLE\n# first divides a vector (or vectorized image) into a series of piecewise\n# constant regions and then for each piece simply stores the length of\n# that piece. For example, given M=[0 0 1 1 1 0 1] the RLE counts would\n# be [2 3 1 1], or for M=[1 1 1 1 1 1 0] the counts would be [0 6 1]\n# (note that the odd counts are always the numbers of zeros). Instead of\n# storing the counts directly, additional compression is achieved with a\n# variable bitrate representation based on a common scheme called LEB128.\n#\n# Compression is greatest given large piecewise constant regions.\n# Specifically, the size of the RLE is proportional to the number of\n# *boundaries* in M (or for an image the number of boundaries in the y\n# direction). Assuming fairly simple shapes, the RLE representation is\n# O(sqrt(n)) where n is number of pixels in the object. Hence space usage\n# is substantially lower, especially for large simple objects (large n).\n#\n# Many common operations on masks can be computed directly using the RLE\n# (without need for decoding). This includes computations such as area,\n# union, intersection, etc. All of these operations are linear in the\n# size of the RLE, in other words they are O(sqrt(n)) where n is the area\n# of the object. Computing these operations on the original mask is O(n).\n# Thus, using the RLE can result in substantial computational savings.\n#\n# The following API functions are defined:\n# encode - Encode binary masks using RLE.\n# decode - Decode binary masks encoded via RLE.\n# merge - Compute union or intersection of encoded masks.\n# iou - Compute intersection over union between masks.\n# area - Compute area of encoded masks.\n# toBbox - Get bounding boxes surrounding encoded masks.\n# frPyObjects - Convert polygon, bbox, and uncompressed RLE to encoded RLE mask.\n#\n# Usage:\n# Rs = encode( masks )\n# masks = decode( Rs )\n# R = merge( Rs, intersect=false )\n# o = iou( dt, gt, iscrowd )\n# a = area( Rs )\n# bbs = toBbox( Rs )\n# Rs = frPyObjects( [pyObjects], h, w )\n#\n# In the API the following formats are used:\n# Rs - [dict] Run-length encoding of binary masks\n# R - dict Run-length encoding of binary mask\n# masks - [hxwxn] Binary mask(s) (must have type np.ndarray(dtype=uint8) in column-major order)\n# iscrowd - [nx1] list of np.ndarray. 1 indicates corresponding gt image has crowd region to ignore\n# bbs - [nx4] Bounding box(es) stored as [x y w h]\n# poly - Polygon stored as [[x1 y1 x2 y2...],[x1 y1 ...],...] (2D list)\n# dt,gt - May be either bounding boxes or encoded masks\n# Both poly and bbs are 0-indexed (bbox=[0 0 1 1] encloses first pixel).\n#\n# Finally, a note about the intersection over union (iou) computation.\n# The standard iou of a ground truth (gt) and detected (dt) object is\n# iou(gt,dt) = area(intersect(gt,dt)) / area(union(gt,dt))\n# For \"crowd\" regions, we use a modified criteria. If a gt object is\n# marked as \"iscrowd\", we allow a dt to match any subregion of the gt.\n# Choosing gt' in the crowd gt that best matches the dt can be done using\n# gt'=intersect(dt,gt). Since by definition union(gt',dt)=dt, computing\n# iou(gt,dt,iscrowd) = iou(gt',dt) = area(intersect(gt,dt)) / area(dt)\n# For crowd gt regions we use this modified criteria above for the iou.\n#\n# To compile run \"python setup.py build_ext --inplace\"\n# Please do not contact us for help with compiling.\n#\n# Microsoft COCO Toolbox. version 2.0\n# Data, paper, and tutorials available at: http://mscoco.org/\n# Code written by Piotr Dollar and Tsung-Yi Lin, 2015.\n# Licensed under the Simplified BSD License [see coco/license.txt]\n\nencode = _mask.encode\ndecode = _mask.decode\niou = _mask.iou\nmerge = _mask.merge\narea = _mask.area\ntoBbox = _mask.toBbox\nfrPyObjects = _mask.frPyObjects" }, { "path": "lib/pycocotools/maskApi.c", "content": "/**************************************************************************\n* Microsoft COCO Toolbox. version 2.0\n* Data, paper, and tutorials available at: http://mscoco.org/\n* Code written by Piotr Dollar and Tsung-Yi Lin, 2015.\n* Licensed under the Simplified BSD License [see coco/license.txt]\n**************************************************************************/\n#include \"maskApi.h\"\n#include \n#include \n\nuint umin( uint a, uint b ) { return (ab) ? a : b; }\n\nvoid rleInit( RLE *R, siz h, siz w, siz m, uint *cnts ) {\n R->h=h; R->w=w; R->m=m; R->cnts=(m==0)?0:malloc(sizeof(uint)*m);\n if(cnts) for(siz j=0; jcnts[j]=cnts[j];\n}\n\nvoid rleFree( RLE *R ) {\n free(R->cnts); R->cnts=0;\n}\n\nvoid rlesInit( RLE **R, siz n ) {\n *R = (RLE*) malloc(sizeof(RLE)*n);\n for(siz i=0; i0 ) {\n c=umin(ca,cb); cc+=c; ct=0;\n ca-=c; if(!ca && a0) {\n crowd=iscrowd!=NULL && iscrowd[g];\n if(dt[d].h!=gt[g].h || dt[d].w!=gt[g].w) { o[g*m+d]=-1; continue; }\n siz ka, kb, a, b; uint c, ca, cb, ct, i, u; bool va, vb;\n ca=dt[d].cnts[0]; ka=dt[d].m; va=vb=0;\n cb=gt[g].cnts[0]; kb=gt[g].m; a=b=1; i=u=0; ct=1;\n while( ct>0 ) {\n c=umin(ca,cb); if(va||vb) { u+=c; if(va&&vb) i+=c; } ct=0;\n ca-=c; if(!ca && ad?1:c=dy && xs>xe) || (dxye);\n if(flip) { t=xs; xs=xe; xe=t; t=ys; ys=ye; ye=t; }\n s = dx>=dy ? (double)(ye-ys)/dx : (double)(xe-xs)/dy;\n if(dx>=dy) for( int d=0; d<=dx; d++ ) {\n t=flip?dx-d:d; u[m]=t+xs; v[m]=(int)(ys+s*t+.5); m++;\n } else for( int d=0; d<=dy; d++ ) {\n t=flip?dy-d:d; v[m]=t+ys; u[m]=(int)(xs+s*t+.5); m++;\n }\n }\n // get points along y-boundary and downsample\n free(x); free(y); k=m; m=0; double xd, yd;\n x=malloc(sizeof(int)*k); y=malloc(sizeof(int)*k);\n for( j=1; jw-1 ) continue;\n yd=(double)(v[j]h) yd=h; yd=ceil(yd);\n x[m]=(int) xd; y[m]=(int) yd; m++;\n }\n // compute rle encoding given y-boundary points\n k=m; a=malloc(sizeof(uint)*(k+1));\n for( j=0; j0) b[m++]=a[j++]; else {\n j++; if(jm, p=0; long x; bool more;\n char *s=malloc(sizeof(char)*m*6);\n for( i=0; icnts[i]; if(i>2) x-=(long) R->cnts[i-2]; more=1;\n while( more ) {\n char c=x & 0x1f; x >>= 5; more=(c & 0x10) ? x!=-1 : x!=0;\n if(more) c |= 0x20; c+=48; s[p++]=c;\n }\n }\n s[p]=0; return s;\n}\n\nvoid rleFrString( RLE *R, char *s, siz h, siz w ) {\n siz m=0, p=0, k; long x; bool more; uint *cnts;\n while( s[m] ) m++; cnts=malloc(sizeof(uint)*m); m=0;\n while( s[p] ) {\n x=0; k=0; more=1;\n while( more ) {\n char c=s[p]-48; x |= (c & 0x1f) << 5*k;\n more = c & 0x20; p++; k++;\n if(!more && (c & 0x10)) x |= -1 << 5*k;\n }\n if(m>2) x+=(long) cnts[m-2]; cnts[m++]=(uint) x;\n }\n rleInit(R,h,w,m,cnts); free(cnts);\n}\n" }, { "path": "lib/pycocotools/maskApi.h", "content": "/**************************************************************************\n* Microsoft COCO Toolbox. version 2.0\n* Data, paper, and tutorials available at: http://mscoco.org/\n* Code written by Piotr Dollar and Tsung-Yi Lin, 2015.\n* Licensed under the Simplified BSD License [see coco/license.txt]\n**************************************************************************/\n#pragma once\n#include \n\ntypedef unsigned int uint;\ntypedef unsigned long siz;\ntypedef unsigned char byte;\ntypedef double* BB;\ntypedef struct { siz h, w, m; uint *cnts; } RLE;\n\n// Initialize/destroy RLE.\nvoid rleInit( RLE *R, siz h, siz w, siz m, uint *cnts );\nvoid rleFree( RLE *R );\n\n// Initialize/destroy RLE array.\nvoid rlesInit( RLE **R, siz n );\nvoid rlesFree( RLE **R, siz n );\n\n// Encode binary masks using RLE.\nvoid rleEncode( RLE *R, const byte *mask, siz h, siz w, siz n );\n\n// Decode binary masks encoded via RLE.\nvoid rleDecode( const RLE *R, byte *mask, siz n );\n\n// Compute union or intersection of encoded masks.\nvoid rleMerge( const RLE *R, RLE *M, siz n, bool intersect );\n\n// Compute area of encoded masks.\nvoid rleArea( const RLE *R, siz n, uint *a );\n\n// Compute intersection over union between masks.\nvoid rleIou( RLE *dt, RLE *gt, siz m, siz n, byte *iscrowd, double *o );\n\n// Compute intersection over union between bounding boxes.\nvoid bbIou( BB dt, BB gt, siz m, siz n, byte *iscrowd, double *o );\n\n// Get bounding boxes surrounding encoded masks.\nvoid rleToBbox( const RLE *R, BB bb, siz n );\n\n// Convert bounding boxes to encoded masks.\nvoid rleFrBbox( RLE *R, const BB bb, siz h, siz w, siz n );\n\n// Convert polygon to encoded mask.\nvoid rleFrPoly( RLE *R, const double *xy, siz k, siz h, siz w );\n\n// Get compressed string representation of encoded mask.\nchar* rleToString( const RLE *R );\n\n// Convert from compressed string representation of encoded mask.\nvoid rleFrString( RLE *R, char *s, siz h, siz w );\n" }, { "path": "lib/roi_data_layer/__init__.py", "content": "# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n" }, { "path": "lib/roi_data_layer/layer.py", "content": "# --------------------------------------------------------\n# Fast R-CNN with OHEM\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick and Abhinav Shrivastava\n# --------------------------------------------------------\n\n\"\"\"\nThe data layer used during training to train a Fast R-CNN network.\nRoIDataLayer implements a Caffe Python layer.\n\"\"\"\n\nimport caffe\nfrom fast_rcnn.config import cfg\nfrom roi_data_layer.minibatch import get_minibatch, get_allrois_minibatch, get_ohem_minibatch\nimport numpy as np\nimport yaml\nfrom multiprocessing import Process, Queue\n\nclass RoIDataLayer(caffe.Layer):\n \"\"\"Fast R-CNN data layer used for training.\"\"\"\n\n def _shuffle_roidb_inds(self):\n \"\"\"Randomly permute the training roidb.\"\"\"\n if cfg.TRAIN.ASPECT_GROUPING:\n widths = np.array([r['width'] for r in self._roidb])\n heights = np.array([r['height'] for r in self._roidb])\n horz = (widths >= heights)\n vert = np.logical_not(horz)\n horz_inds = np.where(horz)[0]\n vert_inds = np.where(vert)[0]\n inds = np.hstack((\n np.random.permutation(horz_inds),\n np.random.permutation(vert_inds)))\n inds = np.reshape(inds, (-1, 2))\n row_perm = np.random.permutation(np.arange(inds.shape[0]))\n inds = np.reshape(inds[row_perm, :], (-1,))\n self._perm = inds\n else:\n self._perm = np.random.permutation(np.arange(len(self._roidb)))\n self._cur = 0\n\n def _get_next_minibatch_inds(self):\n \"\"\"Return the roidb indices for the next minibatch.\"\"\"\n if self._cur + cfg.TRAIN.IMS_PER_BATCH >= len(self._roidb):\n self._shuffle_roidb_inds()\n\n db_inds = self._perm[self._cur:self._cur + cfg.TRAIN.IMS_PER_BATCH]\n self._cur += cfg.TRAIN.IMS_PER_BATCH\n return db_inds\n\n def _get_next_minibatch(self):\n \"\"\"Return the blobs to be used for the next minibatch.\n\n If cfg.TRAIN.USE_PREFETCH is True, then blobs will be computed in a\n separate process and made available through self._blob_queue.\n \"\"\"\n if cfg.TRAIN.USE_PREFETCH:\n return self._blob_queue.get()\n else:\n db_inds = self._get_next_minibatch_inds()\n minibatch_db = [self._roidb[i] for i in db_inds]\n if cfg.TRAIN.USE_OHEM:\n blobs = get_allrois_minibatch(minibatch_db, self._num_classes)\n else:\n blobs = get_minibatch(minibatch_db, self._num_classes)\n\n return blobs\n\n def set_roidb(self, roidb):\n \"\"\"Set the roidb to be used by this layer during training.\"\"\"\n self._roidb = roidb\n self._shuffle_roidb_inds()\n if cfg.TRAIN.USE_PREFETCH:\n self._blob_queue = Queue(10)\n self._prefetch_process = BlobFetcher(self._blob_queue,\n self._roidb,\n self._num_classes)\n self._prefetch_process.start()\n # Terminate the child process when the parent exists\n def cleanup():\n print 'Terminating BlobFetcher'\n self._prefetch_process.terminate()\n self._prefetch_process.join()\n import atexit\n atexit.register(cleanup)\n\n def setup(self, bottom, top):\n \"\"\"Setup the RoIDataLayer.\"\"\"\n\n # parse the layer parameter string, which must be valid YAML\n layer_params = yaml.load(self.param_str_)\n\n self._num_classes = layer_params['num_classes']\n\n self._name_to_top_map = {}\n\n # data blob: holds a batch of N images, each with 3 channels\n idx = 0\n top[idx].reshape(cfg.TRAIN.IMS_PER_BATCH, 3,\n max(cfg.TRAIN.SCALES), cfg.TRAIN.MAX_SIZE)\n self._name_to_top_map['data'] = idx\n idx += 1\n\n if cfg.TRAIN.HAS_RPN:\n top[idx].reshape(1, 3)\n self._name_to_top_map['im_info'] = idx\n idx += 1\n\n top[idx].reshape(1, 4)\n self._name_to_top_map['gt_boxes'] = idx\n idx += 1\n else: # not using RPN\n # rois blob: holds R regions of interest, each is a 5-tuple\n # (n, x1, y1, x2, y2) specifying an image batch index n and a\n # rectangle (x1, y1, x2, y2)\n top[idx].reshape(1, 5)\n self._name_to_top_map['rois'] = idx\n idx += 1\n\n # labels blob: R categorical labels in [0, ..., K] for K foreground\n # classes plus background\n top[idx].reshape(1)\n self._name_to_top_map['labels'] = idx\n idx += 1\n\n if cfg.TRAIN.BBOX_REG:\n # bbox_targets blob: R bounding-box regression targets with 4\n # targets per class\n top[idx].reshape(1, self._num_classes * 4)\n self._name_to_top_map['bbox_targets'] = idx\n idx += 1\n\n # bbox_inside_weights blob: At most 4 targets per roi are active;\n # thisbinary vector sepcifies the subset of active targets\n top[idx].reshape(1, self._num_classes * 4)\n self._name_to_top_map['bbox_inside_weights'] = idx\n idx += 1\n\n top[idx].reshape(1, self._num_classes * 4)\n self._name_to_top_map['bbox_outside_weights'] = idx\n idx += 1\n\n print 'RoiDataLayer: name_to_top:', self._name_to_top_map\n assert len(top) == len(self._name_to_top_map)\n\n def forward(self, bottom, top):\n \"\"\"Get blobs and copy them into this layer's top blob vector.\"\"\"\n blobs = self._get_next_minibatch()\n\n for blob_name, blob in blobs.iteritems():\n top_ind = self._name_to_top_map[blob_name]\n # Reshape net's input blobs\n top[top_ind].reshape(*(blob.shape))\n # Copy data into net's input blobs\n top[top_ind].data[...] = blob.astype(np.float32, copy=False)\n\n def backward(self, top, propagate_down, bottom):\n \"\"\"This layer does not propagate gradients.\"\"\"\n pass\n\n def reshape(self, bottom, top):\n \"\"\"Reshaping happens during the call to forward.\"\"\"\n pass\n\nclass OHEMDataLayer(caffe.Layer):\n \"\"\"Online Hard-example Mining Layer.\"\"\"\n def setup(self, bottom, top):\n \"\"\"Setup the OHEMDataLayer.\"\"\"\n\n # parse the layer parameter string, which must be valid YAML\n layer_params = yaml.load(self.param_str_)\n\n self._num_classes = layer_params['num_classes']\n\n self._name_to_bottom_map = {\n 'cls_prob_readonly': 0,\n 'bbox_pred_readonly': 1,\n 'rois': 2,\n 'labels': 3}\n\n if cfg.TRAIN.BBOX_REG:\n self._name_to_bottom_map['bbox_targets'] = 4\n self._name_to_bottom_map['bbox_loss_weights'] = 5\n\n self._name_to_top_map = {}\n\n # assert cfg.TRAIN.HAS_RPN == False\n # data blob: holds a batch of N images, each with 3 channels\n idx = 0\n # rois blob: holds R regions of interest, each is a 5-tuple\n # (n, x1, y1, x2, y2) specifying an image batch index n and a\n # rectangle (x1, y1, x2, y2)\n top[idx].reshape(1, 5)\n self._name_to_top_map['rois_hard'] = idx\n idx += 1\n\n # labels blob: R categorical labels in [0, ..., K] for K foreground\n # classes plus background\n top[idx].reshape(1)\n self._name_to_top_map['labels_hard'] = idx\n idx += 1\n\n if cfg.TRAIN.BBOX_REG:\n # bbox_targets blob: R bounding-box regression targets with 4\n # targets per class\n top[idx].reshape(1, self._num_classes * 4)\n self._name_to_top_map['bbox_targets_hard'] = idx\n idx += 1\n\n # bbox_inside_weights blob: At most 4 targets per roi are active;\n # thisbinary vector sepcifies the subset of active targets\n top[idx].reshape(1, self._num_classes * 4)\n self._name_to_top_map['bbox_inside_weights_hard'] = idx\n idx += 1\n\n top[idx].reshape(1, self._num_classes * 4)\n self._name_to_top_map['bbox_outside_weights_hard'] = idx\n idx += 1\n\n print 'OHEMDataLayer: name_to_top:', self._name_to_top_map\n assert len(top) == len(self._name_to_top_map)\n\n def forward(self, bottom, top):\n \"\"\"Compute loss, select RoIs using OHEM. Use RoIs to get blobs and copy them into this layer's top blob vector.\"\"\"\n\n cls_prob = bottom[0].data\n bbox_pred = bottom[1].data\n rois = bottom[2].data\n labels = bottom[3].data\n if cfg.TRAIN.BBOX_REG:\n bbox_target = bottom[4].data\n bbox_inside_weights = bottom[5].data\n bbox_outside_weights = bottom[6].data\n else:\n bbox_target = None\n bbox_inside_weights = None\n bbox_outside_weights = None\n\n flt_min = np.finfo(float).eps\n # classification loss\n loss = [ -1 * np.log(max(x, flt_min)) \\\n for x in [cls_prob[i,label] for i, label in enumerate(labels)]]\n\n if cfg.TRAIN.BBOX_REG:\n # bounding-box regression loss\n # d := w * (b0 - b1)\n # smoothL1(x) = 0.5 * x^2 if |x| < 1\n # |x| - 0.5 otherwise\n def smoothL1(x):\n if abs(x) < 1:\n return 0.5 * x * x\n else:\n return abs(x) - 0.5\n\n bbox_loss = np.zeros(labels.shape[0])\n for i in np.where(labels > 0 )[0]:\n indices = np.where(bbox_inside_weights[i,:] != 0)[0]\n bbox_loss[i] = sum(bbox_outside_weights[i,indices] * [smoothL1(x) \\\n for x in bbox_inside_weights[i,indices] * (bbox_pred[i,indices] - bbox_target[i,indices])])\n loss += bbox_loss\n\n blobs = get_ohem_minibatch(loss, rois, labels, bbox_target, \\\n bbox_inside_weights, bbox_outside_weights)\n\n for blob_name, blob in blobs.iteritems():\n top_ind = self._name_to_top_map[blob_name]\n # Reshape net's input blobs\n top[top_ind].reshape(*(blob.shape))\n # Copy data into net's input blobs\n top[top_ind].data[...] = blob.astype(np.float32, copy=False)\n\n def backward(self, top, propagate_down, bottom):\n \"\"\"This layer does not propagate gradients.\"\"\"\n pass\n\n def reshape(self, bottom, top):\n \"\"\"Reshaping happens during the call to forward.\"\"\"\n pass\n\nclass BlobFetcher(Process):\n \"\"\"Experimental class for prefetching blobs in a separate process.\"\"\"\n def __init__(self, queue, roidb, num_classes):\n super(BlobFetcher, self).__init__()\n self._queue = queue\n self._roidb = roidb\n self._num_classes = num_classes\n self._perm = None\n self._cur = 0\n self._shuffle_roidb_inds()\n # fix the random seed for reproducibility\n np.random.seed(cfg.RNG_SEED)\n\n def _shuffle_roidb_inds(self):\n \"\"\"Randomly permute the training roidb.\"\"\"\n # TODO(rbg): remove duplicated code\n self._perm = np.random.permutation(np.arange(len(self._roidb)))\n self._cur = 0\n\n def _get_next_minibatch_inds(self):\n \"\"\"Return the roidb indices for the next minibatch.\"\"\"\n # TODO(rbg): remove duplicated code\n if self._cur + cfg.TRAIN.IMS_PER_BATCH >= len(self._roidb):\n self._shuffle_roidb_inds()\n\n db_inds = self._perm[self._cur:self._cur + cfg.TRAIN.IMS_PER_BATCH]\n self._cur += cfg.TRAIN.IMS_PER_BATCH\n return db_inds\n\n def run(self):\n print 'BlobFetcher started'\n while True:\n db_inds = self._get_next_minibatch_inds()\n minibatch_db = [self._roidb[i] for i in db_inds]\n if cfg.TRAIN.USE_OHEM:\n blobs = get_allrois_minibatch(minibatch_db, self._num_classes)\n else:\n blobs = get_minibatch(minibatch_db, self._num_classes)\n self._queue.put(blobs)\n" }, { "path": "lib/roi_data_layer/minibatch.py", "content": "# --------------------------------------------------------\n# Fast R-CNN with OHEM\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick and Abhinav Shrivastava\n# --------------------------------------------------------\n\n\"\"\"Compute minibatch blobs for training a Fast R-CNN network.\"\"\"\n\nimport numpy as np\nimport numpy.random as npr\nimport cv2\nfrom fast_rcnn.config import cfg\nfrom utils.blob import prep_im_for_blob, im_list_to_blob\nfrom fast_rcnn.nms_wrapper import nms\n\ndef get_minibatch(roidb, num_classes):\n \"\"\"Given a roidb, construct a minibatch sampled from it.\"\"\"\n num_images = len(roidb)\n # Sample random scales to use for each image in this batch\n random_scale_inds = npr.randint(0, high=len(cfg.TRAIN.SCALES),\n size=num_images)\n assert(cfg.TRAIN.BATCH_SIZE % num_images == 0) or cfg.TRAIN.USE_OHEM, \\\n 'num_images ({}) must divide BATCH_SIZE ({})'. \\\n format(num_images, cfg.TRAIN.BATCH_SIZE)\n rois_per_image = np.inf if cfg.TRAIN.USE_OHEM else cfg.TRAIN.BATCH_SIZE / num_images\n fg_rois_per_image = np.round(cfg.TRAIN.FG_FRACTION * rois_per_image)\n\n # Get the input image blob, formatted for caffe\n im_blob, im_scales = _get_image_blob(roidb, random_scale_inds)\n\n blobs = {'data': im_blob}\n\n if cfg.TRAIN.HAS_RPN:\n assert len(im_scales) == 1, \"Single batch only\"\n assert len(roidb) == 1, \"Single batch only\"\n # gt boxes: (x1, y1, x2, y2, cls)\n gt_inds = np.where(roidb[0]['gt_classes'] != 0)[0]\n gt_boxes = np.empty((len(gt_inds), 5), dtype=np.float32)\n gt_boxes[:, 0:4] = roidb[0]['boxes'][gt_inds, :] * im_scales[0]\n gt_boxes[:, 4] = roidb[0]['gt_classes'][gt_inds]\n blobs['gt_boxes'] = gt_boxes\n blobs['im_info'] = np.array(\n [[im_blob.shape[2], im_blob.shape[3], im_scales[0]]],\n dtype=np.float32)\n else: # not using RPN\n # Now, build the region of interest and label blobs\n rois_blob = np.zeros((0, 5), dtype=np.float32)\n labels_blob = np.zeros((0), dtype=np.float32)\n bbox_targets_blob = np.zeros((0, 4 * num_classes), dtype=np.float32)\n bbox_inside_blob = np.zeros(bbox_targets_blob.shape, dtype=np.float32)\n # all_overlaps = []\n for im_i in xrange(num_images):\n labels, overlaps, im_rois, bbox_targets, bbox_inside_weights \\\n = _sample_rois(roidb[im_i], fg_rois_per_image, rois_per_image,\n num_classes)\n\n # Add to RoIs blob\n rois = _project_im_rois(im_rois, im_scales[im_i])\n batch_ind = im_i * np.ones((rois.shape[0], 1))\n rois_blob_this_image = np.hstack((batch_ind, rois))\n rois_blob = np.vstack((rois_blob, rois_blob_this_image))\n\n # Add to labels, bbox targets, and bbox loss blobs\n labels_blob = np.hstack((labels_blob, labels))\n bbox_targets_blob = np.vstack((bbox_targets_blob, bbox_targets))\n bbox_inside_blob = np.vstack((bbox_inside_blob, bbox_inside_weights))\n # all_overlaps = np.hstack((all_overlaps, overlaps))\n\n # For debug visualizations\n # _vis_minibatch(im_blob, rois_blob, labels_blob, all_overlaps)\n\n blobs['rois'] = rois_blob\n blobs['labels'] = labels_blob\n\n if cfg.TRAIN.BBOX_REG:\n blobs['bbox_targets'] = bbox_targets_blob\n blobs['bbox_inside_weights'] = bbox_inside_blob\n blobs['bbox_outside_weights'] = \\\n np.array(bbox_inside_blob > 0).astype(np.float32)\n\n return blobs\n\ndef get_allrois_minibatch(roidb, num_classes):\n \"\"\"Given a roidb, construct a minibatch sampled from it.\"\"\"\n num_images = len(roidb)\n # Sample random scales to use for each image in this batch\n random_scale_inds = npr.randint(0, high=len(cfg.TRAIN.SCALES),\n size=num_images)\n assert(cfg.TRAIN.BATCH_SIZE % num_images == 0), \\\n 'num_images ({}) must divide BATCH_SIZE ({})'. \\\n format(num_images, cfg.TRAIN.BATCH_SIZE)\n\n # Get the input image blob, formatted for caffe\n im_blob, im_scales = _get_image_blob(roidb, random_scale_inds)\n\n blobs = {'data': im_blob}\n\n if cfg.TRAIN.HAS_RPN:\n # Doesn't support RPN yet.\n # assert False\n assert len(im_scales) == 1, \"Single batch only\"\n assert len(roidb) == 1, \"Single batch only\"\n # gt boxes: (x1, y1, x2, y2, cls)\n gt_inds = np.where(roidb[0]['gt_classes'] != 0)[0]\n gt_boxes = np.empty((len(gt_inds), 5), dtype=np.float32)\n gt_boxes[:, 0:4] = roidb[0]['boxes'][gt_inds, :] * im_scales[0]\n gt_boxes[:, 4] = roidb[0]['gt_classes'][gt_inds]\n blobs['gt_boxes'] = gt_boxes\n blobs['im_info'] = np.array(\n [[im_blob.shape[2], im_blob.shape[3], im_scales[0]]],\n dtype=np.float32)\n else: # not using RPN\n # Now, build the region of interest and label blobs\n rois_blob = np.zeros((0, 5), dtype=np.float32)\n labels_blob = np.zeros((0), dtype=np.float32)\n bbox_targets_blob = np.zeros((0, 4 * num_classes), dtype=np.float32)\n bbox_inside_blob = np.zeros(bbox_targets_blob.shape, dtype=np.float32)\n\n for im_i in xrange(num_images):\n labels, overlaps, im_rois, bbox_targets, bbox_inside_weights \\\n = _all_rois(roidb[im_i], num_classes)\n\n # Add to RoIs blob\n rois = _project_im_rois(im_rois, im_scales[im_i])\n batch_ind = im_i * np.ones((rois.shape[0], 1))\n rois_blob_this_image = np.hstack((batch_ind, rois))\n rois_blob = np.vstack((rois_blob, rois_blob_this_image))\n\n # Add to labels, bbox targets, and bbox loss blobs\n labels_blob = np.hstack((labels_blob, labels))\n bbox_targets_blob = np.vstack((bbox_targets_blob, bbox_targets))\n bbox_inside_blob = np.vstack((bbox_inside_blob, bbox_inside_weights))\n\n blobs['rois'] = rois_blob\n blobs['labels'] = labels_blob\n\n if cfg.TRAIN.BBOX_REG:\n blobs['bbox_targets'] = bbox_targets_blob\n blobs['bbox_inside_weights'] = bbox_inside_blob\n blobs['bbox_outside_weights'] = \\\n np.array(bbox_inside_blob > 0).astype(np.float32)\n\n return blobs\n\n\ndef get_ohem_minibatch(loss, rois, labels, bbox_targets=None,\n bbox_inside_weights=None, bbox_outside_weights=None):\n \"\"\"Given rois and their loss, construct a minibatch using OHEM.\"\"\"\n loss = np.array(loss)\n\n if cfg.TRAIN.OHEM_USE_NMS:\n # Do NMS using loss for de-dup and diversity\n keep_inds = []\n nms_thresh = cfg.TRAIN.OHEM_NMS_THRESH\n source_img_ids = [roi[0] for roi in rois]\n for img_id in np.unique(source_img_ids):\n for label in np.unique(labels):\n sel_indx = np.where(np.logical_and(labels == label, \\\n source_img_ids == img_id))[0]\n if not len(sel_indx):\n continue\n boxes = np.concatenate((rois[sel_indx, 1:],\n loss[sel_indx][:,np.newaxis]), axis=1).astype(np.float32)\n keep_inds.extend(sel_indx[nms(boxes, nms_thresh)])\n\n hard_keep_inds = select_hard_examples(loss[keep_inds])\n hard_inds = np.array(keep_inds)[hard_keep_inds]\n else:\n hard_inds = select_hard_examples(loss)\n\n blobs = {'rois_hard': rois[hard_inds, :].copy(),\n 'labels_hard': labels[hard_inds].copy()}\n if bbox_targets is not None:\n assert cfg.TRAIN.BBOX_REG\n blobs['bbox_targets_hard'] = bbox_targets[hard_inds, :].copy()\n blobs['bbox_inside_weights_hard'] = bbox_inside_weights[hard_inds, :].copy()\n blobs['bbox_outside_weights_hard'] = bbox_outside_weights[hard_inds, :].copy()\n\n return blobs\n\ndef select_hard_examples(loss):\n \"\"\"Select hard rois.\"\"\"\n # Sort and select top hard examples.\n sorted_indices = np.argsort(loss)[::-1]\n hard_keep_inds = sorted_indices[0:np.minimum(len(loss), cfg.TRAIN.BATCH_SIZE)]\n # (explore more ways of selecting examples in this function; e.g., sampling)\n\n return hard_keep_inds\n\ndef _sample_rois(roidb, fg_rois_per_image, rois_per_image, num_classes):\n \"\"\"Generate a random sample of RoIs comprising foreground and background\n examples.\n \"\"\"\n # label = class RoI has max overlap with\n labels = roidb['max_classes']\n overlaps = roidb['max_overlaps']\n rois = roidb['boxes']\n\n # Select foreground RoIs as those with >= FG_THRESH overlap\n fg_inds = np.where(overlaps >= cfg.TRAIN.FG_THRESH)[0]\n # foreground RoIs\n fg_rois_per_this_image = np.minimum(fg_rois_per_image, fg_inds.size)\n # Sample foreground regions without replacement\n if fg_inds.size > 0:\n fg_inds = npr.choice(\n fg_inds, size=fg_rois_per_this_image, replace=False)\n\n # Select background RoIs as those within [BG_THRESH_LO, BG_THRESH_HI)\n bg_inds = np.where((overlaps < cfg.TRAIN.BG_THRESH_HI) &\n (overlaps >= cfg.TRAIN.BG_THRESH_LO))[0]\n # Compute number of background RoIs to take from this image (guarding\n # against there being fewer than desired)\n bg_rois_per_this_image = rois_per_image - fg_rois_per_this_image\n bg_rois_per_this_image = np.minimum(bg_rois_per_this_image,\n bg_inds.size)\n # Sample foreground regions without replacement\n if bg_inds.size > 0:\n bg_inds = npr.choice(\n bg_inds, size=bg_rois_per_this_image, replace=False)\n\n # The indices that we're selecting (both fg and bg)\n keep_inds = np.append(fg_inds, bg_inds)\n # Select sampled values from various arrays:\n labels = labels[keep_inds]\n # Clamp labels for the background RoIs to 0\n labels[fg_rois_per_this_image:] = 0\n overlaps = overlaps[keep_inds]\n rois = rois[keep_inds]\n\n bbox_targets, bbox_inside_weights = _get_bbox_regression_labels(\n roidb['bbox_targets'][keep_inds, :], num_classes)\n\n return labels, overlaps, rois, bbox_targets, bbox_inside_weights\n\ndef _all_rois(roidb, num_classes):\n \"\"\"Generate a random sample of RoIs comprising foreground and background\n examples.\n \"\"\"\n # label = class RoI has max overlap with\n labels = roidb['max_classes']\n overlaps = roidb['max_overlaps']\n rois = roidb['boxes']\n\n # To use custom cfg.TRAIN.BG_THRESH_LO, comment the following assert.\n assert cfg.TRAIN.BG_THRESH_LO == 0.0, \\\n \"OHEM works best with BG_THRESH_LO = 0.0 (current value is {}).\".format(cfg.TRAIN.BG_THRESH_LO)\n\n # Select foreground (background) RoIs.\n fg_inds = np.where(overlaps >= cfg.TRAIN.FG_THRESH)[0]\n bg_inds = np.where(overlaps < cfg.TRAIN.BG_THRESH_HI)[0]\n\n # All RoIs.\n keep_inds = np.append(fg_inds, bg_inds)\n\n # Select sampled values from various arrays:\n labels = labels[keep_inds]\n # Clamp labels for the background RoIs to 0\n labels[len(fg_inds):] = 0\n overlaps = overlaps[keep_inds]\n rois = rois[keep_inds]\n\n bbox_targets, bbox_inside_weights = _get_bbox_regression_labels(\n roidb['bbox_targets'][keep_inds, :], num_classes)\n\n return labels, overlaps, rois, bbox_targets, bbox_inside_weights\n\ndef _get_image_blob(roidb, scale_inds):\n \"\"\"Builds an input blob from the images in the roidb at the specified\n scales.\n \"\"\"\n num_images = len(roidb)\n processed_ims = []\n im_scales = []\n for i in xrange(num_images):\n im = cv2.imread(roidb[i]['image'])\n if roidb[i]['flipped']:\n im = im[:, ::-1, :]\n target_size = cfg.TRAIN.SCALES[scale_inds[i]]\n im, im_scale = prep_im_for_blob(im, cfg.PIXEL_MEANS, target_size,\n cfg.TRAIN.MAX_SIZE)\n im_scales.append(im_scale)\n processed_ims.append(im)\n\n # Create a blob to hold the input images\n blob = im_list_to_blob(processed_ims)\n\n return blob, im_scales\n\ndef _project_im_rois(im_rois, im_scale_factor):\n \"\"\"Project image RoIs into the rescaled training image.\"\"\"\n rois = im_rois * im_scale_factor\n return rois\n\ndef _get_bbox_regression_labels(bbox_target_data, num_classes):\n \"\"\"Bounding-box regression targets are stored in a compact form in the\n roidb.\n\n This function expands those targets into the 4-of-4*K representation used\n by the network (i.e. only one class has non-zero targets). The loss weights\n are similarly expanded.\n\n Returns:\n bbox_target_data (ndarray): N x 4K blob of regression targets\n bbox_inside_weights (ndarray): N x 4K blob of loss weights\n \"\"\"\n clss = bbox_target_data[:, 0]\n bbox_targets = np.zeros((clss.size, 4 * num_classes), dtype=np.float32)\n bbox_inside_weights = np.zeros(bbox_targets.shape, dtype=np.float32)\n inds = np.where(clss > 0)[0]\n for ind in inds:\n cls = clss[ind]\n start = 4 * cls\n end = start + 4\n bbox_targets[ind, start:end] = bbox_target_data[ind, 1:]\n bbox_inside_weights[ind, start:end] = cfg.TRAIN.BBOX_INSIDE_WEIGHTS\n return bbox_targets, bbox_inside_weights\n\ndef _vis_minibatch(im_blob, rois_blob, labels_blob, overlaps):\n \"\"\"Visualize a mini-batch for debugging.\"\"\"\n import matplotlib.pyplot as plt\n for i in xrange(rois_blob.shape[0]):\n rois = rois_blob[i, :]\n im_ind = rois[0]\n roi = rois[1:]\n im = im_blob[im_ind, :, :, :].transpose((1, 2, 0)).copy()\n im += cfg.PIXEL_MEANS\n im = im[:, :, (2, 1, 0)]\n im = im.astype(np.uint8)\n cls = labels_blob[i]\n plt.imshow(im)\n print 'class: ', cls, ' overlap: ', overlaps[i]\n plt.gca().add_patch(\n plt.Rectangle((roi[0], roi[1]), roi[2] - roi[0],\n roi[3] - roi[1], fill=False,\n edgecolor='r', linewidth=3)\n )\n plt.show()\n" }, { "path": "lib/roi_data_layer/roidb.py", "content": "# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\n\"\"\"Transform a roidb into a trainable roidb by adding a bunch of metadata.\"\"\"\n\nimport numpy as np\nfrom fast_rcnn.config import cfg\nfrom fast_rcnn.bbox_transform import bbox_transform\nfrom utils.cython_bbox import bbox_overlaps\nimport PIL\n\ndef prepare_roidb(imdb):\n \"\"\"Enrich the imdb's roidb by adding some derived quantities that\n are useful for training. This function precomputes the maximum\n overlap, taken over ground-truth boxes, between each ROI and\n each ground-truth box. The class with maximum overlap is also\n recorded.\n \"\"\"\n sizes = [PIL.Image.open(imdb.image_path_at(i)).size\n for i in xrange(imdb.num_images)]\n roidb = imdb.roidb\n for i in xrange(len(imdb.image_index)):\n roidb[i]['image'] = imdb.image_path_at(i)\n roidb[i]['width'] = sizes[i][0]\n roidb[i]['height'] = sizes[i][1]\n # need gt_overlaps as a dense array for argmax\n gt_overlaps = roidb[i]['gt_overlaps'].toarray()\n # max overlap with gt over classes (columns)\n max_overlaps = gt_overlaps.max(axis=1)\n # gt class that had the max overlap\n max_classes = gt_overlaps.argmax(axis=1)\n roidb[i]['max_classes'] = max_classes\n roidb[i]['max_overlaps'] = max_overlaps\n # sanity checks\n # max overlap of 0 => class should be zero (background)\n zero_inds = np.where(max_overlaps == 0)[0]\n assert all(max_classes[zero_inds] == 0)\n # max overlap > 0 => class should not be zero (must be a fg class)\n nonzero_inds = np.where(max_overlaps > 0)[0]\n assert all(max_classes[nonzero_inds] != 0)\n\ndef add_bbox_regression_targets(roidb):\n \"\"\"Add information needed to train bounding-box regressors.\"\"\"\n assert len(roidb) > 0\n assert 'max_classes' in roidb[0], 'Did you call prepare_roidb first?'\n\n num_images = len(roidb)\n # Infer number of classes from the number of columns in gt_overlaps\n num_classes = roidb[0]['gt_overlaps'].shape[1]\n for im_i in xrange(num_images):\n rois = roidb[im_i]['boxes']\n max_overlaps = roidb[im_i]['max_overlaps']\n max_classes = roidb[im_i]['max_classes']\n roidb[im_i]['bbox_targets'] = \\\n _compute_targets(rois, max_overlaps, max_classes)\n\n if cfg.TRAIN.BBOX_NORMALIZE_TARGETS_PRECOMPUTED:\n # Use fixed / precomputed \"means\" and \"stds\" instead of empirical values\n means = np.tile(\n np.array(cfg.TRAIN.BBOX_NORMALIZE_MEANS), (num_classes, 1))\n stds = np.tile(\n np.array(cfg.TRAIN.BBOX_NORMALIZE_STDS), (num_classes, 1))\n else:\n # Compute values needed for means and stds\n # var(x) = E(x^2) - E(x)^2\n class_counts = np.zeros((num_classes, 1)) + cfg.EPS\n sums = np.zeros((num_classes, 4))\n squared_sums = np.zeros((num_classes, 4))\n for im_i in xrange(num_images):\n targets = roidb[im_i]['bbox_targets']\n for cls in xrange(1, num_classes):\n cls_inds = np.where(targets[:, 0] == cls)[0]\n if cls_inds.size > 0:\n class_counts[cls] += cls_inds.size\n sums[cls, :] += targets[cls_inds, 1:].sum(axis=0)\n squared_sums[cls, :] += \\\n (targets[cls_inds, 1:] ** 2).sum(axis=0)\n\n means = sums / class_counts\n stds = np.sqrt(squared_sums / class_counts - means ** 2)\n\n print 'bbox target means:'\n print means\n print means[1:, :].mean(axis=0) # ignore bg class\n print 'bbox target stdevs:'\n print stds\n print stds[1:, :].mean(axis=0) # ignore bg class\n\n # Normalize targets\n if cfg.TRAIN.BBOX_NORMALIZE_TARGETS:\n print \"Normalizing targets\"\n for im_i in xrange(num_images):\n targets = roidb[im_i]['bbox_targets']\n for cls in xrange(1, num_classes):\n cls_inds = np.where(targets[:, 0] == cls)[0]\n roidb[im_i]['bbox_targets'][cls_inds, 1:] -= means[cls, :]\n roidb[im_i]['bbox_targets'][cls_inds, 1:] /= stds[cls, :]\n else:\n print \"NOT normalizing targets\"\n\n # These values will be needed for making predictions\n # (the predicts will need to be unnormalized and uncentered)\n return means.ravel(), stds.ravel()\n\ndef _compute_targets(rois, overlaps, labels):\n \"\"\"Compute bounding-box regression targets for an image.\"\"\"\n # Indices of ground-truth ROIs\n gt_inds = np.where(overlaps == 1)[0]\n if len(gt_inds) == 0:\n # Bail if the image has no ground-truth ROIs\n return np.zeros((rois.shape[0], 5), dtype=np.float32)\n # Indices of examples for which we try to make predictions\n ex_inds = np.where(overlaps >= cfg.TRAIN.BBOX_THRESH)[0]\n\n # Get IoU overlap between each ex ROI and gt ROI\n ex_gt_overlaps = bbox_overlaps(\n np.ascontiguousarray(rois[ex_inds, :], dtype=np.float),\n np.ascontiguousarray(rois[gt_inds, :], dtype=np.float))\n\n # Find which gt ROI each ex ROI has max overlap with:\n # this will be the ex ROI's gt target\n gt_assignment = ex_gt_overlaps.argmax(axis=1)\n gt_rois = rois[gt_inds[gt_assignment], :]\n ex_rois = rois[ex_inds, :]\n\n targets = np.zeros((rois.shape[0], 5), dtype=np.float32)\n targets[ex_inds, 0] = labels[ex_inds]\n targets[ex_inds, 1:] = bbox_transform(ex_rois, gt_rois)\n return targets\n" }, { "path": "lib/rpn/README.md", "content": "### `rpn` module overview\n\n##### `generate_anchors.py`\n\nGenerates a regular grid of multi-scale, multi-aspect anchor boxes.\n\n##### `proposal_layer.py`\n\nConverts RPN outputs (per-anchor scores and bbox regression estimates) into object proposals.\n\n##### `anchor_target_layer.py` \n\nGenerates training targets/labels for each anchor. Classification labels are 1 (object), 0 (not object) or -1 (ignore).\nBbox regression targets are specified when the classification label is > 0.\n\n##### `proposal_target_layer.py`\n\nGenerates training targets/labels for each object proposal: classification labels 0 - K (bg or object class 1, ... , K)\nand bbox regression targets in that case that the label is > 0.\n\n##### `generate.py`\n\nGenerate object detection proposals from an imdb using an RPN.\n" }, { "path": "lib/rpn/__init__.py", "content": "# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick and Sean Bell\n# --------------------------------------------------------\n" }, { "path": "lib/rpn/anchor_target_layer.py", "content": "# --------------------------------------------------------\n# Faster R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick and Sean Bell\n# --------------------------------------------------------\n\nimport os\nimport caffe\nimport yaml\nfrom fast_rcnn.config import cfg\nimport numpy as np\nimport numpy.random as npr\nfrom generate_anchors import generate_anchors\nfrom utils.cython_bbox import bbox_overlaps\nfrom fast_rcnn.bbox_transform import bbox_transform\n\nDEBUG = False\n\nclass AnchorTargetLayer(caffe.Layer):\n \"\"\"\n Assign anchors to ground-truth targets. Produces anchor classification\n labels and bounding-box regression targets.\n \"\"\"\n\n def setup(self, bottom, top):\n layer_params = yaml.load(self.param_str_)\n anchor_scales = layer_params.get('scales', (8, 16, 32))\n self._anchors = generate_anchors(scales=np.array(anchor_scales))\n self._num_anchors = self._anchors.shape[0]\n self._feat_stride = layer_params['feat_stride']\n\n if DEBUG:\n print 'anchors:'\n print self._anchors\n print 'anchor shapes:'\n print np.hstack((\n self._anchors[:, 2::4] - self._anchors[:, 0::4],\n self._anchors[:, 3::4] - self._anchors[:, 1::4],\n ))\n self._counts = cfg.EPS\n self._sums = np.zeros((1, 4))\n self._squared_sums = np.zeros((1, 4))\n self._fg_sum = 0\n self._bg_sum = 0\n self._count = 0\n\n # allow boxes to sit over the edge by a small amount\n self._allowed_border = layer_params.get('allowed_border', 0)\n\n height, width = bottom[0].data.shape[-2:]\n if DEBUG:\n print 'AnchorTargetLayer: height', height, 'width', width\n\n A = self._num_anchors\n # labels\n top[0].reshape(1, 1, A * height, width)\n # bbox_targets\n top[1].reshape(1, A * 4, height, width)\n # bbox_inside_weights\n top[2].reshape(1, A * 4, height, width)\n # bbox_outside_weights\n top[3].reshape(1, A * 4, height, width)\n\n def forward(self, bottom, top):\n # Algorithm:\n #\n # for each (H, W) location i\n # generate 9 anchor boxes centered on cell i\n # apply predicted bbox deltas at cell i to each of the 9 anchors\n # filter out-of-image anchors\n # measure GT overlap\n\n assert bottom[0].data.shape[0] == 1, \\\n 'Only single item batches are supported'\n\n # map of shape (..., H, W)\n height, width = bottom[0].data.shape[-2:]\n # GT boxes (x1, y1, x2, y2, label)\n gt_boxes = bottom[1].data\n # im_info\n im_info = bottom[2].data[0, :]\n\n if DEBUG:\n print ''\n print 'im_size: ({}, {})'.format(im_info[0], im_info[1])\n print 'scale: {}'.format(im_info[2])\n print 'height, width: ({}, {})'.format(height, width)\n print 'rpn: gt_boxes.shape', gt_boxes.shape\n print 'rpn: gt_boxes', gt_boxes\n\n # 1. Generate proposals from bbox deltas and shifted anchors\n shift_x = np.arange(0, width) * self._feat_stride\n shift_y = np.arange(0, height) * self._feat_stride\n shift_x, shift_y = np.meshgrid(shift_x, shift_y)\n shifts = np.vstack((shift_x.ravel(), shift_y.ravel(),\n shift_x.ravel(), shift_y.ravel())).transpose()\n # add A anchors (1, A, 4) to\n # cell K shifts (K, 1, 4) to get\n # shift anchors (K, A, 4)\n # reshape to (K*A, 4) shifted anchors\n A = self._num_anchors\n K = shifts.shape[0]\n all_anchors = (self._anchors.reshape((1, A, 4)) +\n shifts.reshape((1, K, 4)).transpose((1, 0, 2)))\n all_anchors = all_anchors.reshape((K * A, 4))\n total_anchors = int(K * A)\n\n # only keep anchors inside the image\n inds_inside = np.where(\n (all_anchors[:, 0] >= -self._allowed_border) &\n (all_anchors[:, 1] >= -self._allowed_border) &\n (all_anchors[:, 2] < im_info[1] + self._allowed_border) & # width\n (all_anchors[:, 3] < im_info[0] + self._allowed_border) # height\n )[0]\n\n if DEBUG:\n print 'total_anchors', total_anchors\n print 'inds_inside', len(inds_inside)\n\n # keep only inside anchors\n anchors = all_anchors[inds_inside, :]\n if DEBUG:\n print 'anchors.shape', anchors.shape\n\n # label: 1 is positive, 0 is negative, -1 is dont care\n labels = np.empty((len(inds_inside), ), dtype=np.float32)\n labels.fill(-1)\n\n # overlaps between the anchors and the gt boxes\n # overlaps (ex, gt)\n overlaps = bbox_overlaps(\n np.ascontiguousarray(anchors, dtype=np.float),\n np.ascontiguousarray(gt_boxes, dtype=np.float))\n argmax_overlaps = overlaps.argmax(axis=1)\n max_overlaps = overlaps[np.arange(len(inds_inside)), argmax_overlaps]\n gt_argmax_overlaps = overlaps.argmax(axis=0)\n gt_max_overlaps = overlaps[gt_argmax_overlaps,\n np.arange(overlaps.shape[1])]\n gt_argmax_overlaps = np.where(overlaps == gt_max_overlaps)[0]\n\n if not cfg.TRAIN.RPN_CLOBBER_POSITIVES:\n # assign bg labels first so that positive labels can clobber them\n labels[max_overlaps < cfg.TRAIN.RPN_NEGATIVE_OVERLAP] = 0\n\n # fg label: for each gt, anchor with highest overlap\n labels[gt_argmax_overlaps] = 1\n\n # fg label: above threshold IOU\n labels[max_overlaps >= cfg.TRAIN.RPN_POSITIVE_OVERLAP] = 1\n\n if cfg.TRAIN.RPN_CLOBBER_POSITIVES:\n # assign bg labels last so that negative labels can clobber positives\n labels[max_overlaps < cfg.TRAIN.RPN_NEGATIVE_OVERLAP] = 0\n\n # subsample positive labels if we have too many\n num_fg = int(cfg.TRAIN.RPN_FG_FRACTION * cfg.TRAIN.RPN_BATCHSIZE)\n fg_inds = np.where(labels == 1)[0]\n if len(fg_inds) > num_fg:\n disable_inds = npr.choice(\n fg_inds, size=(len(fg_inds) - num_fg), replace=False)\n labels[disable_inds] = -1\n\n # subsample negative labels if we have too many\n num_bg = cfg.TRAIN.RPN_BATCHSIZE - np.sum(labels == 1)\n bg_inds = np.where(labels == 0)[0]\n if len(bg_inds) > num_bg:\n disable_inds = npr.choice(\n bg_inds, size=(len(bg_inds) - num_bg), replace=False)\n labels[disable_inds] = -1\n #print \"was %s inds, disabling %s, now %s inds\" % (\n #len(bg_inds), len(disable_inds), np.sum(labels == 0))\n\n bbox_targets = np.zeros((len(inds_inside), 4), dtype=np.float32)\n bbox_targets = _compute_targets(anchors, gt_boxes[argmax_overlaps, :])\n\n bbox_inside_weights = np.zeros((len(inds_inside), 4), dtype=np.float32)\n bbox_inside_weights[labels == 1, :] = np.array(cfg.TRAIN.RPN_BBOX_INSIDE_WEIGHTS)\n\n bbox_outside_weights = np.zeros((len(inds_inside), 4), dtype=np.float32)\n if cfg.TRAIN.RPN_POSITIVE_WEIGHT < 0:\n # uniform weighting of examples (given non-uniform sampling)\n num_examples = np.sum(labels >= 0)\n positive_weights = np.ones((1, 4)) * 1.0 / num_examples\n negative_weights = np.ones((1, 4)) * 1.0 / num_examples\n else:\n assert ((cfg.TRAIN.RPN_POSITIVE_WEIGHT > 0) &\n (cfg.TRAIN.RPN_POSITIVE_WEIGHT < 1))\n positive_weights = (cfg.TRAIN.RPN_POSITIVE_WEIGHT /\n np.sum(labels == 1))\n negative_weights = ((1.0 - cfg.TRAIN.RPN_POSITIVE_WEIGHT) /\n np.sum(labels == 0))\n bbox_outside_weights[labels == 1, :] = positive_weights\n bbox_outside_weights[labels == 0, :] = negative_weights\n\n if DEBUG:\n self._sums += bbox_targets[labels == 1, :].sum(axis=0)\n self._squared_sums += (bbox_targets[labels == 1, :] ** 2).sum(axis=0)\n self._counts += np.sum(labels == 1)\n means = self._sums / self._counts\n stds = np.sqrt(self._squared_sums / self._counts - means ** 2)\n print 'means:'\n print means\n print 'stdevs:'\n print stds\n\n # map up to original set of anchors\n labels = _unmap(labels, total_anchors, inds_inside, fill=-1)\n bbox_targets = _unmap(bbox_targets, total_anchors, inds_inside, fill=0)\n bbox_inside_weights = _unmap(bbox_inside_weights, total_anchors, inds_inside, fill=0)\n bbox_outside_weights = _unmap(bbox_outside_weights, total_anchors, inds_inside, fill=0)\n\n if DEBUG:\n print 'rpn: max max_overlap', np.max(max_overlaps)\n print 'rpn: num_positive', np.sum(labels == 1)\n print 'rpn: num_negative', np.sum(labels == 0)\n self._fg_sum += np.sum(labels == 1)\n self._bg_sum += np.sum(labels == 0)\n self._count += 1\n print 'rpn: num_positive avg', self._fg_sum / self._count\n print 'rpn: num_negative avg', self._bg_sum / self._count\n\n # labels\n labels = labels.reshape((1, height, width, A)).transpose(0, 3, 1, 2)\n labels = labels.reshape((1, 1, A * height, width))\n top[0].reshape(*labels.shape)\n top[0].data[...] = labels\n\n # bbox_targets\n bbox_targets = bbox_targets \\\n .reshape((1, height, width, A * 4)).transpose(0, 3, 1, 2)\n top[1].reshape(*bbox_targets.shape)\n top[1].data[...] = bbox_targets\n\n # bbox_inside_weights\n bbox_inside_weights = bbox_inside_weights \\\n .reshape((1, height, width, A * 4)).transpose(0, 3, 1, 2)\n assert bbox_inside_weights.shape[2] == height\n assert bbox_inside_weights.shape[3] == width\n top[2].reshape(*bbox_inside_weights.shape)\n top[2].data[...] = bbox_inside_weights\n\n # bbox_outside_weights\n bbox_outside_weights = bbox_outside_weights \\\n .reshape((1, height, width, A * 4)).transpose(0, 3, 1, 2)\n assert bbox_outside_weights.shape[2] == height\n assert bbox_outside_weights.shape[3] == width\n top[3].reshape(*bbox_outside_weights.shape)\n top[3].data[...] = bbox_outside_weights\n\n def backward(self, top, propagate_down, bottom):\n \"\"\"This layer does not propagate gradients.\"\"\"\n pass\n\n def reshape(self, bottom, top):\n \"\"\"Reshaping happens during the call to forward.\"\"\"\n pass\n\n\ndef _unmap(data, count, inds, fill=0):\n \"\"\" Unmap a subset of item (data) back to the original set of items (of\n size count) \"\"\"\n if len(data.shape) == 1:\n ret = np.empty((count, ), dtype=np.float32)\n ret.fill(fill)\n ret[inds] = data\n else:\n ret = np.empty((count, ) + data.shape[1:], dtype=np.float32)\n ret.fill(fill)\n ret[inds, :] = data\n return ret\n\n\ndef _compute_targets(ex_rois, gt_rois):\n \"\"\"Compute bounding-box regression targets for an image.\"\"\"\n\n assert ex_rois.shape[0] == gt_rois.shape[0]\n assert ex_rois.shape[1] == 4\n assert gt_rois.shape[1] == 5\n\n return bbox_transform(ex_rois, gt_rois[:, :4]).astype(np.float32, copy=False)\n" }, { "path": "lib/rpn/generate.py", "content": "# --------------------------------------------------------\n# Faster R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\nfrom fast_rcnn.config import cfg\nfrom utils.blob import im_list_to_blob\nfrom utils.timer import Timer\nimport numpy as np\nimport cv2\n\ndef _vis_proposals(im, dets, thresh=0.5):\n \"\"\"Draw detected bounding boxes.\"\"\"\n inds = np.where(dets[:, -1] >= thresh)[0]\n if len(inds) == 0:\n return\n\n class_name = 'obj'\n im = im[:, :, (2, 1, 0)]\n fig, ax = plt.subplots(figsize=(12, 12))\n ax.imshow(im, aspect='equal')\n for i in inds:\n bbox = dets[i, :4]\n score = dets[i, -1]\n\n ax.add_patch(\n plt.Rectangle((bbox[0], bbox[1]),\n bbox[2] - bbox[0],\n bbox[3] - bbox[1], fill=False,\n edgecolor='red', linewidth=3.5)\n )\n ax.text(bbox[0], bbox[1] - 2,\n '{:s} {:.3f}'.format(class_name, score),\n bbox=dict(facecolor='blue', alpha=0.5),\n fontsize=14, color='white')\n\n ax.set_title(('{} detections with '\n 'p({} | box) >= {:.1f}').format(class_name, class_name,\n thresh),\n fontsize=14)\n plt.axis('off')\n plt.tight_layout()\n plt.draw()\n\ndef _get_image_blob(im):\n \"\"\"Converts an image into a network input.\n\n Arguments:\n im (ndarray): a color image in BGR order\n\n Returns:\n blob (ndarray): a data blob holding an image pyramid\n im_scale_factors (list): list of image scales (relative to im) used\n in the image pyramid\n \"\"\"\n im_orig = im.astype(np.float32, copy=True)\n im_orig -= cfg.PIXEL_MEANS\n\n im_shape = im_orig.shape\n im_size_min = np.min(im_shape[0:2])\n im_size_max = np.max(im_shape[0:2])\n\n processed_ims = []\n\n assert len(cfg.TEST.SCALES) == 1\n target_size = cfg.TEST.SCALES[0]\n\n im_scale = float(target_size) / float(im_size_min)\n # Prevent the biggest axis from being more than MAX_SIZE\n if np.round(im_scale * im_size_max) > cfg.TEST.MAX_SIZE:\n im_scale = float(cfg.TEST.MAX_SIZE) / float(im_size_max)\n im = cv2.resize(im_orig, None, None, fx=im_scale, fy=im_scale,\n interpolation=cv2.INTER_LINEAR)\n im_info = np.hstack((im.shape[:2], im_scale))[np.newaxis, :]\n processed_ims.append(im)\n\n # Create a blob to hold the input images\n blob = im_list_to_blob(processed_ims)\n\n return blob, im_info\n\ndef im_proposals(net, im):\n \"\"\"Generate RPN proposals on a single image.\"\"\"\n blobs = {}\n blobs['data'], blobs['im_info'] = _get_image_blob(im)\n net.blobs['data'].reshape(*(blobs['data'].shape))\n net.blobs['im_info'].reshape(*(blobs['im_info'].shape))\n blobs_out = net.forward(\n data=blobs['data'].astype(np.float32, copy=False),\n im_info=blobs['im_info'].astype(np.float32, copy=False))\n\n scale = blobs['im_info'][0, 2]\n boxes = blobs_out['rois'][:, 1:].copy() / scale\n scores = blobs_out['scores'].copy()\n return boxes, scores\n\ndef imdb_proposals(net, imdb):\n \"\"\"Generate RPN proposals on all images in an imdb.\"\"\"\n\n _t = Timer()\n imdb_boxes = [[] for _ in xrange(imdb.num_images)]\n for i in xrange(imdb.num_images):\n im = cv2.imread(imdb.image_path_at(i))\n _t.tic()\n imdb_boxes[i], scores = im_proposals(net, im)\n _t.toc()\n print 'im_proposals: {:d}/{:d} {:.3f}s' \\\n .format(i + 1, imdb.num_images, _t.average_time)\n if 0:\n dets = np.hstack((imdb_boxes[i], scores))\n # from IPython import embed; embed()\n _vis_proposals(im, dets[:3, :], thresh=0.9)\n plt.show()\n\n return imdb_boxes\n" }, { "path": "lib/rpn/generate_anchors.py", "content": "# --------------------------------------------------------\n# Faster R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick and Sean Bell\n# --------------------------------------------------------\n\nimport numpy as np\n\n# Verify that we compute the same anchors as Shaoqing's matlab implementation:\n#\n# >> load output/rpn_cachedir/faster_rcnn_VOC2007_ZF_stage1_rpn/anchors.mat\n# >> anchors\n#\n# anchors =\n#\n# -83 -39 100 56\n# -175 -87 192 104\n# -359 -183 376 200\n# -55 -55 72 72\n# -119 -119 136 136\n# -247 -247 264 264\n# -35 -79 52 96\n# -79 -167 96 184\n# -167 -343 184 360\n\n#array([[ -83., -39., 100., 56.],\n# [-175., -87., 192., 104.],\n# [-359., -183., 376., 200.],\n# [ -55., -55., 72., 72.],\n# [-119., -119., 136., 136.],\n# [-247., -247., 264., 264.],\n# [ -35., -79., 52., 96.],\n# [ -79., -167., 96., 184.],\n# [-167., -343., 184., 360.]])\n\ndef generate_anchors(base_size=16, ratios=[0.5, 1, 2],\n scales=2**np.arange(3, 6)):\n \"\"\"\n Generate anchor (reference) windows by enumerating aspect ratios X\n scales wrt a reference (0, 0, 15, 15) window.\n \"\"\"\n\n base_anchor = np.array([1, 1, base_size, base_size]) - 1\n ratio_anchors = _ratio_enum(base_anchor, ratios)\n anchors = np.vstack([_scale_enum(ratio_anchors[i, :], scales)\n for i in xrange(ratio_anchors.shape[0])])\n return anchors\n\ndef _whctrs(anchor):\n \"\"\"\n Return width, height, x center, and y center for an anchor (window).\n \"\"\"\n\n w = anchor[2] - anchor[0] + 1\n h = anchor[3] - anchor[1] + 1\n x_ctr = anchor[0] + 0.5 * (w - 1)\n y_ctr = anchor[1] + 0.5 * (h - 1)\n return w, h, x_ctr, y_ctr\n\ndef _mkanchors(ws, hs, x_ctr, y_ctr):\n \"\"\"\n Given a vector of widths (ws) and heights (hs) around a center\n (x_ctr, y_ctr), output a set of anchors (windows).\n \"\"\"\n\n ws = ws[:, np.newaxis]\n hs = hs[:, np.newaxis]\n anchors = np.hstack((x_ctr - 0.5 * (ws - 1),\n y_ctr - 0.5 * (hs - 1),\n x_ctr + 0.5 * (ws - 1),\n y_ctr + 0.5 * (hs - 1)))\n return anchors\n\ndef _ratio_enum(anchor, ratios):\n \"\"\"\n Enumerate a set of anchors for each aspect ratio wrt an anchor.\n \"\"\"\n\n w, h, x_ctr, y_ctr = _whctrs(anchor)\n size = w * h\n size_ratios = size / ratios\n ws = np.round(np.sqrt(size_ratios))\n hs = np.round(ws * ratios)\n anchors = _mkanchors(ws, hs, x_ctr, y_ctr)\n return anchors\n\ndef _scale_enum(anchor, scales):\n \"\"\"\n Enumerate a set of anchors for each scale wrt an anchor.\n \"\"\"\n\n w, h, x_ctr, y_ctr = _whctrs(anchor)\n ws = w * scales\n hs = h * scales\n anchors = _mkanchors(ws, hs, x_ctr, y_ctr)\n return anchors\n\nif __name__ == '__main__':\n import time\n t = time.time()\n a = generate_anchors()\n print time.time() - t\n print a\n from IPython import embed; embed()\n" }, { "path": "lib/rpn/proposal_layer.py", "content": "# --------------------------------------------------------\n# Faster R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick and Sean Bell\n# --------------------------------------------------------\n\nimport caffe\nimport numpy as np\nimport yaml\nfrom fast_rcnn.config import cfg\nfrom generate_anchors import generate_anchors\nfrom fast_rcnn.bbox_transform import bbox_transform_inv, clip_boxes\nfrom fast_rcnn.nms_wrapper import nms\n\nDEBUG = False\n\nclass ProposalLayer(caffe.Layer):\n \"\"\"\n Outputs object detection proposals by applying estimated bounding-box\n transformations to a set of regular boxes (called \"anchors\").\n \"\"\"\n\n def setup(self, bottom, top):\n # parse the layer parameter string, which must be valid YAML\n layer_params = yaml.load(self.param_str_)\n\n self._feat_stride = layer_params['feat_stride']\n anchor_scales = layer_params.get('scales', (8, 16, 32))\n self._anchors = generate_anchors(scales=np.array(anchor_scales))\n self._num_anchors = self._anchors.shape[0]\n\n if DEBUG:\n print 'feat_stride: {}'.format(self._feat_stride)\n print 'anchors:'\n print self._anchors\n\n # rois blob: holds R regions of interest, each is a 5-tuple\n # (n, x1, y1, x2, y2) specifying an image batch index n and a\n # rectangle (x1, y1, x2, y2)\n top[0].reshape(1, 5)\n\n # scores blob: holds scores for R regions of interest\n if len(top) > 1:\n top[1].reshape(1, 1, 1, 1)\n\n def forward(self, bottom, top):\n # Algorithm:\n #\n # for each (H, W) location i\n # generate A anchor boxes centered on cell i\n # apply predicted bbox deltas at cell i to each of the A anchors\n # clip predicted boxes to image\n # remove predicted boxes with either height or width < threshold\n # sort all (proposal, score) pairs by score from highest to lowest\n # take top pre_nms_topN proposals before NMS\n # apply NMS with threshold 0.7 to remaining proposals\n # take after_nms_topN proposals after NMS\n # return the top proposals (-> RoIs top, scores top)\n\n assert bottom[0].data.shape[0] == 1, \\\n 'Only single item batches are supported'\n\n cfg_key = str(self.phase) # either 'TRAIN' or 'TEST'\n pre_nms_topN = cfg[cfg_key].RPN_PRE_NMS_TOP_N\n post_nms_topN = cfg[cfg_key].RPN_POST_NMS_TOP_N\n nms_thresh = cfg[cfg_key].RPN_NMS_THRESH\n min_size = cfg[cfg_key].RPN_MIN_SIZE\n\n # the first set of _num_anchors channels are bg probs\n # the second set are the fg probs, which we want\n scores = bottom[0].data[:, self._num_anchors:, :, :]\n bbox_deltas = bottom[1].data\n im_info = bottom[2].data[0, :]\n\n if DEBUG:\n print 'im_size: ({}, {})'.format(im_info[0], im_info[1])\n print 'scale: {}'.format(im_info[2])\n\n # 1. Generate proposals from bbox deltas and shifted anchors\n height, width = scores.shape[-2:]\n\n if DEBUG:\n print 'score map size: {}'.format(scores.shape)\n\n # Enumerate all shifts\n shift_x = np.arange(0, width) * self._feat_stride\n shift_y = np.arange(0, height) * self._feat_stride\n shift_x, shift_y = np.meshgrid(shift_x, shift_y)\n shifts = np.vstack((shift_x.ravel(), shift_y.ravel(),\n shift_x.ravel(), shift_y.ravel())).transpose()\n\n # Enumerate all shifted anchors:\n #\n # add A anchors (1, A, 4) to\n # cell K shifts (K, 1, 4) to get\n # shift anchors (K, A, 4)\n # reshape to (K*A, 4) shifted anchors\n A = self._num_anchors\n K = shifts.shape[0]\n anchors = self._anchors.reshape((1, A, 4)) + \\\n shifts.reshape((1, K, 4)).transpose((1, 0, 2))\n anchors = anchors.reshape((K * A, 4))\n\n # Transpose and reshape predicted bbox transformations to get them\n # into the same order as the anchors:\n #\n # bbox deltas will be (1, 4 * A, H, W) format\n # transpose to (1, H, W, 4 * A)\n # reshape to (1 * H * W * A, 4) where rows are ordered by (h, w, a)\n # in slowest to fastest order\n bbox_deltas = bbox_deltas.transpose((0, 2, 3, 1)).reshape((-1, 4))\n\n # Same story for the scores:\n #\n # scores are (1, A, H, W) format\n # transpose to (1, H, W, A)\n # reshape to (1 * H * W * A, 1) where rows are ordered by (h, w, a)\n scores = scores.transpose((0, 2, 3, 1)).reshape((-1, 1))\n\n # Convert anchors into proposals via bbox transformations\n proposals = bbox_transform_inv(anchors, bbox_deltas)\n\n # 2. clip predicted boxes to image\n proposals = clip_boxes(proposals, im_info[:2])\n\n # 3. remove predicted boxes with either height or width < threshold\n # (NOTE: convert min_size to input image scale stored in im_info[2])\n keep = _filter_boxes(proposals, min_size * im_info[2])\n proposals = proposals[keep, :]\n scores = scores[keep]\n\n # 4. sort all (proposal, score) pairs by score from highest to lowest\n # 5. take top pre_nms_topN (e.g. 6000)\n order = scores.ravel().argsort()[::-1]\n if pre_nms_topN > 0:\n order = order[:pre_nms_topN]\n proposals = proposals[order, :]\n scores = scores[order]\n\n # 6. apply nms (e.g. threshold = 0.7)\n # 7. take after_nms_topN (e.g. 300)\n # 8. return the top proposals (-> RoIs top)\n keep = nms(np.hstack((proposals, scores)), nms_thresh)\n if post_nms_topN > 0:\n keep = keep[:post_nms_topN]\n proposals = proposals[keep, :]\n scores = scores[keep]\n\n # Output rois blob\n # Our RPN implementation only supports a single input image, so all\n # batch inds are 0\n batch_inds = np.zeros((proposals.shape[0], 1), dtype=np.float32)\n blob = np.hstack((batch_inds, proposals.astype(np.float32, copy=False)))\n top[0].reshape(*(blob.shape))\n top[0].data[...] = blob\n\n # [Optional] output scores blob\n if len(top) > 1:\n top[1].reshape(*(scores.shape))\n top[1].data[...] = scores\n\n def backward(self, top, propagate_down, bottom):\n \"\"\"This layer does not propagate gradients.\"\"\"\n pass\n\n def reshape(self, bottom, top):\n \"\"\"Reshaping happens during the call to forward.\"\"\"\n pass\n\ndef _filter_boxes(boxes, min_size):\n \"\"\"Remove all boxes with any side smaller than min_size.\"\"\"\n ws = boxes[:, 2] - boxes[:, 0] + 1\n hs = boxes[:, 3] - boxes[:, 1] + 1\n keep = np.where((ws >= min_size) & (hs >= min_size))[0]\n return keep\n" }, { "path": "lib/rpn/proposal_target_layer.py", "content": "# --------------------------------------------------------\n# Faster R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick and Sean Bell\n# --------------------------------------------------------\n\nimport caffe\nimport yaml\nimport numpy as np\nimport numpy.random as npr\nfrom fast_rcnn.config import cfg\nfrom fast_rcnn.bbox_transform import bbox_transform\nfrom utils.cython_bbox import bbox_overlaps\n\nDEBUG = False\n\nclass ProposalTargetLayer(caffe.Layer):\n \"\"\"\n Assign object detection proposals to ground-truth targets. Produces proposal\n classification labels and bounding-box regression targets.\n \"\"\"\n\n def setup(self, bottom, top):\n layer_params = yaml.load(self.param_str_)\n self._num_classes = layer_params['num_classes']\n\n # sampled rois (0, x1, y1, x2, y2)\n top[0].reshape(1, 5)\n # labels\n top[1].reshape(1, 1)\n # bbox_targets\n top[2].reshape(1, self._num_classes * 4)\n # bbox_inside_weights\n top[3].reshape(1, self._num_classes * 4)\n # bbox_outside_weights\n top[4].reshape(1, self._num_classes * 4)\n\n def forward(self, bottom, top):\n # Proposal ROIs (0, x1, y1, x2, y2) coming from RPN\n # (i.e., rpn.proposal_layer.ProposalLayer), or any other source\n all_rois = bottom[0].data\n # GT boxes (x1, y1, x2, y2, label)\n # TODO(rbg): it's annoying that sometimes I have extra info before\n # and other times after box coordinates -- normalize to one format\n gt_boxes = bottom[1].data\n\n # Include ground-truth boxes in the set of candidate rois\n zeros = np.zeros((gt_boxes.shape[0], 1), dtype=gt_boxes.dtype)\n all_rois = np.vstack(\n (all_rois, np.hstack((zeros, gt_boxes[:, :-1])))\n )\n\n # Sanity check: single batch only\n assert np.all(all_rois[:, 0] == 0), \\\n 'Only single item batches are supported'\n\n num_images = 1\n rois_per_image = np.inf if cfg.TRAIN.USE_OHEM else (cfg.TRAIN.BATCH_SIZE / num_images)\n fg_rois_per_image = np.round(cfg.TRAIN.FG_FRACTION * rois_per_image)\n\n # Sample rois with classification labels and bounding box regression\n # targets\n labels, rois, bbox_targets, bbox_inside_weights = _sample_rois(\n all_rois, gt_boxes, fg_rois_per_image,\n rois_per_image, self._num_classes)\n\n if DEBUG:\n print 'num fg: {}'.format((labels > 0).sum())\n print 'num bg: {}'.format((labels == 0).sum())\n self._count += 1\n self._fg_num += (labels > 0).sum()\n self._bg_num += (labels == 0).sum()\n print 'num fg avg: {}'.format(self._fg_num / self._count)\n print 'num bg avg: {}'.format(self._bg_num / self._count)\n print 'ratio: {:.3f}'.format(float(self._fg_num) / float(self._bg_num))\n\n # sampled rois\n top[0].reshape(*rois.shape)\n top[0].data[...] = rois\n\n # classification labels\n top[1].reshape(*labels.shape)\n top[1].data[...] = labels\n\n # bbox_targets\n top[2].reshape(*bbox_targets.shape)\n top[2].data[...] = bbox_targets\n\n # bbox_inside_weights\n top[3].reshape(*bbox_inside_weights.shape)\n top[3].data[...] = bbox_inside_weights\n\n # bbox_outside_weights\n top[4].reshape(*bbox_inside_weights.shape)\n top[4].data[...] = np.array(bbox_inside_weights > 0).astype(np.float32)\n\n def backward(self, top, propagate_down, bottom):\n \"\"\"This layer does not propagate gradients.\"\"\"\n pass\n\n def reshape(self, bottom, top):\n \"\"\"Reshaping happens during the call to forward.\"\"\"\n pass\n\n\ndef _get_bbox_regression_labels(bbox_target_data, num_classes):\n \"\"\"Bounding-box regression targets (bbox_target_data) are stored in a\n compact form N x (class, tx, ty, tw, th)\n\n This function expands those targets into the 4-of-4*K representation used\n by the network (i.e. only one class has non-zero targets).\n\n Returns:\n bbox_target (ndarray): N x 4K blob of regression targets\n bbox_inside_weights (ndarray): N x 4K blob of loss weights\n \"\"\"\n\n clss = bbox_target_data[:, 0]\n bbox_targets = np.zeros((clss.size, 4 * num_classes), dtype=np.float32)\n bbox_inside_weights = np.zeros(bbox_targets.shape, dtype=np.float32)\n inds = np.where(clss > 0)[0]\n for ind in inds:\n cls = clss[ind]\n start = 4 * cls\n end = start + 4\n bbox_targets[ind, start:end] = bbox_target_data[ind, 1:]\n bbox_inside_weights[ind, start:end] = cfg.TRAIN.BBOX_INSIDE_WEIGHTS\n return bbox_targets, bbox_inside_weights\n\n\ndef _compute_targets(ex_rois, gt_rois, labels):\n \"\"\"Compute bounding-box regression targets for an image.\"\"\"\n\n assert ex_rois.shape[0] == gt_rois.shape[0]\n assert ex_rois.shape[1] == 4\n assert gt_rois.shape[1] == 4\n\n targets = bbox_transform(ex_rois, gt_rois)\n if cfg.TRAIN.BBOX_NORMALIZE_TARGETS_PRECOMPUTED:\n # Optionally normalize targets by a precomputed mean and stdev\n targets = ((targets - np.array(cfg.TRAIN.BBOX_NORMALIZE_MEANS))\n / np.array(cfg.TRAIN.BBOX_NORMALIZE_STDS))\n return np.hstack(\n (labels[:, np.newaxis], targets)).astype(np.float32, copy=False)\n\ndef _sample_rois(all_rois, gt_boxes, fg_rois_per_image, rois_per_image, num_classes):\n \"\"\"Generate a random sample of RoIs comprising foreground and background\n examples.\n \"\"\"\n # overlaps: (rois x gt_boxes)\n overlaps = bbox_overlaps(\n np.ascontiguousarray(all_rois[:, 1:5], dtype=np.float),\n np.ascontiguousarray(gt_boxes[:, :4], dtype=np.float))\n gt_assignment = overlaps.argmax(axis=1)\n max_overlaps = overlaps.max(axis=1)\n labels = gt_boxes[gt_assignment, 4]\n\n # Select foreground RoIs as those with >= FG_THRESH overlap\n fg_inds = np.where(max_overlaps >= cfg.TRAIN.FG_THRESH)[0]\n # Guard against the case when an image has fewer than fg_rois_per_image\n # foreground RoIs\n fg_rois_per_this_image = min(fg_rois_per_image, fg_inds.size)\n # Sample foreground regions without replacement\n if fg_inds.size > 0:\n fg_inds = npr.choice(fg_inds, size=fg_rois_per_this_image, replace=False)\n\n # Select background RoIs as those within [BG_THRESH_LO, BG_THRESH_HI)\n bg_inds = np.where((max_overlaps < cfg.TRAIN.BG_THRESH_HI) &\n (max_overlaps >= cfg.TRAIN.BG_THRESH_LO))[0]\n # Compute number of background RoIs to take from this image (guarding\n # against there being fewer than desired)\n bg_rois_per_this_image = rois_per_image - fg_rois_per_this_image\n bg_rois_per_this_image = min(bg_rois_per_this_image, bg_inds.size)\n # Sample background regions without replacement\n if bg_inds.size > 0:\n bg_inds = npr.choice(bg_inds, size=bg_rois_per_this_image, replace=False)\n\n # The indices that we're selecting (both fg and bg)\n keep_inds = np.append(fg_inds, bg_inds)\n # Select sampled values from various arrays:\n labels = labels[keep_inds]\n # Clamp labels for the background RoIs to 0\n labels[fg_rois_per_this_image:] = 0\n rois = all_rois[keep_inds]\n\n bbox_target_data = _compute_targets(\n rois[:, 1:5], gt_boxes[gt_assignment[keep_inds], :4], labels)\n\n bbox_targets, bbox_inside_weights = \\\n _get_bbox_regression_labels(bbox_target_data, num_classes)\n\n return labels, rois, bbox_targets, bbox_inside_weights\n" }, { "path": "lib/setup.py", "content": "# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\nimport os\nfrom os.path import join as pjoin\nfrom setuptools import setup\nfrom distutils.extension import Extension\nfrom Cython.Distutils import build_ext\nimport subprocess\nimport numpy as np\n\ndef find_in_path(name, path):\n \"Find a file in a search path\"\n # Adapted fom\n # http://code.activestate.com/recipes/52224-find-a-file-given-a-search-path/\n for dir in path.split(os.pathsep):\n binpath = pjoin(dir, name)\n if os.path.exists(binpath):\n return os.path.abspath(binpath)\n return None\n\n\ndef locate_cuda():\n \"\"\"Locate the CUDA environment on the system\n\n Returns a dict with keys 'home', 'nvcc', 'include', and 'lib64'\n and values giving the absolute path to each directory.\n\n Starts by looking for the CUDAHOME env variable. If not found, everything\n is based on finding 'nvcc' in the PATH.\n \"\"\"\n\n # first check if the CUDAHOME env variable is in use\n if 'CUDAHOME' in os.environ:\n home = os.environ['CUDAHOME']\n nvcc = pjoin(home, 'bin', 'nvcc')\n else:\n # otherwise, search the PATH for NVCC\n default_path = pjoin(os.sep, 'usr', 'local', 'cuda', 'bin')\n nvcc = find_in_path('nvcc', os.environ['PATH'] + os.pathsep + default_path)\n if nvcc is None:\n raise EnvironmentError('The nvcc binary could not be '\n 'located in your $PATH. Either add it to your path, or set $CUDAHOME')\n home = os.path.dirname(os.path.dirname(nvcc))\n\n cudaconfig = {'home':home, 'nvcc':nvcc,\n 'include': pjoin(home, 'include'),\n 'lib64': pjoin(home, 'lib64')}\n for k, v in cudaconfig.iteritems():\n if not os.path.exists(v):\n raise EnvironmentError('The CUDA %s path could not be located in %s' % (k, v))\n\n return cudaconfig\nCUDA = locate_cuda()\n\n\n# Obtain the numpy include directory. This logic works across numpy versions.\ntry:\n numpy_include = np.get_include()\nexcept AttributeError:\n numpy_include = np.get_numpy_include()\n\ndef customize_compiler_for_nvcc(self):\n \"\"\"inject deep into distutils to customize how the dispatch\n to gcc/nvcc works.\n\n If you subclass UnixCCompiler, it's not trivial to get your subclass\n injected in, and still have the right customizations (i.e.\n distutils.sysconfig.customize_compiler) run on it. So instead of going\n the OO route, I have this. Note, it's kindof like a wierd functional\n subclassing going on.\"\"\"\n\n # tell the compiler it can processes .cu\n self.src_extensions.append('.cu')\n\n # save references to the default compiler_so and _comple methods\n default_compiler_so = self.compiler_so\n super = self._compile\n\n # now redefine the _compile method. This gets executed for each\n # object but distutils doesn't have the ability to change compilers\n # based on source extension: we add it.\n def _compile(obj, src, ext, cc_args, extra_postargs, pp_opts):\n if os.path.splitext(src)[1] == '.cu':\n # use the cuda for .cu files\n self.set_executable('compiler_so', CUDA['nvcc'])\n # use only a subset of the extra_postargs, which are 1-1 translated\n # from the extra_compile_args in the Extension class\n postargs = extra_postargs['nvcc']\n else:\n postargs = extra_postargs['gcc']\n\n super(obj, src, ext, cc_args, postargs, pp_opts)\n # reset the default compiler_so, which we might have changed for cuda\n self.compiler_so = default_compiler_so\n\n # inject our redefined _compile method into the class\n self._compile = _compile\n\n\n# run the customize_compiler\nclass custom_build_ext(build_ext):\n def build_extensions(self):\n customize_compiler_for_nvcc(self.compiler)\n build_ext.build_extensions(self)\n\n\next_modules = [\n Extension(\n \"utils.cython_bbox\",\n [\"utils/bbox.pyx\"],\n extra_compile_args={'gcc': [\"-Wno-cpp\", \"-Wno-unused-function\"]},\n include_dirs = [numpy_include]\n ),\n Extension(\n \"nms.cpu_nms\",\n [\"nms/cpu_nms.pyx\"],\n extra_compile_args={'gcc': [\"-Wno-cpp\", \"-Wno-unused-function\"]},\n include_dirs = [numpy_include]\n ),\n Extension('nms.gpu_nms',\n ['nms/nms_kernel.cu', 'nms/gpu_nms.pyx'],\n library_dirs=[CUDA['lib64']],\n libraries=['cudart'],\n language='c++',\n runtime_library_dirs=[CUDA['lib64']],\n # this syntax is specific to this build system\n # we're only going to use certain compiler args with nvcc and not with\n # gcc the implementation of this trick is in customize_compiler() below\n extra_compile_args={'gcc': [\"-Wno-unused-function\"],\n 'nvcc': ['-arch=sm_35',\n '--ptxas-options=-v',\n '-c',\n '--compiler-options',\n \"'-fPIC'\"]},\n include_dirs = [numpy_include, CUDA['include']]\n ),\n Extension(\n 'pycocotools._mask',\n sources=['pycocotools/maskApi.c', 'pycocotools/_mask.pyx'],\n include_dirs = [numpy_include, 'pycocotools'],\n extra_compile_args={\n 'gcc': ['-Wno-cpp', '-Wno-unused-function', '-std=c99']},\n ),\n]\n\nsetup(\n name='fast_rcnn',\n ext_modules=ext_modules,\n # inject our custom trigger\n cmdclass={'build_ext': custom_build_ext},\n)\n" }, { "path": "lib/transform/__init__.py", "content": "" }, { "path": "lib/transform/torch_image_transform_layer.py", "content": "# --------------------------------------------------------\n# Fast/er R-CNN\n# Licensed under The MIT License [see LICENSE for details]\n# --------------------------------------------------------\n\n\"\"\" Transform images for compatibility with models trained with\nhttps://github.com/facebook/fb.resnet.torch.\n\nUsage in model prototxt:\n\nlayer {\n name: 'data_xform'\n type: 'Python'\n bottom: 'data_caffe'\n top: 'data'\n python_param {\n module: 'transform.torch_image_transform_layer'\n layer: 'TorchImageTransformLayer'\n }\n}\n\"\"\"\n\nimport caffe\nfrom fast_rcnn.config import cfg\nimport numpy as np\n\nclass TorchImageTransformLayer(caffe.Layer):\n def setup(self, bottom, top):\n # (1, 3, 1, 1) shaped arrays\n self.PIXEL_MEANS = \\\n np.array([[[[0.48462227599918]],\n [[0.45624044862054]],\n [[0.40588363755159]]]])\n self.PIXEL_STDS = \\\n np.array([[[[0.22889466674951]],\n [[0.22446679341259]],\n [[0.22495548344775]]]])\n # The default (\"old\") pixel means that were already subtracted\n channel_swap = (0, 3, 1, 2)\n self.OLD_PIXEL_MEANS = \\\n cfg.PIXEL_MEANS[np.newaxis, :, :, :].transpose(channel_swap)\n\n top[0].reshape(*(bottom[0].shape))\n\n def forward(self, bottom, top):\n ims = bottom[0].data\n # Invert the channel means that were already subtracted\n ims += self.OLD_PIXEL_MEANS\n # 1. Permute BGR to RGB and normalize to [0, 1]\n ims = ims[:, [2, 1, 0], :, :] / 255.0\n # 2. Remove channel means\n ims -= self.PIXEL_MEANS\n # 3. Standardize channels\n ims /= self.PIXEL_STDS\n top[0].reshape(*(ims.shape))\n top[0].data[...] = ims\n\n def backward(self, top, propagate_down, bottom):\n \"\"\"This layer does not propagate gradients.\"\"\"\n pass\n\n def reshape(self, bottom, top):\n \"\"\"Reshaping happens during the call to forward.\"\"\"\n pass\n" }, { "path": "lib/utils/.gitignore", "content": "*.c\n*.so\n" }, { "path": "lib/utils/__init__.py", "content": "# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n" }, { "path": "lib/utils/bbox.pyx", "content": "# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Sergey Karayev\n# --------------------------------------------------------\n\ncimport cython\nimport numpy as np\ncimport numpy as np\n\nDTYPE = np.float\nctypedef np.float_t DTYPE_t\n\ndef bbox_overlaps(\n np.ndarray[DTYPE_t, ndim=2] boxes,\n np.ndarray[DTYPE_t, ndim=2] query_boxes):\n \"\"\"\n Parameters\n ----------\n boxes: (N, 4) ndarray of float\n query_boxes: (K, 4) ndarray of float\n Returns\n -------\n overlaps: (N, K) ndarray of overlap between boxes and query_boxes\n \"\"\"\n cdef unsigned int N = boxes.shape[0]\n cdef unsigned int K = query_boxes.shape[0]\n cdef np.ndarray[DTYPE_t, ndim=2] overlaps = np.zeros((N, K), dtype=DTYPE)\n cdef DTYPE_t iw, ih, box_area\n cdef DTYPE_t ua\n cdef unsigned int k, n\n for k in range(K):\n box_area = (\n (query_boxes[k, 2] - query_boxes[k, 0] + 1) *\n (query_boxes[k, 3] - query_boxes[k, 1] + 1)\n )\n for n in range(N):\n iw = (\n min(boxes[n, 2], query_boxes[k, 2]) -\n max(boxes[n, 0], query_boxes[k, 0]) + 1\n )\n if iw > 0:\n ih = (\n min(boxes[n, 3], query_boxes[k, 3]) -\n max(boxes[n, 1], query_boxes[k, 1]) + 1\n )\n if ih > 0:\n ua = float(\n (boxes[n, 2] - boxes[n, 0] + 1) *\n (boxes[n, 3] - boxes[n, 1] + 1) +\n box_area - iw * ih\n )\n overlaps[n, k] = iw * ih / ua\n return overlaps\n" }, { "path": "lib/utils/blob.py", "content": "# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\n\"\"\"Blob helper functions.\"\"\"\n\nimport numpy as np\nimport cv2\n\ndef im_list_to_blob(ims):\n \"\"\"Convert a list of images into a network input.\n\n Assumes images are already prepared (means subtracted, BGR order, ...).\n \"\"\"\n max_shape = np.array([im.shape for im in ims]).max(axis=0)\n num_images = len(ims)\n blob = np.zeros((num_images, max_shape[0], max_shape[1], 3),\n dtype=np.float32)\n for i in xrange(num_images):\n im = ims[i]\n blob[i, 0:im.shape[0], 0:im.shape[1], :] = im\n # Move channels (axis 3) to axis 1\n # Axis order will become: (batch elem, channel, height, width)\n channel_swap = (0, 3, 1, 2)\n blob = blob.transpose(channel_swap)\n return blob\n\ndef prep_im_for_blob(im, pixel_means, target_size, max_size):\n \"\"\"Mean subtract and scale an image for use in a blob.\"\"\"\n im = im.astype(np.float32, copy=False)\n im -= pixel_means\n im_shape = im.shape\n im_size_min = np.min(im_shape[0:2])\n im_size_max = np.max(im_shape[0:2])\n im_scale = float(target_size) / float(im_size_min)\n # Prevent the biggest axis from being more than MAX_SIZE\n if np.round(im_scale * im_size_max) > max_size:\n im_scale = float(max_size) / float(im_size_max)\n im = cv2.resize(im, None, None, fx=im_scale, fy=im_scale,\n interpolation=cv2.INTER_LINEAR)\n\n return im, im_scale\n" }, { "path": "lib/utils/timer.py", "content": "# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\nimport time\n\nclass Timer(object):\n \"\"\"A simple timer.\"\"\"\n def __init__(self):\n self.total_time = 0.\n self.calls = 0\n self.start_time = 0.\n self.diff = 0.\n self.average_time = 0.\n\n def tic(self):\n # using time.time instead of time.clock because time time.clock\n # does not normalize for multithreading\n self.start_time = time.time()\n\n def toc(self, average=True):\n self.diff = time.time() - self.start_time\n self.total_time += self.diff\n self.calls += 1\n self.average_time = self.total_time / self.calls\n if average:\n return self.average_time\n else:\n return self.diff\n" }, { "path": "models/README.md", "content": "## Model Zoo\n\n### COCO Faster R-CNN VGG-16 trained using end-to-end\n\nModel URL: www.cs.berkeley.edu/~rbg/faster-rcnn-data/coco_vgg16_faster_rcnn_final.caffemodel\n\nTraining command:\n```\ntools/train_net.py \\\n --gpu 0 \\\n --solver ./models/coco/VGG16/faster_rcnn_end2end/solver.prototxt \\\n --weights data/imagenet_models/VGG16.v2.caffemodel \\\n --imdb coco_2014_train+coco_2014_valminusminival \\\n --iters 490000 \\\n --cfg ./experiments/cfgs/faster_rcnn_end2end.yml\n```\n\n`py-faster-rcnn` commit: 68eec95\n\ntest-dev2015 results\n```\n Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.242\n Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.453\n Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.235\n Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.077\n Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.264\n Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.371\n Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.238\n Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.340\n Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.346\n Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.120\n Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.385\n Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.544\n```\n\ntest-standard2015 results\n```\n Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.242\n Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.453\n Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.234\n Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.072\n Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.264\n Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.369\n Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.238\n Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.341\n Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.347\n Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.115\n Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.389\n Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.544\n```\n" }, { "path": "models/coco/VGG16/fast_rcnn/solver.prototxt", "content": "train_net: \"models/coco/VGG16/fast_rcnn/train.prototxt\"\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 200000\ndisplay: 20\naverage_loss: 100\n# iter_size: 1\nmomentum: 0.9\nweight_decay: 0.0005\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"vgg16_fast_rcnn\"\n#debug_info: true\n" }, { "path": "models/coco/VGG16/fast_rcnn/test.prototxt", "content": "name: \"VGG_ILSVRC_16_layers\"\n\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\n\ninput: \"rois\"\ninput_shape {\n dim: 1 # to be changed on-the-fly to num ROIs\n dim: 5 # [batch ind, x1, y1, x2, y2] zero-based indexing\n}\n\nlayer {\n name: \"conv1_1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1_1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_1\"\n type: \"ReLU\"\n bottom: \"conv1_1\"\n top: \"conv1_1\"\n}\nlayer {\n name: \"conv1_2\"\n type: \"Convolution\"\n bottom: \"conv1_1\"\n top: \"conv1_2\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_2\"\n type: \"ReLU\"\n bottom: \"conv1_2\"\n top: \"conv1_2\"\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"conv1_2\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv2_1\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2_1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_1\"\n type: \"ReLU\"\n bottom: \"conv2_1\"\n top: \"conv2_1\"\n}\nlayer {\n name: \"conv2_2\"\n type: \"Convolution\"\n bottom: \"conv2_1\"\n top: \"conv2_2\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_2\"\n type: \"ReLU\"\n bottom: \"conv2_2\"\n top: \"conv2_2\"\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"conv2_2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv3_1\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3_1\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_1\"\n type: \"ReLU\"\n bottom: \"conv3_1\"\n top: \"conv3_1\"\n}\nlayer {\n name: \"conv3_2\"\n type: \"Convolution\"\n bottom: \"conv3_1\"\n top: \"conv3_2\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_2\"\n type: \"ReLU\"\n bottom: \"conv3_2\"\n top: \"conv3_2\"\n}\nlayer {\n name: \"conv3_3\"\n type: \"Convolution\"\n bottom: \"conv3_2\"\n top: \"conv3_3\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_3\"\n type: \"ReLU\"\n bottom: \"conv3_3\"\n top: \"conv3_3\"\n}\nlayer {\n name: \"pool3\"\n type: \"Pooling\"\n bottom: \"conv3_3\"\n top: \"pool3\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv4_1\"\n type: \"Convolution\"\n bottom: \"pool3\"\n top: \"conv4_1\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_1\"\n type: \"ReLU\"\n bottom: \"conv4_1\"\n top: \"conv4_1\"\n}\nlayer {\n name: \"conv4_2\"\n type: \"Convolution\"\n bottom: \"conv4_1\"\n top: \"conv4_2\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_2\"\n type: \"ReLU\"\n bottom: \"conv4_2\"\n top: \"conv4_2\"\n}\nlayer {\n name: \"conv4_3\"\n type: \"Convolution\"\n bottom: \"conv4_2\"\n top: \"conv4_3\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_3\"\n type: \"ReLU\"\n bottom: \"conv4_3\"\n top: \"conv4_3\"\n}\nlayer {\n name: \"pool4\"\n type: \"Pooling\"\n bottom: \"conv4_3\"\n top: \"pool4\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv5_1\"\n type: \"Convolution\"\n bottom: \"pool4\"\n top: \"conv5_1\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_1\"\n type: \"ReLU\"\n bottom: \"conv5_1\"\n top: \"conv5_1\"\n}\nlayer {\n name: \"conv5_2\"\n type: \"Convolution\"\n bottom: \"conv5_1\"\n top: \"conv5_2\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_2\"\n type: \"ReLU\"\n bottom: \"conv5_2\"\n top: \"conv5_2\"\n}\nlayer {\n name: \"conv5_3\"\n type: \"Convolution\"\n bottom: \"conv5_2\"\n top: \"conv5_3\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_3\"\n type: \"ReLU\"\n bottom: \"conv5_3\"\n top: \"conv5_3\"\n}\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"conv5_3\"\n bottom: \"rois\"\n top: \"pool5\"\n roi_pooling_param {\n pooled_w: 7\n pooled_h: 7\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"fc6\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 81\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 324\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"cls_prob\"\n type: \"Softmax\"\n bottom: \"cls_score\"\n top: \"cls_prob\"\n}\n" }, { "path": "models/coco/VGG16/fast_rcnn/train.prototxt", "content": "name: \"VGG_ILSVRC_16_layers\"\nlayer {\n name: 'data'\n type: 'Python'\n top: 'data'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 81\"\n }\n}\nlayer {\n name: \"conv1_1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1_1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_1\"\n type: \"ReLU\"\n bottom: \"conv1_1\"\n top: \"conv1_1\"\n}\nlayer {\n name: \"conv1_2\"\n type: \"Convolution\"\n bottom: \"conv1_1\"\n top: \"conv1_2\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_2\"\n type: \"ReLU\"\n bottom: \"conv1_2\"\n top: \"conv1_2\"\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"conv1_2\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv2_1\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2_1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_1\"\n type: \"ReLU\"\n bottom: \"conv2_1\"\n top: \"conv2_1\"\n}\nlayer {\n name: \"conv2_2\"\n type: \"Convolution\"\n bottom: \"conv2_1\"\n top: \"conv2_2\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_2\"\n type: \"ReLU\"\n bottom: \"conv2_2\"\n top: \"conv2_2\"\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"conv2_2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv3_1\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3_1\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_1\"\n type: \"ReLU\"\n bottom: \"conv3_1\"\n top: \"conv3_1\"\n}\nlayer {\n name: \"conv3_2\"\n type: \"Convolution\"\n bottom: \"conv3_1\"\n top: \"conv3_2\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_2\"\n type: \"ReLU\"\n bottom: \"conv3_2\"\n top: \"conv3_2\"\n}\nlayer {\n name: \"conv3_3\"\n type: \"Convolution\"\n bottom: \"conv3_2\"\n top: \"conv3_3\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_3\"\n type: \"ReLU\"\n bottom: \"conv3_3\"\n top: \"conv3_3\"\n}\nlayer {\n name: \"pool3\"\n type: \"Pooling\"\n bottom: \"conv3_3\"\n top: \"pool3\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv4_1\"\n type: \"Convolution\"\n bottom: \"pool3\"\n top: \"conv4_1\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_1\"\n type: \"ReLU\"\n bottom: \"conv4_1\"\n top: \"conv4_1\"\n}\nlayer {\n name: \"conv4_2\"\n type: \"Convolution\"\n bottom: \"conv4_1\"\n top: \"conv4_2\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_2\"\n type: \"ReLU\"\n bottom: \"conv4_2\"\n top: \"conv4_2\"\n}\nlayer {\n name: \"conv4_3\"\n type: \"Convolution\"\n bottom: \"conv4_2\"\n top: \"conv4_3\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_3\"\n type: \"ReLU\"\n bottom: \"conv4_3\"\n top: \"conv4_3\"\n}\nlayer {\n name: \"pool4\"\n type: \"Pooling\"\n bottom: \"conv4_3\"\n top: \"pool4\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv5_1\"\n type: \"Convolution\"\n bottom: \"pool4\"\n top: \"conv5_1\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_1\"\n type: \"ReLU\"\n bottom: \"conv5_1\"\n top: \"conv5_1\"\n}\nlayer {\n name: \"conv5_2\"\n type: \"Convolution\"\n bottom: \"conv5_1\"\n top: \"conv5_2\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_2\"\n type: \"ReLU\"\n bottom: \"conv5_2\"\n top: \"conv5_2\"\n}\nlayer {\n name: \"conv5_3\"\n type: \"Convolution\"\n bottom: \"conv5_2\"\n top: \"conv5_3\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_3\"\n type: \"ReLU\"\n bottom: \"conv5_3\"\n top: \"conv5_3\"\n}\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"conv5_3\"\n bottom: \"rois\"\n top: \"pool5\"\n roi_pooling_param {\n pooled_w: 7\n pooled_h: 7\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"fc6\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 81\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 324\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"loss_bbox\"\n loss_weight: 1\n}\n" }, { "path": "models/coco/VGG16/faster_rcnn_end2end/solver.prototxt", "content": "train_net: \"models/coco/VGG16/faster_rcnn_end2end/train.prototxt\"\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 350000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"vgg16_faster_rcnn\"\niter_size: 2\n" }, { "path": "models/coco/VGG16/faster_rcnn_end2end/test.prototxt", "content": "name: \"VGG_ILSVRC_16_layers\"\n\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\n\ninput: \"im_info\"\ninput_shape {\n dim: 1\n dim: 3\n}\n\nlayer {\n name: \"conv1_1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1_1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_1\"\n type: \"ReLU\"\n bottom: \"conv1_1\"\n top: \"conv1_1\"\n}\nlayer {\n name: \"conv1_2\"\n type: \"Convolution\"\n bottom: \"conv1_1\"\n top: \"conv1_2\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_2\"\n type: \"ReLU\"\n bottom: \"conv1_2\"\n top: \"conv1_2\"\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"conv1_2\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv2_1\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2_1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_1\"\n type: \"ReLU\"\n bottom: \"conv2_1\"\n top: \"conv2_1\"\n}\nlayer {\n name: \"conv2_2\"\n type: \"Convolution\"\n bottom: \"conv2_1\"\n top: \"conv2_2\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_2\"\n type: \"ReLU\"\n bottom: \"conv2_2\"\n top: \"conv2_2\"\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"conv2_2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv3_1\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3_1\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_1\"\n type: \"ReLU\"\n bottom: \"conv3_1\"\n top: \"conv3_1\"\n}\nlayer {\n name: \"conv3_2\"\n type: \"Convolution\"\n bottom: \"conv3_1\"\n top: \"conv3_2\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_2\"\n type: \"ReLU\"\n bottom: \"conv3_2\"\n top: \"conv3_2\"\n}\nlayer {\n name: \"conv3_3\"\n type: \"Convolution\"\n bottom: \"conv3_2\"\n top: \"conv3_3\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_3\"\n type: \"ReLU\"\n bottom: \"conv3_3\"\n top: \"conv3_3\"\n}\nlayer {\n name: \"pool3\"\n type: \"Pooling\"\n bottom: \"conv3_3\"\n top: \"pool3\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv4_1\"\n type: \"Convolution\"\n bottom: \"pool3\"\n top: \"conv4_1\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_1\"\n type: \"ReLU\"\n bottom: \"conv4_1\"\n top: \"conv4_1\"\n}\nlayer {\n name: \"conv4_2\"\n type: \"Convolution\"\n bottom: \"conv4_1\"\n top: \"conv4_2\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_2\"\n type: \"ReLU\"\n bottom: \"conv4_2\"\n top: \"conv4_2\"\n}\nlayer {\n name: \"conv4_3\"\n type: \"Convolution\"\n bottom: \"conv4_2\"\n top: \"conv4_3\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_3\"\n type: \"ReLU\"\n bottom: \"conv4_3\"\n top: \"conv4_3\"\n}\nlayer {\n name: \"pool4\"\n type: \"Pooling\"\n bottom: \"conv4_3\"\n top: \"pool4\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv5_1\"\n type: \"Convolution\"\n bottom: \"pool4\"\n top: \"conv5_1\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_1\"\n type: \"ReLU\"\n bottom: \"conv5_1\"\n top: \"conv5_1\"\n}\nlayer {\n name: \"conv5_2\"\n type: \"Convolution\"\n bottom: \"conv5_1\"\n top: \"conv5_2\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_2\"\n type: \"ReLU\"\n bottom: \"conv5_2\"\n top: \"conv5_2\"\n}\nlayer {\n name: \"conv5_3\"\n type: \"Convolution\"\n bottom: \"conv5_2\"\n top: \"conv5_3\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_3\"\n type: \"ReLU\"\n bottom: \"conv5_3\"\n top: \"conv5_3\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"conv5_3\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 decay_mult: 1.0 }\n param { lr_mult: 2.0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 decay_mult: 1.0 }\n param { lr_mult: 2.0 decay_mult: 0 }\n convolution_param {\n num_output: 24 # 2(bg/fg) * 12(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 decay_mult: 1.0 }\n param { lr_mult: 2.0 decay_mult: 0 }\n convolution_param {\n num_output: 48 # 4 * 12(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 24 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rois'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16 \\n'scales': !!python/tuple [4, 8, 16, 32]\"\n }\n}\n\n#========= RCNN ============\n\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"conv5_3\"\n bottom: \"rois\"\n top: \"pool5\"\n roi_pooling_param {\n pooled_w: 7\n pooled_h: 7\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"fc6\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 81\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 324\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"cls_prob\"\n type: \"Softmax\"\n bottom: \"cls_score\"\n top: \"cls_prob\"\n}\n" }, { "path": "models/coco/VGG16/faster_rcnn_end2end/train.prototxt", "content": "name: \"VGG_ILSVRC_16_layers\"\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 81\"\n }\n}\n\nlayer {\n name: \"conv1_1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1_1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_1\"\n type: \"ReLU\"\n bottom: \"conv1_1\"\n top: \"conv1_1\"\n}\nlayer {\n name: \"conv1_2\"\n type: \"Convolution\"\n bottom: \"conv1_1\"\n top: \"conv1_2\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_2\"\n type: \"ReLU\"\n bottom: \"conv1_2\"\n top: \"conv1_2\"\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"conv1_2\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv2_1\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2_1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_1\"\n type: \"ReLU\"\n bottom: \"conv2_1\"\n top: \"conv2_1\"\n}\nlayer {\n name: \"conv2_2\"\n type: \"Convolution\"\n bottom: \"conv2_1\"\n top: \"conv2_2\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_2\"\n type: \"ReLU\"\n bottom: \"conv2_2\"\n top: \"conv2_2\"\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"conv2_2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv3_1\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3_1\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_1\"\n type: \"ReLU\"\n bottom: \"conv3_1\"\n top: \"conv3_1\"\n}\nlayer {\n name: \"conv3_2\"\n type: \"Convolution\"\n bottom: \"conv3_1\"\n top: \"conv3_2\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_2\"\n type: \"ReLU\"\n bottom: \"conv3_2\"\n top: \"conv3_2\"\n}\nlayer {\n name: \"conv3_3\"\n type: \"Convolution\"\n bottom: \"conv3_2\"\n top: \"conv3_3\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_3\"\n type: \"ReLU\"\n bottom: \"conv3_3\"\n top: \"conv3_3\"\n}\nlayer {\n name: \"pool3\"\n type: \"Pooling\"\n bottom: \"conv3_3\"\n top: \"pool3\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv4_1\"\n type: \"Convolution\"\n bottom: \"pool3\"\n top: \"conv4_1\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_1\"\n type: \"ReLU\"\n bottom: \"conv4_1\"\n top: \"conv4_1\"\n}\nlayer {\n name: \"conv4_2\"\n type: \"Convolution\"\n bottom: \"conv4_1\"\n top: \"conv4_2\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_2\"\n type: \"ReLU\"\n bottom: \"conv4_2\"\n top: \"conv4_2\"\n}\nlayer {\n name: \"conv4_3\"\n type: \"Convolution\"\n bottom: \"conv4_2\"\n top: \"conv4_3\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_3\"\n type: \"ReLU\"\n bottom: \"conv4_3\"\n top: \"conv4_3\"\n}\nlayer {\n name: \"pool4\"\n type: \"Pooling\"\n bottom: \"conv4_3\"\n top: \"pool4\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv5_1\"\n type: \"Convolution\"\n bottom: \"pool4\"\n top: \"conv5_1\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_1\"\n type: \"ReLU\"\n bottom: \"conv5_1\"\n top: \"conv5_1\"\n}\nlayer {\n name: \"conv5_2\"\n type: \"Convolution\"\n bottom: \"conv5_1\"\n top: \"conv5_2\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_2\"\n type: \"ReLU\"\n bottom: \"conv5_2\"\n top: \"conv5_2\"\n}\nlayer {\n name: \"conv5_3\"\n type: \"Convolution\"\n bottom: \"conv5_2\"\n top: \"conv5_3\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_3\"\n type: \"ReLU\"\n bottom: \"conv5_3\"\n top: \"conv5_3\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"conv5_3\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 512\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 24 # 2(bg/fg) * 12(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 48 # 4 * 12(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16 \\n'scales': !!python/tuple [4, 8, 16, 32]\"\n }\n}\n\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\n\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 24 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rpn_rois'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16 \\n'scales': !!python/tuple [4, 8, 16, 32]\"\n }\n}\n\nlayer {\n name: 'roi-data'\n type: 'Python'\n bottom: 'rpn_rois'\n bottom: 'gt_boxes'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'rpn.proposal_target_layer'\n layer: 'ProposalTargetLayer'\n param_str: \"'num_classes': 81\"\n }\n}\n\n#========= RCNN ============\n\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"conv5_3\"\n bottom: \"rois\"\n top: \"pool5\"\n roi_pooling_param {\n pooled_w: 7\n pooled_h: 7\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"fc6\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 81\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 324\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"loss_bbox\"\n loss_weight: 1\n}\n" }, { "path": "models/coco/VGG_CNN_M_1024/fast_rcnn/solver.prototxt", "content": "train_net: \"models/coco/VGG_CNN_M_1024/fast_rcnn/train.prototxt\"\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 200000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"vgg_cnn_m_1024_fast_rcnn\"\n#debug_info: true\n" }, { "path": "models/coco/VGG_CNN_M_1024/fast_rcnn/test.prototxt", "content": "name: \"VGG_CNN_M_1024\"\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\ninput: \"rois\"\ninput_shape {\n dim: 1 # to be changed on-the-fly to num ROIs\n dim: 5 # [batch ind, x1, y1, x2, y2] zero-based indexing\n}\nlayer {\n name: \"conv1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 96\n kernel_size: 7\n stride: 2\n }\n}\nlayer {\n name: \"relu1\"\n type: \"ReLU\"\n bottom: \"conv1\"\n top: \"conv1\"\n}\nlayer {\n name: \"norm1\"\n type: \"LRN\"\n bottom: \"conv1\"\n top: \"norm1\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"norm1\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 3\n stride: 2\n }\n}\nlayer {\n name: \"conv2\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 5\n stride: 2\n }\n}\nlayer {\n name: \"relu2\"\n type: \"ReLU\"\n bottom: \"conv2\"\n top: \"conv2\"\n}\nlayer {\n name: \"norm2\"\n type: \"LRN\"\n bottom: \"conv2\"\n top: \"norm2\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"norm2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 3\n stride: 2\n }\n}\nlayer {\n name: \"conv3\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3\"\n type: \"ReLU\"\n bottom: \"conv3\"\n top: \"conv3\"\n}\nlayer {\n name: \"conv4\"\n type: \"Convolution\"\n bottom: \"conv3\"\n top: \"conv4\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4\"\n type: \"ReLU\"\n bottom: \"conv4\"\n top: \"conv4\"\n}\nlayer {\n name: \"conv5\"\n type: \"Convolution\"\n bottom: \"conv4\"\n top: \"conv5\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5\"\n type: \"ReLU\"\n bottom: \"conv5\"\n top: \"conv5\"\n}\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"conv5\"\n bottom: \"rois\"\n top: \"pool5\"\n roi_pooling_param {\n pooled_w: 6\n pooled_h: 6\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"fc6\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 1024\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 81\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 324\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"cls_prob\"\n type: \"Softmax\"\n bottom: \"cls_score\"\n top: \"cls_prob\"\n}\n" }, { "path": "models/coco/VGG_CNN_M_1024/fast_rcnn/train.prototxt", "content": "name: \"VGG_CNN_M_1024\"\nlayer {\n name: 'data'\n type: 'Python'\n top: 'data'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 81\"\n }\n}\nlayer {\n name: \"conv1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 96\n kernel_size: 7\n stride: 2\n }\n}\nlayer {\n name: \"relu1\"\n type: \"ReLU\"\n bottom: \"conv1\"\n top: \"conv1\"\n}\nlayer {\n name: \"norm1\"\n type: \"LRN\"\n bottom: \"conv1\"\n top: \"norm1\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"norm1\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 3\n stride: 2\n }\n}\nlayer {\n name: \"conv2\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 5\n stride: 2\n }\n}\nlayer {\n name: \"relu2\"\n type: \"ReLU\"\n bottom: \"conv2\"\n top: \"conv2\"\n}\nlayer {\n name: \"norm2\"\n type: \"LRN\"\n bottom: \"conv2\"\n top: \"norm2\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"norm2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 3\n stride: 2\n }\n}\nlayer {\n name: \"conv3\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3\"\n type: \"ReLU\"\n bottom: \"conv3\"\n top: \"conv3\"\n}\nlayer {\n name: \"conv4\"\n type: \"Convolution\"\n bottom: \"conv3\"\n top: \"conv4\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4\"\n type: \"ReLU\"\n bottom: \"conv4\"\n top: \"conv4\"\n}\nlayer {\n name: \"conv5\"\n type: \"Convolution\"\n bottom: \"conv4\"\n top: \"conv5\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5\"\n type: \"ReLU\"\n bottom: \"conv5\"\n top: \"conv5\"\n}\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"conv5\"\n bottom: \"rois\"\n top: \"pool5\"\n roi_pooling_param {\n pooled_w: 6\n pooled_h: 6\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"fc6\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 1024\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 81\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 324\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"loss_bbox\"\n loss_weight: 1\n}\n" }, { "path": "models/coco/VGG_CNN_M_1024/faster_rcnn_end2end/solver.prototxt", "content": "train_net: \"models/coco/VGG_CNN_M_1024/faster_rcnn_end2end/train.prototxt\"\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 350000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"vgg_cnn_m_1024_faster_rcnn\"\n" }, { "path": "models/coco/VGG_CNN_M_1024/faster_rcnn_end2end/test.prototxt", "content": "name: \"VGG_CNN_M_1024\"\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\ninput: \"im_info\"\ninput_shape {\n dim: 1\n dim: 3\n}\nlayer {\n name: \"conv1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 96\n kernel_size: 7\n stride: 2\n }\n}\nlayer {\n name: \"relu1\"\n type: \"ReLU\"\n bottom: \"conv1\"\n top: \"conv1\"\n}\nlayer {\n name: \"norm1\"\n type: \"LRN\"\n bottom: \"conv1\"\n top: \"norm1\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"norm1\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 3\n stride: 2\n }\n}\nlayer {\n name: \"conv2\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 5\n stride: 2\n }\n}\nlayer {\n name: \"relu2\"\n type: \"ReLU\"\n bottom: \"conv2\"\n top: \"conv2\"\n}\nlayer {\n name: \"norm2\"\n type: \"LRN\"\n bottom: \"conv2\"\n top: \"norm2\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"norm2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 3\n stride: 2\n }\n}\nlayer {\n name: \"conv3\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3\"\n type: \"ReLU\"\n bottom: \"conv3\"\n top: \"conv3\"\n}\nlayer {\n name: \"conv4\"\n type: \"Convolution\"\n bottom: \"conv3\"\n top: \"conv4\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4\"\n type: \"ReLU\"\n bottom: \"conv4\"\n top: \"conv4\"\n}\nlayer {\n name: \"conv5\"\n type: \"Convolution\"\n bottom: \"conv4\"\n top: \"conv5\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5\"\n type: \"ReLU\"\n bottom: \"conv5\"\n top: \"conv5\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"conv5\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 decay_mult: 1.0 }\n param { lr_mult: 2.0 decay_mult: 0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\n#layer {\n# name: \"rpn_conv/3x3\"\n# type: \"Convolution\"\n# bottom: \"conv5\"\n# top: \"rpn_conv/3x3\"\n# param { lr_mult: 1.0 decay_mult: 1.0 }\n# param { lr_mult: 2.0 decay_mult: 0 }\n# convolution_param {\n# num_output: 192\n# kernel_size: 3 pad: 1 stride: 1\n# weight_filler { type: \"gaussian\" std: 0.01 }\n# bias_filler { type: \"constant\" value: 0 }\n# }\n#}\n#layer {\n# name: \"rpn_conv/5x5\"\n# type: \"Convolution\"\n# bottom: \"conv5\"\n# top: \"rpn_conv/5x5\"\n# param { lr_mult: 1.0 decay_mult: 1.0 }\n# param { lr_mult: 2.0 decay_mult: 0 }\n# convolution_param {\n# num_output: 64\n# kernel_size: 5 pad: 2 stride: 1\n# weight_filler { type: \"gaussian\" std: 0.0036 }\n# bias_filler { type: \"constant\" value: 0 }\n# }\n#}\n#layer {\n# name: \"rpn/output\"\n# type: \"Concat\"\n# bottom: \"rpn_conv/3x3\"\n# bottom: \"rpn_conv/5x5\"\n# top: \"rpn/output\"\n#}\n#layer {\n# name: \"rpn_relu/output\"\n# type: \"ReLU\"\n# bottom: \"rpn/output\"\n# top: \"rpn/output\"\n#}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 decay_mult: 1.0 }\n param { lr_mult: 2.0 decay_mult: 0 }\n convolution_param {\n num_output: 24 # 2(bg/fg) * 12(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 decay_mult: 1.0 }\n param { lr_mult: 2.0 decay_mult: 0 }\n convolution_param {\n num_output: 48 # 4 * 12(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 24 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rois'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16 \\n'scales': !!python/tuple [4, 8, 16, 32]\"\n }\n}\n\n#========= RCNN ============\n\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"conv5\"\n bottom: \"rois\"\n top: \"pool5\"\n roi_pooling_param {\n pooled_w: 6\n pooled_h: 6\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"fc6\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 1024\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 81\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 324\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"cls_prob\"\n type: \"Softmax\"\n bottom: \"cls_score\"\n top: \"cls_prob\"\n}\n" }, { "path": "models/coco/VGG_CNN_M_1024/faster_rcnn_end2end/train.prototxt", "content": "name: \"VGG_CNN_M_1024\"\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 81\"\n }\n}\nlayer {\n name: \"conv1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 96\n kernel_size: 7\n stride: 2\n }\n}\nlayer {\n name: \"relu1\"\n type: \"ReLU\"\n bottom: \"conv1\"\n top: \"conv1\"\n}\nlayer {\n name: \"norm1\"\n type: \"LRN\"\n bottom: \"conv1\"\n top: \"norm1\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"norm1\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 3\n stride: 2\n }\n}\nlayer {\n name: \"conv2\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 5\n stride: 2\n }\n}\nlayer {\n name: \"relu2\"\n type: \"ReLU\"\n bottom: \"conv2\"\n top: \"conv2\"\n}\nlayer {\n name: \"norm2\"\n type: \"LRN\"\n bottom: \"conv2\"\n top: \"norm2\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"norm2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 3\n stride: 2\n }\n}\nlayer {\n name: \"conv3\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3\"\n type: \"ReLU\"\n bottom: \"conv3\"\n top: \"conv3\"\n}\nlayer {\n name: \"conv4\"\n type: \"Convolution\"\n bottom: \"conv3\"\n top: \"conv4\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4\"\n type: \"ReLU\"\n bottom: \"conv4\"\n top: \"conv4\"\n}\nlayer {\n name: \"conv5\"\n type: \"Convolution\"\n bottom: \"conv4\"\n top: \"conv5\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5\"\n type: \"ReLU\"\n bottom: \"conv5\"\n top: \"conv5\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"conv5\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 24 # 2(bg/fg) * 12(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 48 # 4 * 12(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16 \\n'scales': !!python/tuple [4, 8, 16, 32]\"\n }\n}\n\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\n\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 24 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rpn_rois'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16 \\n'scales': !!python/tuple [4, 8, 16, 32]\"\n }\n}\n\nlayer {\n name: 'roi-data'\n type: 'Python'\n bottom: 'rpn_rois'\n bottom: 'gt_boxes'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'rpn.proposal_target_layer'\n layer: 'ProposalTargetLayer'\n param_str: \"'num_classes': 81\"\n }\n}\n\n#========= RCNN ============\n\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"conv5\"\n bottom: \"rois\"\n top: \"pool5\"\n roi_pooling_param {\n pooled_w: 6\n pooled_h: 6\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"fc6\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 1024\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 81\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 324\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"loss_bbox\"\n loss_weight: 1\n}\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_BN_SCALE_Merged/faster_rcnn_alt_opt/faster_rcnn_test.pt", "content": "name: \"ResNet50_BN_SCALE_Merged\"\n\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\n\ninput: \"im_info\"\ninput_shape {\n dim: 1\n dim: 3\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4f\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rois'\n top: 'scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n\n#========= RCNN ============\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"res4f\"\n bottom: \"rois\"\n top: \"roi_pool5\"\n roi_pooling_param {\n pooled_w: 14\n pooled_h: 14\n spatial_scale: 0.0625 # 1/16\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\n\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\n\nlayer {\n name: \"cls_prob\"\n type: \"Softmax\"\n bottom: \"cls_score\"\n top: \"cls_prob\"\n}\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_BN_SCALE_Merged/faster_rcnn_alt_opt/rpn_test.pt", "content": "name: \"ResNet50_BN_SCALE_Merged\"\n\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\n\ninput: \"im_info\"\ninput_shape {\n dim: 1\n dim: 3\n}\n\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4f\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rois'\n top: 'scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_BN_SCALE_Merged/faster_rcnn_alt_opt/stage1_fast_rcnn_solver30k40k.pt", "content": "train_net: \"models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_alt_opt/stage1_fast_rcnn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 30000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet101_bn_scale_merged_fast_rcnn\"\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_BN_SCALE_Merged/faster_rcnn_alt_opt/stage1_fast_rcnn_train.pt", "content": "name: \"ResNet50_BN_SCALE_Merged\"\nlayer {\n name: 'data'\n type: 'Python'\n top: 'data'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"res4f\"\n bottom: \"rois\"\n top: \"roi_pool5\"\n roi_pooling_param {\n pooled_w: 14\n pooled_h: 14\n spatial_scale: 0.0625 # 1/16\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\n\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"loss_bbox\"\n loss_weight: 1\n}\n\n\n#========= RPN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4f\"\n top: \"rpn/output\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"silence_rpn_cls_score\"\n type: \"Silence\"\n bottom: \"rpn_cls_score\"\n}\nlayer {\n name: \"silence_rpn_bbox_pred\"\n type: \"Silence\"\n bottom: \"rpn_bbox_pred\"\n}\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_BN_SCALE_Merged/faster_rcnn_alt_opt/stage1_rpn_solver60k80k.pt", "content": "train_net: \"models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_alt_opt/stage1_rpn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 60000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet101_bn_scale_merged_rpn\"\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_BN_SCALE_Merged/faster_rcnn_alt_opt/stage1_rpn_train.pt", "content": "name: \"ResNet50_BN_SCALE_Merged\"\n\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4f\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RCNN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"dummy_roi_pool_res4f\"\n type: \"DummyData\"\n top: \"dummy_roi_pool_res4f\"\n dummy_data_param {\n shape { dim: 1 dim: 1024 dim: 14 dim: 14 }\n data_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"dummy_roi_pool_res4f\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"dummy_roi_pool_res4f\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\nlayer {\n name: \"silence_pool5\"\n type: \"Silence\"\n bottom: \"pool5\"\n}\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_BN_SCALE_Merged/faster_rcnn_alt_opt/stage2_fast_rcnn_solver30k40k.pt", "content": "train_net: \"models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_alt_opt/stage2_fast_rcnn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 30000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet101_bn_scale_merged_fast_rcnn\"\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_BN_SCALE_Merged/faster_rcnn_alt_opt/stage2_fast_rcnn_train.pt", "content": "name: \"ResNet50_BN_SCALE_Merged\"\nlayer {\n name: 'data'\n type: 'Python'\n top: 'data'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"res4f\"\n bottom: \"rois\"\n top: \"roi_pool5\"\n roi_pooling_param {\n pooled_w: 14\n pooled_h: 14\n spatial_scale: 0.0625 # 1/16\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\n\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"loss_bbox\"\n loss_weight: 1\n}\n\n\n#========= RPN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4f\"\n top: \"rpn/output\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"silence_rpn_cls_score\"\n type: \"Silence\"\n bottom: \"rpn_cls_score\"\n}\nlayer {\n name: \"silence_rpn_bbox_pred\"\n type: \"Silence\"\n bottom: \"rpn_bbox_pred\"\n}\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_BN_SCALE_Merged/faster_rcnn_alt_opt/stage2_rpn_solver60k80k.pt", "content": "train_net: \"models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_alt_opt/stage2_rpn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 60000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet101_bn_scale_merged_rpn\"\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_BN_SCALE_Merged/faster_rcnn_alt_opt/stage2_rpn_train.pt", "content": "name: \"ResNet50_BN_SCALE_Merged\"\n\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4f\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RCNN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"dummy_roi_pool_res4f\"\n type: \"DummyData\"\n top: \"dummy_roi_pool_res4f\"\n dummy_data_param {\n shape { dim: 1 dim: 1024 dim: 14 dim: 14 }\n data_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"dummy_roi_pool_res4f\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"dummy_roi_pool_res4f\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\nlayer {\n name: \"silence_pool5\"\n type: \"Silence\"\n bottom: \"pool5\"\n}\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_BN_SCALE_Merged/faster_rcnn_end2end/solver.prototxt", "content": "train_net: \"models/pascal_voc/ResNet-50/faster_rcnn_BN_SCALE_Merged/faster_rcnn_end2end/train.prototxt\"\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 50000\ndisplay: 20\naverage_loss: 100\n# iter_size: 1\nmomentum: 0.9\nweight_decay: 0.0005\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet101_faster_rcnn_bn_scale_merged_end2end\"\niter_size: 2\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_BN_SCALE_Merged/faster_rcnn_end2end/test.prototxt", "content": "name: \"ResNet50_BN_SCALE_Merged\"\n\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4f\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\n\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rpn_rois'\n# top: 'rpn_scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n#layer {\n# name: 'debug-data'\n# type: 'Python'\n# bottom: 'data'\n# bottom: 'rpn_rois'\n# bottom: 'rpn_scores'\n# python_param {\n# module: 'rpn.debug_layer'\n# layer: 'RPNDebugLayer'\n# }\n#}\n\nlayer {\n name: 'roi-data'\n type: 'Python'\n bottom: 'rpn_rois'\n bottom: 'gt_boxes'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'rpn.proposal_target_layer'\n layer: 'ProposalTargetLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n#========= RCNN ============\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"res4f\"\n bottom: \"rois\"\n top: \"roi_pool5\"\n roi_pooling_param {\n pooled_w: 14\n pooled_h: 14\n spatial_scale: 0.0625 # 1/16\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"pool5\"\n name: \"pool5\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 7\n stride: 1\n pool: AVE\n }\n}\n\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\n\nlayer {\n name: \"cls_prob\"\n type: \"Softmax\"\n bottom: \"cls_score\"\n top: \"cls_prob\"\n}\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_BN_SCALE_Merged/faster_rcnn_end2end/train.prototxt", "content": "name: \"ResNet50_BN_SCALE_Merged\"\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4f\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\n\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rpn_rois'\n# top: 'rpn_scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n#layer {\n# name: 'debug-data'\n# type: 'Python'\n# bottom: 'data'\n# bottom: 'rpn_rois'\n# bottom: 'rpn_scores'\n# python_param {\n# module: 'rpn.debug_layer'\n# layer: 'RPNDebugLayer'\n# }\n#}\n\nlayer {\n name: 'roi-data'\n type: 'Python'\n bottom: 'rpn_rois'\n bottom: 'gt_boxes'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'rpn.proposal_target_layer'\n layer: 'ProposalTargetLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n#========= RCNN ============\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"res4f\"\n bottom: \"rois\"\n top: \"roi_pool5\"\n roi_pooling_param {\n pooled_w: 14\n pooled_h: 14\n spatial_scale: 0.0625 # 1/16\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\n\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"loss_bbox\"\n loss_weight: 1\n}" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_BN_SCALE_Merged_OHEM/faster_rcnn_end2end/solver.prototxt", "content": "train_net: \"models/pascal_voc/ResNet-50/faster_rcnn_BN_SCALE_Merged_OHEM/faster_rcnn_end2end/train.prototxt\"\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 50000\ndisplay: 20\naverage_loss: 100\niter_size: 2\nmomentum: 0.9\nweight_decay: 0.0005\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet101_faster_rcnn_bn_scale_merged_end2end_ohem\"\n#debug_info: true\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_BN_SCALE_Merged_OHEM/faster_rcnn_end2end/test.prototxt", "content": "name: \"ResNet-50\"\n\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4f\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\n\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rpn_rois'\n# top: 'rpn_scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n#layer {\n# name: 'debug-data'\n# type: 'Python'\n# bottom: 'data'\n# bottom: 'rpn_rois'\n# bottom: 'rpn_scores'\n# python_param {\n# module: 'rpn.debug_layer'\n# layer: 'RPNDebugLayer'\n# }\n#}\n\nlayer {\n name: 'roi-data'\n type: 'Python'\n bottom: 'rpn_rois'\n bottom: 'gt_boxes'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'rpn.proposal_target_layer'\n layer: 'ProposalTargetLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n\n##########################\n## Readonly RoI Network ##\n######### Start ##########\nlayer {\n name: \"roi_pool5_readonly\"\n type: \"ROIPooling\"\n bottom: \"res4f\"\n bottom: \"rois\"\n top: \"roi_pool5_readonly\"\n propagate_down: false\n propagate_down: false\n roi_pooling_param {\n pooled_w: 14\n pooled_h: 14\n spatial_scale: 0.0625 # 1/16\n }\n}\n\nlayer {\n bottom: \"roi_pool5_readonly\"\n top: \"res5a_branch1_readonly\"\n name: \"res5a_branch1_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n name: \"res5a_branch1_w\"\n }\n}\n\nlayer {\n bottom: \"res5a_branch1_readonly\"\n top: \"res5a_branch1_readonly\"\n name: \"scale5a_branch1_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch1_w\"\n }\n param {\n name: \"scale5a_branch1_b\"\n }\n}\n\nlayer {\n bottom: \"roi_pool5_readonly\"\n top: \"res5a_branch2a_readonly\"\n name: \"res5a_branch2a_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n name: \"res5a_branch2a_w\"\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a_readonly\"\n top: \"res5a_branch2a_readonly\"\n name: \"scale5a_branch2a_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch2a_w\"\n }\n param {\n name: \"scale5a_branch2a_b\"\n }\n}\n\nlayer {\n top: \"res5a_branch2a_readonly\"\n bottom: \"res5a_branch2a_readonly\"\n name: \"res5a_branch2a_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a_readonly\"\n top: \"res5a_branch2b_readonly\"\n name: \"res5a_branch2b_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5a_branch2b_w\"\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2b_readonly\"\n top: \"res5a_branch2b_readonly\"\n name: \"scale5a_branch2b_readonly\"\n type: \"Scale\"\n propagate_down: false\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch2b_w\"\n }\n param {\n name: \"scale5a_branch2b_b\"\n }\n}\n\nlayer {\n top: \"res5a_branch2b_readonly\"\n bottom: \"res5a_branch2b_readonly\"\n name: \"res5a_branch2b_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b_readonly\"\n top: \"res5a_branch2c_readonly\"\n name: \"res5a_branch2c_readonly\"\n type: \"Convolution\"\n propagate_down: false\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5a_branch2c_w\"\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2c_readonly\"\n top: \"res5a_branch2c_readonly\"\n name: \"scale5a_branch2c_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch2c_w\"\n }\n param {\n name: \"scale5a_branch2c_b\"\n }\n}\n\nlayer {\n bottom: \"res5a_branch1_readonly\"\n bottom: \"res5a_branch2c_readonly\"\n top: \"res5a_readonly\"\n name: \"res5a_readonly\"\n propagate_down: false\n propagate_down: false\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a_readonly\"\n top: \"res5a_readonly\"\n name: \"res5a_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_readonly\"\n top: \"res5b_branch2a_readonly\"\n name: \"res5b_branch2a_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5b_branch2a_w\"\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2a_readonly\"\n top: \"res5b_branch2a_readonly\"\n name: \"scale5b_branch2a_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5b_branch2a_w\"\n }\n param {\n name: \"scale5b_branch2a_b\"\n }\n}\n\nlayer {\n top: \"res5b_branch2a_readonly\"\n bottom: \"res5b_branch2a_readonly\"\n name: \"res5b_branch2a_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a_readonly\"\n top: \"res5b_branch2b_readonly\"\n name: \"res5b_branch2b_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5b_branch2b_w\"\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2b_readonly\"\n top: \"res5b_branch2b_readonly\"\n name: \"scale5b_branch2b_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5b_branch2b_w\"\n }\n param {\n name: \"scale5b_branch2b_b\"\n }\n}\n\nlayer {\n top: \"res5b_branch2b_readonly\"\n bottom: \"res5b_branch2b_readonly\"\n name: \"res5b_branch2b_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b_readonly\"\n top: \"res5b_branch2c_readonly\"\n name: \"res5b_branch2c_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5b_branch2c_w\"\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c_readonly\"\n top: \"res5b_branch2c_readonly\"\n name: \"scale5b_branch2c_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5b_branch2c_w\"\n }\n param {\n name: \"scale5b_branch2c_b\"\n }\n}\n\nlayer {\n bottom: \"res5a_readonly\"\n bottom: \"res5b_branch2c_readonly\"\n top: \"res5b_readonly\"\n name: \"res5b_readonly\"\n propagate_down: false\n propagate_down: false\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b_readonly\"\n top: \"res5b_readonly\"\n name: \"res5b_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_readonly\"\n top: \"res5c_branch2a_readonly\"\n name: \"res5c_branch2a_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5c_branch2a_w\"\n }\n}\n\n\nlayer {\n bottom: \"res5c_branch2a_readonly\"\n top: \"res5c_branch2a_readonly\"\n name: \"scale5c_branch2a_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5c_branch2a_w\"\n }\n param {\n name: \"scale5c_branch2a_b\"\n }\n}\n\nlayer {\n top: \"res5c_branch2a_readonly\"\n bottom: \"res5c_branch2a_readonly\"\n name: \"res5c_branch2a_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a_readonly\"\n top: \"res5c_branch2b_readonly\"\n name: \"res5c_branch2b_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5c_branch2b_w\"\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b_readonly\"\n top: \"res5c_branch2b_readonly\"\n name: \"scale5c_branch2b_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5c_branch2b_w\"\n }\n param {\n name: \"scale5c_branch2b_b\"\n }\n}\n\nlayer {\n top: \"res5c_branch2b_readonly\"\n bottom: \"res5c_branch2b_readonly\"\n name: \"res5c_branch2b_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b_readonly\"\n top: \"res5c_branch2c_readonly\"\n name: \"res5c_branch2c_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5c_branch2c_w\"\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c_readonly\"\n top: \"res5c_branch2c_readonly\"\n name: \"scale5c_branch2c_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5c_branch2c_w\"\n }\n param {\n name: \"scale5c_branch2c_b\"\n }\n}\n\nlayer {\n bottom: \"res5b_readonly\"\n bottom: \"res5c_branch2c_readonly\"\n propagate_down: false\n propagate_down: false\n top: \"res5c_readonly\"\n name: \"res5c_readonly\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c_readonly\"\n top: \"res5c_readonly\"\n propagate_down: false\n name: \"res5c_relu_readonly\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_readonly\"\n top: \"pool5_readonly\"\n name: \"pool5_readonly\"\n type: \"Pooling\"\n propagate_down: false\n pooling_param {\n kernel_size: 7\n stride: 1\n pool: AVE\n }\n}\n\nlayer {\n name: \"cls_score_readonly\"\n type: \"InnerProduct\"\n bottom: \"pool5_readonly\"\n top: \"cls_score_readonly\"\n propagate_down: false\n param {\n name: \"cls_score_w\"\n }\n param {\n name: \"cls_score_b\"\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred_readonly\"\n type: \"InnerProduct\"\n bottom: \"pool5_readonly\"\n top: \"bbox_pred_readonly\"\n propagate_down: false\n param {\n name: \"bbox_pred_w\"\n }\n param {\n name: \"bbox_pred_b\"\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"cls_prob_readonly\"\n type: \"Softmax\"\n bottom: \"cls_score_readonly\"\n top: \"cls_prob_readonly\"\n propagate_down: false\n}\nlayer {\n name: \"hard_roi_mining\"\n type: \"Python\"\n bottom: \"cls_prob_readonly\"\n bottom: \"bbox_pred_readonly\"\n bottom: \"rois\"\n bottom: \"labels\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"rois_hard\"\n top: \"labels_hard\"\n top: \"bbox_targets_hard\"\n top: \"bbox_inside_weights_hard\"\n top: \"bbox_outside_weights_hard\"\n propagate_down: false\n propagate_down: false\n propagate_down: false\n propagate_down: false\n propagate_down: false\n propagate_down: false\n propagate_down: false\n python_param {\n module: \"roi_data_layer.layer\"\n layer: \"OHEMDataLayer\"\n param_str: \"'num_classes': 21\"\n }\n}\n########## End ###########\n## Readonly RoI Network ##\n##########################\n\n\n#========= RCNN ============\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"res4f\"\n bottom: \"rois_hard\"\n top: \"roi_pool5\"\n propagate_down: true\n propagate_down: false\n roi_pooling_param {\n pooled_w: 14\n pooled_h: 14\n spatial_scale: 0.0625 # 1/16\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n name: \"res5a_branch1_w\"\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch1_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5a_branch1_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n name: \"res5a_branch2a_w\"\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch2a_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5a_branch2a_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5a_branch2b_w\"\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch2b_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5a_branch2b_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5a_branch2c_w\"\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch2c_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5a_branch2c_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5b_branch2a_w\"\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5b_branch2a_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5b_branch2a_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5b_branch2b_w\"\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5b_branch2b_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5b_branch2b_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5b_branch2c_w\"\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5b_branch2c_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5b_branch2c_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5c_branch2a_w\"\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5c_branch2a_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5c_branch2a_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5c_branch2b_w\"\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5c_branch2b_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5c_branch2b_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5c_branch2c_w\"\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5c_branch2c_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5c_branch2c_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"pool5\"\n name: \"pool5\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 7\n stride: 1\n pool: AVE\n }\n}\n\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"cls_score\"\n param {\n name: \"cls_score_w\"\n lr_mult: 1\n }\n param {\n name: \"cls_score_b\"\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"bbox_pred\"\n param {\n name: \"bbox_pred_w\"\n lr_mult: 1\n }\n param {\n name: \"bbox_pred_b\"\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\n\nlayer {\n name: \"cls_prob\"\n type: \"Softmax\"\n bottom: \"cls_score\"\n top: \"cls_prob\"\n}" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_BN_SCALE_Merged_OHEM/faster_rcnn_end2end/train.prototxt", "content": "name: \"ResNet-50\"\n\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4f\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\n\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rpn_rois'\n# top: 'rpn_scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n#layer {\n# name: 'debug-data'\n# type: 'Python'\n# bottom: 'data'\n# bottom: 'rpn_rois'\n# bottom: 'rpn_scores'\n# python_param {\n# module: 'rpn.debug_layer'\n# layer: 'RPNDebugLayer'\n# }\n#}\n\nlayer {\n name: 'roi-data'\n type: 'Python'\n bottom: 'rpn_rois'\n bottom: 'gt_boxes'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'rpn.proposal_target_layer'\n layer: 'ProposalTargetLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n\n##########################\n## Readonly RoI Network ##\n######### Start ##########\nlayer {\n name: \"roi_pool5_readonly\"\n type: \"ROIPooling\"\n bottom: \"res4f\"\n bottom: \"rois\"\n top: \"roi_pool5_readonly\"\n propagate_down: false\n propagate_down: false\n roi_pooling_param {\n pooled_w: 14\n pooled_h: 14\n spatial_scale: 0.0625 # 1/16\n }\n}\n\nlayer {\n bottom: \"roi_pool5_readonly\"\n top: \"res5a_branch1_readonly\"\n name: \"res5a_branch1_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n name: \"res5a_branch1_w\"\n }\n}\n\nlayer {\n bottom: \"res5a_branch1_readonly\"\n top: \"res5a_branch1_readonly\"\n name: \"scale5a_branch1_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch1_w\"\n }\n param {\n name: \"scale5a_branch1_b\"\n }\n}\n\nlayer {\n bottom: \"roi_pool5_readonly\"\n top: \"res5a_branch2a_readonly\"\n name: \"res5a_branch2a_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n name: \"res5a_branch2a_w\"\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a_readonly\"\n top: \"res5a_branch2a_readonly\"\n name: \"scale5a_branch2a_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch2a_w\"\n }\n param {\n name: \"scale5a_branch2a_b\"\n }\n}\n\nlayer {\n top: \"res5a_branch2a_readonly\"\n bottom: \"res5a_branch2a_readonly\"\n name: \"res5a_branch2a_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a_readonly\"\n top: \"res5a_branch2b_readonly\"\n name: \"res5a_branch2b_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5a_branch2b_w\"\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2b_readonly\"\n top: \"res5a_branch2b_readonly\"\n name: \"scale5a_branch2b_readonly\"\n type: \"Scale\"\n propagate_down: false\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch2b_w\"\n }\n param {\n name: \"scale5a_branch2b_b\"\n }\n}\n\nlayer {\n top: \"res5a_branch2b_readonly\"\n bottom: \"res5a_branch2b_readonly\"\n name: \"res5a_branch2b_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b_readonly\"\n top: \"res5a_branch2c_readonly\"\n name: \"res5a_branch2c_readonly\"\n type: \"Convolution\"\n propagate_down: false\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5a_branch2c_w\"\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2c_readonly\"\n top: \"res5a_branch2c_readonly\"\n name: \"scale5a_branch2c_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch2c_w\"\n }\n param {\n name: \"scale5a_branch2c_b\"\n }\n}\n\nlayer {\n bottom: \"res5a_branch1_readonly\"\n bottom: \"res5a_branch2c_readonly\"\n top: \"res5a_readonly\"\n name: \"res5a_readonly\"\n propagate_down: false\n propagate_down: false\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a_readonly\"\n top: \"res5a_readonly\"\n name: \"res5a_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_readonly\"\n top: \"res5b_branch2a_readonly\"\n name: \"res5b_branch2a_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5b_branch2a_w\"\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2a_readonly\"\n top: \"res5b_branch2a_readonly\"\n name: \"scale5b_branch2a_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5b_branch2a_w\"\n }\n param {\n name: \"scale5b_branch2a_b\"\n }\n}\n\nlayer {\n top: \"res5b_branch2a_readonly\"\n bottom: \"res5b_branch2a_readonly\"\n name: \"res5b_branch2a_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a_readonly\"\n top: \"res5b_branch2b_readonly\"\n name: \"res5b_branch2b_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5b_branch2b_w\"\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2b_readonly\"\n top: \"res5b_branch2b_readonly\"\n name: \"scale5b_branch2b_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5b_branch2b_w\"\n }\n param {\n name: \"scale5b_branch2b_b\"\n }\n}\n\nlayer {\n top: \"res5b_branch2b_readonly\"\n bottom: \"res5b_branch2b_readonly\"\n name: \"res5b_branch2b_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b_readonly\"\n top: \"res5b_branch2c_readonly\"\n name: \"res5b_branch2c_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5b_branch2c_w\"\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c_readonly\"\n top: \"res5b_branch2c_readonly\"\n name: \"scale5b_branch2c_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5b_branch2c_w\"\n }\n param {\n name: \"scale5b_branch2c_b\"\n }\n}\n\nlayer {\n bottom: \"res5a_readonly\"\n bottom: \"res5b_branch2c_readonly\"\n top: \"res5b_readonly\"\n name: \"res5b_readonly\"\n propagate_down: false\n propagate_down: false\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b_readonly\"\n top: \"res5b_readonly\"\n name: \"res5b_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_readonly\"\n top: \"res5c_branch2a_readonly\"\n name: \"res5c_branch2a_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5c_branch2a_w\"\n }\n}\n\n\nlayer {\n bottom: \"res5c_branch2a_readonly\"\n top: \"res5c_branch2a_readonly\"\n name: \"scale5c_branch2a_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5c_branch2a_w\"\n }\n param {\n name: \"scale5c_branch2a_b\"\n }\n}\n\nlayer {\n top: \"res5c_branch2a_readonly\"\n bottom: \"res5c_branch2a_readonly\"\n name: \"res5c_branch2a_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a_readonly\"\n top: \"res5c_branch2b_readonly\"\n name: \"res5c_branch2b_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5c_branch2b_w\"\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b_readonly\"\n top: \"res5c_branch2b_readonly\"\n name: \"scale5c_branch2b_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5c_branch2b_w\"\n }\n param {\n name: \"scale5c_branch2b_b\"\n }\n}\n\nlayer {\n top: \"res5c_branch2b_readonly\"\n bottom: \"res5c_branch2b_readonly\"\n name: \"res5c_branch2b_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b_readonly\"\n top: \"res5c_branch2c_readonly\"\n name: \"res5c_branch2c_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5c_branch2c_w\"\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c_readonly\"\n top: \"res5c_branch2c_readonly\"\n name: \"scale5c_branch2c_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5c_branch2c_w\"\n }\n param {\n name: \"scale5c_branch2c_b\"\n }\n}\n\nlayer {\n bottom: \"res5b_readonly\"\n bottom: \"res5c_branch2c_readonly\"\n propagate_down: false\n propagate_down: false\n top: \"res5c_readonly\"\n name: \"res5c_readonly\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c_readonly\"\n top: \"res5c_readonly\"\n propagate_down: false\n name: \"res5c_relu_readonly\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_readonly\"\n top: \"pool5_readonly\"\n name: \"pool5_readonly\"\n type: \"Pooling\"\n propagate_down: false\n pooling_param {\n kernel_size: 7\n stride: 1\n pool: AVE\n }\n}\n\nlayer {\n name: \"cls_score_readonly\"\n type: \"InnerProduct\"\n bottom: \"pool5_readonly\"\n top: \"cls_score_readonly\"\n propagate_down: false\n param {\n name: \"cls_score_w\"\n }\n param {\n name: \"cls_score_b\"\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred_readonly\"\n type: \"InnerProduct\"\n bottom: \"pool5_readonly\"\n top: \"bbox_pred_readonly\"\n propagate_down: false\n param {\n name: \"bbox_pred_w\"\n }\n param {\n name: \"bbox_pred_b\"\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"cls_prob_readonly\"\n type: \"Softmax\"\n bottom: \"cls_score_readonly\"\n top: \"cls_prob_readonly\"\n propagate_down: false\n}\nlayer {\n name: \"hard_roi_mining\"\n type: \"Python\"\n bottom: \"cls_prob_readonly\"\n bottom: \"bbox_pred_readonly\"\n bottom: \"rois\"\n bottom: \"labels\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"rois_hard\"\n top: \"labels_hard\"\n top: \"bbox_targets_hard\"\n top: \"bbox_inside_weights_hard\"\n top: \"bbox_outside_weights_hard\"\n propagate_down: false\n propagate_down: false\n propagate_down: false\n propagate_down: false\n propagate_down: false\n propagate_down: false\n propagate_down: false\n python_param {\n module: \"roi_data_layer.layer\"\n layer: \"OHEMDataLayer\"\n param_str: \"'num_classes': 21\"\n }\n}\n########## End ###########\n## Readonly RoI Network ##\n##########################\n\n\n#========= RCNN ============\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"res4f\"\n bottom: \"rois_hard\"\n top: \"roi_pool5\"\n propagate_down: true\n propagate_down: false\n roi_pooling_param {\n pooled_w: 14\n pooled_h: 14\n spatial_scale: 0.0625 # 1/16\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n name: \"res5a_branch1_w\"\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch1_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5a_branch1_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n name: \"res5a_branch2a_w\"\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch2a_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5a_branch2a_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5a_branch2b_w\"\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch2b_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5a_branch2b_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5a_branch2c_w\"\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch2c_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5a_branch2c_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5b_branch2a_w\"\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5b_branch2a_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5b_branch2a_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5b_branch2b_w\"\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5b_branch2b_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5b_branch2b_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5b_branch2c_w\"\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5b_branch2c_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5b_branch2c_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5c_branch2a_w\"\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5c_branch2a_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5c_branch2a_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5c_branch2b_w\"\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5c_branch2b_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5c_branch2b_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5c_branch2c_w\"\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5c_branch2c_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5c_branch2c_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"pool5\"\n name: \"pool5\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 7\n stride: 1\n pool: AVE\n }\n}\n\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"cls_score\"\n param {\n name: \"cls_score_w\"\n lr_mult: 1\n }\n param {\n name: \"cls_score_b\"\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"bbox_pred\"\n param {\n name: \"bbox_pred_w\"\n lr_mult: 1\n }\n param {\n name: \"bbox_pred_b\"\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\n\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels_hard\"\n propagate_down: 1\n propagate_down: 0\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets_hard\"\n bottom: \"bbox_inside_weights_hard\"\n bottom: \"bbox_outside_weights_hard\"\n top: \"loss_bbox\"\n propagate_down: true\n propagate_down: false\n propagate_down: false\n propagate_down: false\n loss_weight: 1\n}\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_alt_opt/faster_rcnn_test.pt", "content": "name: \"ResNet50\"\n\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\n\ninput: \"im_info\"\ninput_shape {\n dim: 1\n dim: 3\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4f\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rois'\n top: 'scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n\n#========= RCNN ============\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"res4f\"\n bottom: \"rois\"\n top: \"roi_pool5\"\n roi_pooling_param {\n pooled_w: 14\n pooled_h: 14\n spatial_scale: 0.0625 # 1/16\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"bn5a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"bn5a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"bn5a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"bn5a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"bn5b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"bn5b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"bn5b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"bn5c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"bn5c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"bn5c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\n\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\n\nlayer {\n name: \"cls_prob\"\n type: \"Softmax\"\n bottom: \"cls_score\"\n top: \"cls_prob\"\n}\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_alt_opt/rpn_test.pt", "content": "name: \"ResNet50\"\n\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\n\ninput: \"im_info\"\ninput_shape {\n dim: 1\n dim: 3\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4f\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rois'\n top: 'scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_alt_opt/stage1_fast_rcnn_solver30k40k.pt", "content": "train_net: \"models/pascal_voc/ResNet101/faster_rcnn_alt_opt/stage1_fast_rcnn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 30000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet101_fast_rcnn\"\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_alt_opt/stage1_fast_rcnn_train.pt", "content": "name: \"ResNet50\"\nlayer {\n name: 'data'\n type: 'Python'\n top: 'data'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"res4f\"\n bottom: \"rois\"\n top: \"roi_pool5\"\n roi_pooling_param {\n pooled_w: 14\n pooled_h: 14\n spatial_scale: 0.0625 # 1/16\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"bn5a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"bn5a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"bn5a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"bn5a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"bn5b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"bn5b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"bn5b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"bn5c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"bn5c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"bn5c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\n\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"loss_bbox\"\n loss_weight: 1\n}\n\n\n#========= RPN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4f\"\n top: \"rpn/output\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"silence_rpn_cls_score\"\n type: \"Silence\"\n bottom: \"rpn_cls_score\"\n}\nlayer {\n name: \"silence_rpn_bbox_pred\"\n type: \"Silence\"\n bottom: \"rpn_bbox_pred\"\n}\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_alt_opt/stage1_rpn_solver60k80k.pt", "content": "train_net: \"models/pascal_voc/ResNet101/faster_rcnn_alt_opt/stage1_rpn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 60000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet101_rpn\"\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_alt_opt/stage1_rpn_train.pt", "content": "name: \"ResNet50\"\n\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4f\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RCNN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"dummy_roi_pool_res4f\"\n type: \"DummyData\"\n top: \"dummy_roi_pool_res4f\"\n dummy_data_param {\n shape { dim: 1 dim: 1024 dim: 14 dim: 14 }\n data_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"dummy_roi_pool_res4f\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"bn5a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"dummy_roi_pool_res4f\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"bn5a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"bn5a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"bn5a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"bn5b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"bn5b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"bn5b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"bn5c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"bn5c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"bn5c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\nlayer {\n name: \"silence_pool5\"\n type: \"Silence\"\n bottom: \"pool5\"\n}\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_alt_opt/stage2_fast_rcnn_solver30k40k.pt", "content": "train_net: \"models/pascal_voc/ResNet101/faster_rcnn_alt_opt/stage2_fast_rcnn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 30000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet101_fast_rcnn\"\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_alt_opt/stage2_fast_rcnn_train.pt", "content": "name: \"ResNet50\"\nlayer {\n name: 'data'\n type: 'Python'\n top: 'data'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"res4f\"\n bottom: \"rois\"\n top: \"roi_pool5\"\n roi_pooling_param {\n pooled_w: 14\n pooled_h: 14\n spatial_scale: 0.0625 # 1/16\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"bn5a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"bn5a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"bn5a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"bn5a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"bn5b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"bn5b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"bn5b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"bn5c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"bn5c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"bn5c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\n\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"loss_bbox\"\n loss_weight: 1\n}\n\n\n#========= RPN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4f\"\n top: \"rpn/output\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"silence_rpn_cls_score\"\n type: \"Silence\"\n bottom: \"rpn_cls_score\"\n}\nlayer {\n name: \"silence_rpn_bbox_pred\"\n type: \"Silence\"\n bottom: \"rpn_bbox_pred\"\n}\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_alt_opt/stage2_rpn_solver60k80k.pt", "content": "train_net: \"models/pascal_voc/ResNet101/faster_rcnn_alt_opt/stage2_rpn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 60000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet101_rpn\"\n" }, { "path": "models/pascal_voc/ResNet-50/faster_rcnn_alt_opt/stage2_rpn_train.pt", "content": "name: \"ResNet50\"\n\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4f\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RCNN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"dummy_roi_pool_res4f\"\n type: \"DummyData\"\n top: \"dummy_roi_pool_res4f\"\n dummy_data_param {\n shape { dim: 1 dim: 1024 dim: 14 dim: 14 }\n data_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"dummy_roi_pool_res4f\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"bn5a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"dummy_roi_pool_res4f\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"bn5a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"bn5a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"bn5a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"bn5b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"bn5b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"bn5b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"bn5c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"bn5c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"bn5c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\nlayer {\n name: \"silence_pool5\"\n type: \"Silence\"\n bottom: \"pool5\"\n}\n" }, { "path": "models/pascal_voc/ResNet-50/rfcn_alt_opt_5step_ohem/rfcn_test.pt", "content": "name: \"ResNet-50\"\n\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\n\ninput: \"rois\"\ninput_shape {\n dim: 1 # to be changed on-the-fly to num ROIs\n dim: 5 # [batch ind, x1, y1, x2, y2] zero-based indexing\n}\n\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"bn5a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"bn5a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"bn5a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"bn5a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"bn5b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"bn5b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"bn5b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"bn5c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"bn5c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"bn5c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\n#----------------------new conv layer------------------\nlayer {\n bottom: \"res5c\"\n top: \"conv_new_1\"\n name: \"conv_new_1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\n\nlayer {\n bottom: \"conv_new_1\"\n top: \"conv_new_1\"\n name: \"conv_new_1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv_new_1\"\n top: \"rfcn_cls\"\n name: \"rfcn_cls\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1029 #21*(7^2) cls_num*(score_maps_size^2)\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\nlayer {\n bottom: \"conv_new_1\"\n top: \"rfcn_bbox\"\n name: \"rfcn_bbox\"\n type: \"Convolution\"\n convolution_param {\n num_output: 392 #8*(7^2) cls_num*(score_maps_size^2)\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\n\n#--------------position sensitive RoI pooling--------------\nlayer {\n bottom: \"rfcn_cls\"\n bottom: \"rois\"\n top: \"psroipooled_cls_rois\"\n name: \"psroipooled_cls_rois\"\n type: \"PSROIPooling\"\n psroi_pooling_param {\n spatial_scale: 0.0625\n output_dim: 21\n group_size: 7\n }\n}\n\nlayer {\n bottom: \"psroipooled_cls_rois\"\n top: \"cls_score\"\n name: \"ave_cls_score_rois\"\n type: \"Pooling\"\n pooling_param {\n pool: AVE\n kernel_size: 7\n stride: 7\n }\n}\n\n\nlayer {\n bottom: \"rfcn_bbox\"\n bottom: \"rois\"\n top: \"psroipooled_loc_rois\"\n name: \"psroipooled_loc_rois\"\n type: \"PSROIPooling\"\n psroi_pooling_param {\n spatial_scale: 0.0625\n output_dim: 8\n group_size: 7\n }\n}\n\nlayer {\n bottom: \"psroipooled_loc_rois\"\n top: \"bbox_pred_pre\"\n name: \"ave_bbox_pred_rois\"\n type: \"Pooling\"\n pooling_param {\n pool: AVE\n kernel_size: 7\n stride: 7\n }\n}\n\n\n#-----------------------output------------------------\nlayer {\n name: \"cls_prob\"\n type: \"Softmax\"\n bottom: \"cls_score\"\n top: \"cls_prob_pre\"\n}\n\nlayer {\n name: \"cls_prob_reshape\"\n type: \"Reshape\"\n bottom: \"cls_prob_pre\"\n top: \"cls_prob\"\n reshape_param {\n shape {\n dim: -1\n dim: 21\n }\n }\n}\n\nlayer {\n name: \"bbox_pred_reshape\"\n type: \"Reshape\"\n bottom: \"bbox_pred_pre\"\n top: \"bbox_pred\"\n reshape_param {\n shape {\n dim: -1\n dim: 8\n }\n }\n}\n\n\n" }, { "path": "models/pascal_voc/ResNet-50/rfcn_alt_opt_5step_ohem/rpn_test.pt", "content": "name: \"ZF\"\n\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\n\ninput: \"im_info\"\ninput_shape {\n dim: 1\n dim: 3\n}\n\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\n#-----------------------layer +-------------------------\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4f\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\n#-----------------------output------------------------\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rois'\n top: 'scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n" }, { "path": "models/pascal_voc/ResNet-50/rfcn_alt_opt_5step_ohem/stage1_rfcn_ohem_solver80k120k.pt", "content": "train_net: \"models/pascal_voc/ResNet-50/rfcn_alt_opt_5step_ohem/stage1_rfcn_ohem_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 80000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet50_rfcn_ohem\"\niter_size: 2\n" }, { "path": "models/pascal_voc/ResNet-50/rfcn_alt_opt_5step_ohem/stage1_rfcn_ohem_train.pt", "content": "name: \"ResNet-50\"\nlayer {\n name: 'data'\n type: 'Python'\n top: 'data'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"bn5a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"bn5a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"bn5a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"bn5a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"bn5b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"bn5b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"bn5b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"bn5c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"bn5c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"bn5c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\n#----------------------new conv layer------------------\nlayer {\n bottom: \"res5c\"\n top: \"conv_new_1\"\n name: \"conv_new_1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\n\nlayer {\n bottom: \"conv_new_1\"\n top: \"conv_new_1\"\n name: \"conv_new_1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv_new_1\"\n top: \"rfcn_cls\"\n name: \"rfcn_cls\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1029 #21*(7^2) cls_num*(score_maps_size^2)\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\nlayer {\n bottom: \"conv_new_1\"\n top: \"rfcn_bbox\"\n name: \"rfcn_bbox\"\n type: \"Convolution\"\n convolution_param {\n num_output: 392 #8*(7^2) cls_num*(score_maps_size^2)\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\n\n#--------------position sensitive RoI pooling--------------\nlayer {\n bottom: \"rfcn_cls\"\n bottom: \"rois\"\n top: \"psroipooled_cls_rois\"\n name: \"psroipooled_cls_rois\"\n type: \"PSROIPooling\"\n psroi_pooling_param {\n spatial_scale: 0.0625\n output_dim: 21\n group_size: 7\n }\n}\n\nlayer {\n bottom: \"psroipooled_cls_rois\"\n top: \"cls_score\"\n name: \"ave_cls_score_rois\"\n type: \"Pooling\"\n pooling_param {\n pool: AVE\n kernel_size: 7\n stride: 7\n }\n}\n\n\nlayer {\n bottom: \"rfcn_bbox\"\n bottom: \"rois\"\n top: \"psroipooled_loc_rois\"\n name: \"psroipooled_loc_rois\"\n type: \"PSROIPooling\"\n psroi_pooling_param {\n spatial_scale: 0.0625\n output_dim: 8\n group_size: 7\n }\n}\n\nlayer {\n bottom: \"psroipooled_loc_rois\"\n top: \"bbox_pred\"\n name: \"ave_bbox_pred_rois\"\n type: \"Pooling\"\n pooling_param {\n pool: AVE\n kernel_size: 7\n stride: 7\n }\n}\n\n\n#--------------online hard example mining--------------\nlayer {\n name: \"per_roi_loss_cls\"\n type: \"SoftmaxWithLossOHEM\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n top: \"temp_loss_cls\"\n top: \"temp_prob_cls\"\n top: \"per_roi_loss_cls\"\n loss_weight: 0\n loss_weight: 0\n loss_weight: 0\n propagate_down: false\n propagate_down: false\n}\n\nlayer {\n name: \"per_roi_loss_bbox\"\n type: \"SmoothL1LossOHEM\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n top: \"temp_loss_bbox\"\n top: \"per_roi_loss_bbox\"\n loss_weight: 0\n loss_weight: 0\n propagate_down: false\n propagate_down: false\n propagate_down: false\n}\n\nlayer {\n name: \"per_roi_loss\"\n type: \"Eltwise\"\n bottom: \"per_roi_loss_cls\"\n bottom: \"per_roi_loss_bbox\"\n top: \"per_roi_loss\"\n propagate_down: false\n propagate_down: false\n}\n\nlayer {\n bottom: \"rois\"\n bottom: \"per_roi_loss\"\n bottom: \"labels\"\n bottom: \"bbox_inside_weights\"\n top: \"labels_ohem\"\n top: \"bbox_loss_weights_ohem\"\n name: \"annotator_detector\"\n type: \"BoxAnnotatorOHEM\"\n box_annotator_ohem_param {\n roi_per_img: 128\n ignore_label: -1\n }\n propagate_down: false\n propagate_down: false\n propagate_down: false\n propagate_down: false\n}\n\nlayer {\n name: \"silence\"\n type: \"Silence\"\n bottom: \"bbox_outside_weights\"\n bottom: \"temp_loss_cls\"\n bottom: \"temp_prob_cls\"\n bottom: \"temp_loss_bbox\"\n}\n\n#-----------------------output------------------------\nlayer {\n name: \"loss\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels_ohem\"\n top: \"loss_cls\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n }\n propagate_down: true\n propagate_down: false\n}\n\nlayer {\n name: \"accuarcy\"\n type: \"Accuracy\"\n bottom: \"cls_score\"\n bottom: \"labels_ohem\"\n top: \"accuarcy\"\n #include: { phase: TEST }\n accuracy_param {\n ignore_label: -1\n }\n propagate_down: false\n propagate_down: false\n}\n\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1LossOHEM\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_loss_weights_ohem\"\n top: \"loss_bbox\"\n loss_weight: 1\n loss_param {\n normalization: PRE_FIXED\n pre_fixed_normalizer: 128\n }\n propagate_down: true\n propagate_down: false\n propagate_down: false\n}\n" }, { "path": "models/pascal_voc/ResNet-50/rfcn_alt_opt_5step_ohem/stage1_rpn_solver60k80k.pt", "content": "train_net: \"models/pascal_voc/ResNet-50/rfcn_alt_opt_5step_ohem/stage1_rpn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 60000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet50_rpn\"\n" }, { "path": "models/pascal_voc/ResNet-50/rfcn_alt_opt_5step_ohem/stage1_rpn_train.pt", "content": "name: \"ResNet-50\"\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4f\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: \"rpn_bbox_inside_weights\"\n bottom: \"rpn_bbox_outside_weights\"\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n" }, { "path": "models/pascal_voc/ResNet-50/rfcn_alt_opt_5step_ohem/stage2_rfcn_ohem_solver80k120k.pt", "content": "train_net: \"models/pascal_voc/ResNet-50/rfcn_alt_opt_5step_ohem/stage2_rfcn_ohem_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 80000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet50_rfcn_ohem\"\niter_size: 2\n" }, { "path": "models/pascal_voc/ResNet-50/rfcn_alt_opt_5step_ohem/stage2_rfcn_ohem_train.pt", "content": "name: \"ResNet-50\"\nlayer {\n name: 'data'\n type: 'Python'\n top: 'data'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"bn5a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"bn5a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"bn5a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"bn5a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"bn5b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"bn5b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"bn5b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"bn5c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"bn5c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"bn5c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\n#----------------------new conv layer------------------\nlayer {\n bottom: \"res5c\"\n top: \"conv_new_1\"\n name: \"conv_new_1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\n\nlayer {\n bottom: \"conv_new_1\"\n top: \"conv_new_1\"\n name: \"conv_new_1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv_new_1\"\n top: \"rfcn_cls\"\n name: \"rfcn_cls\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1029 #21*(7^2) cls_num*(score_maps_size^2)\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\nlayer {\n bottom: \"conv_new_1\"\n top: \"rfcn_bbox\"\n name: \"rfcn_bbox\"\n type: \"Convolution\"\n convolution_param {\n num_output: 392 #8*(7^2) cls_num*(score_maps_size^2)\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\n\n#--------------position sensitive RoI pooling--------------\nlayer {\n bottom: \"rfcn_cls\"\n bottom: \"rois\"\n top: \"psroipooled_cls_rois\"\n name: \"psroipooled_cls_rois\"\n type: \"PSROIPooling\"\n psroi_pooling_param {\n spatial_scale: 0.0625\n output_dim: 21\n group_size: 7\n }\n}\n\nlayer {\n bottom: \"psroipooled_cls_rois\"\n top: \"cls_score\"\n name: \"ave_cls_score_rois\"\n type: \"Pooling\"\n pooling_param {\n pool: AVE\n kernel_size: 7\n stride: 7\n }\n}\n\n\nlayer {\n bottom: \"rfcn_bbox\"\n bottom: \"rois\"\n top: \"psroipooled_loc_rois\"\n name: \"psroipooled_loc_rois\"\n type: \"PSROIPooling\"\n psroi_pooling_param {\n spatial_scale: 0.0625\n output_dim: 8\n group_size: 7\n }\n}\n\nlayer {\n bottom: \"psroipooled_loc_rois\"\n top: \"bbox_pred\"\n name: \"ave_bbox_pred_rois\"\n type: \"Pooling\"\n pooling_param {\n pool: AVE\n kernel_size: 7\n stride: 7\n }\n}\n\n\n#--------------online hard example mining--------------\nlayer {\n name: \"per_roi_loss_cls\"\n type: \"SoftmaxWithLossOHEM\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n top: \"temp_loss_cls\"\n top: \"temp_prob_cls\"\n top: \"per_roi_loss_cls\"\n loss_weight: 0\n loss_weight: 0\n loss_weight: 0\n propagate_down: false\n propagate_down: false\n}\n\nlayer {\n name: \"per_roi_loss_bbox\"\n type: \"SmoothL1LossOHEM\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n top: \"temp_loss_bbox\"\n top: \"per_roi_loss_bbox\"\n loss_weight: 0\n loss_weight: 0\n propagate_down: false\n propagate_down: false\n propagate_down: false\n}\n\nlayer {\n name: \"per_roi_loss\"\n type: \"Eltwise\"\n bottom: \"per_roi_loss_cls\"\n bottom: \"per_roi_loss_bbox\"\n top: \"per_roi_loss\"\n propagate_down: false\n propagate_down: false\n}\n\nlayer {\n bottom: \"rois\"\n bottom: \"per_roi_loss\"\n bottom: \"labels\"\n bottom: \"bbox_inside_weights\"\n top: \"labels_ohem\"\n top: \"bbox_loss_weights_ohem\"\n name: \"annotator_detector\"\n type: \"BoxAnnotatorOHEM\"\n box_annotator_ohem_param {\n roi_per_img: 128\n ignore_label: -1\n }\n propagate_down: false\n propagate_down: false\n propagate_down: false\n propagate_down: false\n}\n\nlayer {\n name: \"silence\"\n type: \"Silence\"\n bottom: \"bbox_outside_weights\"\n bottom: \"temp_loss_cls\"\n bottom: \"temp_prob_cls\"\n bottom: \"temp_loss_bbox\"\n}\n\n#-----------------------output------------------------\nlayer {\n name: \"loss\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels_ohem\"\n top: \"loss_cls\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n }\n propagate_down: true\n propagate_down: false\n}\n\nlayer {\n name: \"accuarcy\"\n type: \"Accuracy\"\n bottom: \"cls_score\"\n bottom: \"labels_ohem\"\n top: \"accuarcy\"\n #include: { phase: TEST }\n accuracy_param {\n ignore_label: -1\n }\n propagate_down: false\n propagate_down: false\n}\n\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1LossOHEM\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_loss_weights_ohem\"\n top: \"loss_bbox\"\n loss_weight: 1\n loss_param {\n normalization: PRE_FIXED\n pre_fixed_normalizer: 128\n }\n propagate_down: true\n propagate_down: false\n propagate_down: false\n}\n" }, { "path": "models/pascal_voc/ResNet-50/rfcn_alt_opt_5step_ohem/stage2_rpn_solver60k80k.pt", "content": "train_net: \"models/pascal_voc/ResNet-50/rfcn_alt_opt_5step_ohem/stage2_rpn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 60000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet50_rpn\"\n" }, { "path": "models/pascal_voc/ResNet-50/rfcn_alt_opt_5step_ohem/stage2_rpn_train.pt", "content": "name: \"ResNet-50\"\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4f\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: \"rpn_bbox_inside_weights\"\n bottom: \"rpn_bbox_outside_weights\"\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n" }, { "path": "models/pascal_voc/ResNet-50/rfcn_alt_opt_5step_ohem/stage3_rpn_solver60k80k.pt", "content": "train_net: \"models/pascal_voc/ResNet-50/rfcn_alt_opt_5step_ohem/stage3_rpn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 60000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet50_rpn\"\n" }, { "path": "models/pascal_voc/ResNet-50/rfcn_alt_opt_5step_ohem/stage3_rpn_train.pt", "content": "name: \"ResNet-50\"\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4f\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: \"rpn_bbox_inside_weights\"\n bottom: \"rpn_bbox_outside_weights\"\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n" }, { "path": "models/pascal_voc/ResNet-50/rfcn_end2end/class-aware/test.prototxt", "content": "name: \"ResNet50\"\n\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\n\ninput: \"im_info\"\ninput_shape {\n dim: 1\n dim: 3\n}\n\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"bn5a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"bn5a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"bn5a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"bn5a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"bn5b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"bn5b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"bn5b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"bn5c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"bn5c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"bn5c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res5c\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 decay_mult: 1.0 }\n param { lr_mult: 2.0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 decay_mult: 1.0 }\n param { lr_mult: 2.0 decay_mult: 0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 decay_mult: 1.0 }\n param { lr_mult: 2.0 decay_mult: 0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rois'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n#----------------------new conv layer------------------\nlayer {\n bottom: \"res5c\"\n top: \"conv_new_1\"\n name: \"conv_new_1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\n\nlayer {\n bottom: \"conv_new_1\"\n top: \"conv_new_1\"\n name: \"conv_new_1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv_new_1\"\n top: \"rfcn_cls\"\n name: \"rfcn_cls\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1029 #21*(7^2) cls_num*(score_maps_size^2)\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\nlayer {\n bottom: \"conv_new_1\"\n top: \"rfcn_bbox\"\n name: \"rfcn_bbox\"\n type: \"Convolution\"\n convolution_param {\n num_output: 4116 #8*(7^2) cls_num*(score_maps_size^2)\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\n\n#--------------position sensitive RoI pooling--------------\nlayer {\n bottom: \"rfcn_cls\"\n bottom: \"rois\"\n top: \"psroipooled_cls_rois\"\n name: \"psroipooled_cls_rois\"\n type: \"PSROIPooling\"\n psroi_pooling_param {\n spatial_scale: 0.0625\n output_dim: 21\n group_size: 7\n }\n}\n\nlayer {\n bottom: \"psroipooled_cls_rois\"\n top: \"cls_score\"\n name: \"ave_cls_score_rois\"\n type: \"Pooling\"\n pooling_param {\n pool: AVE\n kernel_size: 7\n stride: 7\n }\n}\n\n\nlayer {\n bottom: \"rfcn_bbox\"\n bottom: \"rois\"\n top: \"psroipooled_loc_rois\"\n name: \"psroipooled_loc_rois\"\n type: \"PSROIPooling\"\n psroi_pooling_param {\n spatial_scale: 0.0625\n output_dim: 84\n group_size: 7\n }\n}\n\nlayer {\n bottom: \"psroipooled_loc_rois\"\n top: \"bbox_pred_pre\"\n name: \"ave_bbox_pred_rois\"\n type: \"Pooling\"\n pooling_param {\n pool: AVE\n kernel_size: 7\n stride: 7\n }\n}\n\n\n#-----------------------output------------------------\nlayer {\n name: \"cls_prob\"\n type: \"Softmax\"\n bottom: \"cls_score\"\n top: \"cls_prob_pre\"\n}\n\nlayer {\n name: \"cls_prob_reshape\"\n type: \"Reshape\"\n bottom: \"cls_prob_pre\"\n top: \"cls_prob\"\n reshape_param {\n shape {\n dim: -1\n dim: 21\n }\n }\n}\n\nlayer {\n name: \"bbox_pred_reshape\"\n type: \"Reshape\"\n bottom: \"bbox_pred_pre\"\n top: \"bbox_pred\"\n reshape_param {\n shape {\n dim: -1\n dim: 84\n }\n }\n}\n\n\n" }, { "path": "models/pascal_voc/ResNet-50/rfcn_end2end/class-aware/train_ohem.prototxt", "content": "name: \"ResNet-50\"\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"bn5a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"bn5a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"bn5a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"bn5a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"bn5b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"bn5b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"bn5b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"bn5c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"bn5c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"bn5c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res5c\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 512\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\n\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rpn_rois'\n# top: 'rpn_scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n#layer {\n# name: 'debug-data'\n# type: 'Python'\n# bottom: 'data'\n# bottom: 'rpn_rois'\n# bottom: 'rpn_scores'\n# python_param {\n# module: 'rpn.debug_layer'\n# layer: 'RPNDebugLayer'\n# }\n#}\n\nlayer {\n name: 'roi-data'\n type: 'Python'\n bottom: 'rpn_rois'\n bottom: 'gt_boxes'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'rpn.proposal_target_layer'\n layer: 'ProposalTargetLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n#----------------------new conv layer------------------\nlayer {\n bottom: \"res5c\"\n top: \"conv_new_1\"\n name: \"conv_new_1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\n\nlayer {\n bottom: \"conv_new_1\"\n top: \"conv_new_1\"\n name: \"conv_new_1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv_new_1\"\n top: \"rfcn_cls\"\n name: \"rfcn_cls\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1029 #21*(7^2) cls_num*(score_maps_size^2)\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\nlayer {\n bottom: \"conv_new_1\"\n top: \"rfcn_bbox\"\n name: \"rfcn_bbox\"\n type: \"Convolution\"\n convolution_param {\n num_output: 4116 #8*(7^2) cls_num*(score_maps_size^2)\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\n\n#--------------position sensitive RoI pooling--------------\nlayer {\n bottom: \"rfcn_cls\"\n bottom: \"rois\"\n top: \"psroipooled_cls_rois\"\n name: \"psroipooled_cls_rois\"\n type: \"PSROIPooling\"\n psroi_pooling_param {\n spatial_scale: 0.0625\n output_dim: 21\n group_size: 7\n }\n}\n\nlayer {\n bottom: \"psroipooled_cls_rois\"\n top: \"cls_score\"\n name: \"ave_cls_score_rois\"\n type: \"Pooling\"\n pooling_param {\n pool: AVE\n kernel_size: 7\n stride: 7\n }\n}\n\n\nlayer {\n bottom: \"rfcn_bbox\"\n bottom: \"rois\"\n top: \"psroipooled_loc_rois\"\n name: \"psroipooled_loc_rois\"\n type: \"PSROIPooling\"\n psroi_pooling_param {\n spatial_scale: 0.0625\n output_dim: 84\n group_size: 7\n }\n}\n\nlayer {\n bottom: \"psroipooled_loc_rois\"\n top: \"bbox_pred\"\n name: \"ave_bbox_pred_rois\"\n type: \"Pooling\"\n pooling_param {\n pool: AVE\n kernel_size: 7\n stride: 7\n }\n}\n\n\n#--------------online hard example mining--------------\nlayer {\n name: \"per_roi_loss_cls\"\n type: \"SoftmaxWithLossOHEM\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n top: \"temp_loss_cls\"\n top: \"temp_prob_cls\"\n top: \"per_roi_loss_cls\"\n loss_weight: 0\n loss_weight: 0\n loss_weight: 0\n propagate_down: false\n propagate_down: false\n}\n\nlayer {\n name: \"per_roi_loss_bbox\"\n type: \"SmoothL1LossOHEM\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n top: \"temp_loss_bbox\"\n top: \"per_roi_loss_bbox\"\n loss_weight: 0\n loss_weight: 0\n propagate_down: false\n propagate_down: false\n propagate_down: false\n}\n\nlayer {\n name: \"per_roi_loss\"\n type: \"Eltwise\"\n bottom: \"per_roi_loss_cls\"\n bottom: \"per_roi_loss_bbox\"\n top: \"per_roi_loss\"\n propagate_down: false\n propagate_down: false\n}\n\nlayer {\n bottom: \"rois\"\n bottom: \"per_roi_loss\"\n bottom: \"labels\"\n bottom: \"bbox_inside_weights\"\n top: \"labels_ohem\"\n top: \"bbox_loss_weights_ohem\"\n name: \"annotator_detector\"\n type: \"BoxAnnotatorOHEM\"\n box_annotator_ohem_param {\n roi_per_img: 128\n ignore_label: -1\n }\n propagate_down: false\n propagate_down: false\n propagate_down: false\n propagate_down: false\n}\n\nlayer {\n name: \"silence\"\n type: \"Silence\"\n bottom: \"bbox_outside_weights\"\n bottom: \"temp_loss_cls\"\n bottom: \"temp_prob_cls\"\n bottom: \"temp_loss_bbox\"\n}\n\n#-----------------------output------------------------\nlayer {\n name: \"loss\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels_ohem\"\n top: \"loss_cls\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n }\n propagate_down: true\n propagate_down: false\n}\n\nlayer {\n name: \"accuarcy\"\n type: \"Accuracy\"\n bottom: \"cls_score\"\n bottom: \"labels_ohem\"\n top: \"accuarcy\"\n #include: { phase: TEST }\n accuracy_param {\n ignore_label: -1\n }\n propagate_down: false\n propagate_down: false\n}\n\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1LossOHEM\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_loss_weights_ohem\"\n top: \"loss_bbox\"\n loss_weight: 1\n loss_param {\n normalization: PRE_FIXED\n pre_fixed_normalizer: 128\n }\n propagate_down: true\n propagate_down: false\n propagate_down: false\n}\n\n" }, { "path": "models/pascal_voc/ResNet-50/rfcn_end2end/solver.prototxt", "content": "train_net: \"models/pascal_voc/ResNet-50/rfcn_end2end/train_agnostic.prototxt\"\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 80000\ndisplay: 20\n\nmomentum: 0.9\nweight_decay: 0.0005\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet50_rfcn\"\niter_size: 2\n# debug_info: true\n" }, { "path": "models/pascal_voc/ResNet-50/rfcn_end2end/solver_ohem.prototxt", "content": "train_net: \"models/pascal_voc/ResNet-50/rfcn_end2end/train_agnostic_ohem.prototxt\"\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 80000\ndisplay: 20\n\nmomentum: 0.9\nweight_decay: 0.0005\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet50_rfcn_ohem\"\niter_size: 2\n# debug_info: true\n" }, { "path": "models/pascal_voc/ResNet-50/rfcn_end2end/test_agnostic.prototxt", "content": "name: \"ResNet50\"\n\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\n\ninput: \"im_info\"\ninput_shape {\n dim: 1\n dim: 3\n}\n\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"bn5a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"bn5a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"bn5a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"bn5a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"bn5b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"bn5b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"bn5b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"bn5c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"bn5c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"bn5c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4f\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 decay_mult: 1.0 }\n param { lr_mult: 2.0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 decay_mult: 1.0 }\n param { lr_mult: 2.0 decay_mult: 0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 decay_mult: 1.0 }\n param { lr_mult: 2.0 decay_mult: 0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rois'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n#----------------------new conv layer------------------\nlayer {\n bottom: \"res5c\"\n top: \"conv_new_1\"\n name: \"conv_new_1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\n\nlayer {\n bottom: \"conv_new_1\"\n top: \"conv_new_1\"\n name: \"conv_new_1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv_new_1\"\n top: \"rfcn_cls\"\n name: \"rfcn_cls\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1029 #21*(7^2) cls_num*(score_maps_size^2)\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\nlayer {\n bottom: \"conv_new_1\"\n top: \"rfcn_bbox\"\n name: \"rfcn_bbox\"\n type: \"Convolution\"\n convolution_param {\n num_output: 392 #8*(7^2) cls_num*(score_maps_size^2)\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\n\n#--------------position sensitive RoI pooling--------------\nlayer {\n bottom: \"rfcn_cls\"\n bottom: \"rois\"\n top: \"psroipooled_cls_rois\"\n name: \"psroipooled_cls_rois\"\n type: \"PSROIPooling\"\n psroi_pooling_param {\n spatial_scale: 0.0625\n output_dim: 21\n group_size: 7\n }\n}\n\nlayer {\n bottom: \"psroipooled_cls_rois\"\n top: \"cls_score\"\n name: \"ave_cls_score_rois\"\n type: \"Pooling\"\n pooling_param {\n pool: AVE\n kernel_size: 7\n stride: 7\n }\n}\n\n\nlayer {\n bottom: \"rfcn_bbox\"\n bottom: \"rois\"\n top: \"psroipooled_loc_rois\"\n name: \"psroipooled_loc_rois\"\n type: \"PSROIPooling\"\n psroi_pooling_param {\n spatial_scale: 0.0625\n output_dim: 8\n group_size: 7\n }\n}\n\nlayer {\n bottom: \"psroipooled_loc_rois\"\n top: \"bbox_pred_pre\"\n name: \"ave_bbox_pred_rois\"\n type: \"Pooling\"\n pooling_param {\n pool: AVE\n kernel_size: 7\n stride: 7\n }\n}\n\n\n#-----------------------output------------------------\nlayer {\n name: \"cls_prob\"\n type: \"Softmax\"\n bottom: \"cls_score\"\n top: \"cls_prob_pre\"\n}\n\nlayer {\n name: \"cls_prob_reshape\"\n type: \"Reshape\"\n bottom: \"cls_prob_pre\"\n top: \"cls_prob\"\n reshape_param {\n shape {\n dim: -1\n dim: 21\n }\n }\n}\n\nlayer {\n name: \"bbox_pred_reshape\"\n type: \"Reshape\"\n bottom: \"bbox_pred_pre\"\n top: \"bbox_pred\"\n reshape_param {\n shape {\n dim: -1\n dim: 8\n }\n }\n}\n\n\n" }, { "path": "models/pascal_voc/ResNet-50/rfcn_end2end/train_agnostic.prototxt", "content": "name: \"ResNet-50\"\n\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"bn5a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"bn5a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"bn5a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"bn5a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"bn5b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"bn5b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"bn5b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"bn5c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"bn5c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"bn5c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4f\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 512\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\n\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rpn_rois'\n# top: 'rpn_scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n#layer {\n# name: 'debug-data'\n# type: 'Python'\n# bottom: 'data'\n# bottom: 'rpn_rois'\n# bottom: 'rpn_scores'\n# python_param {\n# module: 'rpn.debug_layer'\n# layer: 'RPNDebugLayer'\n# }\n#}\n\nlayer {\n name: 'roi-data'\n type: 'Python'\n bottom: 'rpn_rois'\n bottom: 'gt_boxes'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'rpn.proposal_target_layer'\n layer: 'ProposalTargetLayer'\n param_str: \"'num_classes': 2\"\n }\n}\n\n#----------------------new conv layer------------------\nlayer {\n bottom: \"res5c\"\n top: \"conv_new_1\"\n name: \"conv_new_1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\n\nlayer {\n bottom: \"conv_new_1\"\n top: \"conv_new_1\"\n name: \"conv_new_1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv_new_1\"\n top: \"rfcn_cls\"\n name: \"rfcn_cls\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1029 #21*(7^2) cls_num*(score_maps_size^2)\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\nlayer {\n bottom: \"conv_new_1\"\n top: \"rfcn_bbox\"\n name: \"rfcn_bbox\"\n type: \"Convolution\"\n convolution_param {\n num_output: 392 #8*(7^2) cls_num*(score_maps_size^2)\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\n\n#--------------position sensitive RoI pooling--------------\nlayer {\n bottom: \"rfcn_cls\"\n bottom: \"rois\"\n top: \"psroipooled_cls_rois\"\n name: \"psroipooled_cls_rois\"\n type: \"PSROIPooling\"\n psroi_pooling_param {\n spatial_scale: 0.0625\n output_dim: 21\n group_size: 7\n }\n}\n\nlayer {\n bottom: \"psroipooled_cls_rois\"\n top: \"cls_score\"\n name: \"ave_cls_score_rois\"\n type: \"Pooling\"\n pooling_param {\n pool: AVE\n kernel_size: 7\n stride: 7\n }\n}\n\n\nlayer {\n bottom: \"rfcn_bbox\"\n bottom: \"rois\"\n top: \"psroipooled_loc_rois\"\n name: \"psroipooled_loc_rois\"\n type: \"PSROIPooling\"\n psroi_pooling_param {\n spatial_scale: 0.0625\n output_dim: 8\n group_size: 7\n }\n}\n\nlayer {\n bottom: \"psroipooled_loc_rois\"\n top: \"bbox_pred\"\n name: \"ave_bbox_pred_rois\"\n type: \"Pooling\"\n pooling_param {\n pool: AVE\n kernel_size: 7\n stride: 7\n }\n}\n\n\n#-----------------------output------------------------\nlayer {\n name: \"loss\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n top: \"loss_cls\"\n loss_weight: 1\n propagate_down: true\n propagate_down: false\n}\n\nlayer {\n name: \"accuarcy\"\n type: \"Accuracy\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n top: \"accuarcy\"\n #include: { phase: TEST }\n propagate_down: false\n propagate_down: false\n}\n\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1LossOHEM\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: 'bbox_inside_weights'\n top: \"loss_bbox\"\n loss_weight: 1\n loss_param {\n normalization: PRE_FIXED\n pre_fixed_normalizer: 128\n }\n propagate_down: true\n propagate_down: false\n propagate_down: false\n}\n\nlayer {\n name: \"silence\"\n type: \"Silence\"\n bottom: \"bbox_outside_weights\"\n}\n\n" }, { "path": "models/pascal_voc/ResNet-50/rfcn_end2end/train_agnostic_ohem.prototxt", "content": "name: \"ResNet-50\"\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n }\n param {\n lr_mult: 0.0\n }\n param {\n lr_mult: 0.0\n }\n \n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"bn3b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"scale3b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2a\"\n name: \"res3b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2a\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"bn3b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"scale3b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2b\"\n name: \"res3b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b_branch2b\"\n top: \"res3b_branch2c\"\n name: \"res3b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"bn3b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b_branch2c\"\n top: \"res3b_branch2c\"\n name: \"scale3b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b_branch2c\"\n top: \"res3b\"\n name: \"res3b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3b\"\n name: \"res3b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"bn3c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"scale3c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2a\"\n name: \"res3c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2a\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"bn3c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"scale3c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2b\"\n name: \"res3c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c_branch2b\"\n top: \"res3c_branch2c\"\n name: \"res3c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"bn3c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c_branch2c\"\n top: \"res3c_branch2c\"\n name: \"scale3c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b\"\n bottom: \"res3c_branch2c\"\n top: \"res3c\"\n name: \"res3c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3c\"\n name: \"res3c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3c\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"bn3d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"scale3d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2a\"\n name: \"res3d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2a\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"bn3d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"scale3d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2b\"\n name: \"res3d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d_branch2b\"\n top: \"res3d_branch2c\"\n name: \"res3d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"bn3d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d_branch2c\"\n top: \"res3d_branch2c\"\n name: \"scale3d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3c\"\n bottom: \"res3d_branch2c\"\n top: \"res3d\"\n name: \"res3d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res3d\"\n name: \"res3d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3d\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"bn4b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"scale4b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2a\"\n name: \"res4b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2a\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"bn4b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"scale4b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2b\"\n name: \"res4b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b_branch2b\"\n top: \"res4b_branch2c\"\n name: \"res4b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"bn4b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b_branch2c\"\n top: \"res4b_branch2c\"\n name: \"scale4b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b_branch2c\"\n top: \"res4b\"\n name: \"res4b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4b\"\n name: \"res4b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"bn4c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"scale4c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2a\"\n name: \"res4c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2a\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"bn4c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"scale4c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2b\"\n name: \"res4c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c_branch2b\"\n top: \"res4c_branch2c\"\n name: \"res4c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"bn4c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c_branch2c\"\n top: \"res4c_branch2c\"\n name: \"scale4c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b\"\n bottom: \"res4c_branch2c\"\n top: \"res4c\"\n name: \"res4c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4c\"\n name: \"res4c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4c\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"bn4d_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"scale4d_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2a\"\n name: \"res4d_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2a\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"bn4d_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"scale4d_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2b\"\n name: \"res4d_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d_branch2b\"\n top: \"res4d_branch2c\"\n name: \"res4d_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"bn4d_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d_branch2c\"\n top: \"res4d_branch2c\"\n name: \"scale4d_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4c\"\n bottom: \"res4d_branch2c\"\n top: \"res4d\"\n name: \"res4d\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4d\"\n name: \"res4d_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4d\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"bn4e_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"scale4e_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2a\"\n name: \"res4e_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2a\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"bn4e_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"scale4e_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2b\"\n name: \"res4e_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e_branch2b\"\n top: \"res4e_branch2c\"\n name: \"res4e_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"bn4e_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e_branch2c\"\n top: \"res4e_branch2c\"\n name: \"scale4e_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4d\"\n bottom: \"res4e_branch2c\"\n top: \"res4e\"\n name: \"res4e\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4e\"\n name: \"res4e_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4e\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"bn4f_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"scale4f_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2a\"\n name: \"res4f_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2a\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"bn4f_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"scale4f_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2b\"\n name: \"res4f_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f_branch2b\"\n top: \"res4f_branch2c\"\n name: \"res4f_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"bn4f_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f_branch2c\"\n top: \"res4f_branch2c\"\n name: \"scale4f_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4e\"\n bottom: \"res4f_branch2c\"\n top: \"res4f\"\n name: \"res4f\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res4f\"\n name: \"res4f_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"bn5a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4f\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"bn5a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"bn5a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"bn5a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"bn5b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"bn5b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"bn5b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"bn5c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n dilation: 2\n pad: 2\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"bn5c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"bn5c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4f\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 512\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\n\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rpn_rois'\n# top: 'rpn_scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n#layer {\n# name: 'debug-data'\n# type: 'Python'\n# bottom: 'data'\n# bottom: 'rpn_rois'\n# bottom: 'rpn_scores'\n# python_param {\n# module: 'rpn.debug_layer'\n# layer: 'RPNDebugLayer'\n# }\n#}\n\nlayer {\n name: 'roi-data'\n type: 'Python'\n bottom: 'rpn_rois'\n bottom: 'gt_boxes'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'rpn.proposal_target_layer'\n layer: 'ProposalTargetLayer'\n param_str: \"'num_classes': 2\"\n }\n}\n\n#----------------------new conv layer------------------\nlayer {\n bottom: \"res5c\"\n top: \"conv_new_1\"\n name: \"conv_new_1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\n\nlayer {\n bottom: \"conv_new_1\"\n top: \"conv_new_1\"\n name: \"conv_new_1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv_new_1\"\n top: \"rfcn_cls\"\n name: \"rfcn_cls\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1029 #21*(7^2) cls_num*(score_maps_size^2)\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\nlayer {\n bottom: \"conv_new_1\"\n top: \"rfcn_bbox\"\n name: \"rfcn_bbox\"\n type: \"Convolution\"\n convolution_param {\n num_output: 392 #8*(7^2) cls_num*(score_maps_size^2)\n kernel_size: 1\n pad: 0\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n param {\n lr_mult: 1.0\n }\n param {\n lr_mult: 2.0\n }\n}\n\n#--------------position sensitive RoI pooling--------------\nlayer {\n bottom: \"rfcn_cls\"\n bottom: \"rois\"\n top: \"psroipooled_cls_rois\"\n name: \"psroipooled_cls_rois\"\n type: \"PSROIPooling\"\n psroi_pooling_param {\n spatial_scale: 0.0625\n output_dim: 21\n group_size: 7\n }\n}\n\nlayer {\n bottom: \"psroipooled_cls_rois\"\n top: \"cls_score\"\n name: \"ave_cls_score_rois\"\n type: \"Pooling\"\n pooling_param {\n pool: AVE\n kernel_size: 7\n stride: 7\n }\n}\n\n\nlayer {\n bottom: \"rfcn_bbox\"\n bottom: \"rois\"\n top: \"psroipooled_loc_rois\"\n name: \"psroipooled_loc_rois\"\n type: \"PSROIPooling\"\n psroi_pooling_param {\n spatial_scale: 0.0625\n output_dim: 8\n group_size: 7\n }\n}\n\nlayer {\n bottom: \"psroipooled_loc_rois\"\n top: \"bbox_pred\"\n name: \"ave_bbox_pred_rois\"\n type: \"Pooling\"\n pooling_param {\n pool: AVE\n kernel_size: 7\n stride: 7\n }\n}\n\n\n#--------------online hard example mining--------------\nlayer {\n name: \"per_roi_loss_cls\"\n type: \"SoftmaxWithLossOHEM\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n top: \"temp_loss_cls\"\n top: \"temp_prob_cls\"\n top: \"per_roi_loss_cls\"\n loss_weight: 0\n loss_weight: 0\n loss_weight: 0\n propagate_down: false\n propagate_down: false\n}\n\nlayer {\n name: \"per_roi_loss_bbox\"\n type: \"SmoothL1LossOHEM\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n top: \"temp_loss_bbox\"\n top: \"per_roi_loss_bbox\"\n loss_weight: 0\n loss_weight: 0\n propagate_down: false\n propagate_down: false\n propagate_down: false\n}\n\nlayer {\n name: \"per_roi_loss\"\n type: \"Eltwise\"\n bottom: \"per_roi_loss_cls\"\n bottom: \"per_roi_loss_bbox\"\n top: \"per_roi_loss\"\n propagate_down: false\n propagate_down: false\n}\n\nlayer {\n bottom: \"rois\"\n bottom: \"per_roi_loss\"\n bottom: \"labels\"\n bottom: \"bbox_inside_weights\"\n top: \"labels_ohem\"\n top: \"bbox_loss_weights_ohem\"\n name: \"annotator_detector\"\n type: \"BoxAnnotatorOHEM\"\n box_annotator_ohem_param {\n roi_per_img: 128\n ignore_label: -1\n }\n propagate_down: false\n propagate_down: false\n propagate_down: false\n propagate_down: false\n}\n\nlayer {\n name: \"silence\"\n type: \"Silence\"\n bottom: \"bbox_outside_weights\"\n bottom: \"temp_loss_cls\"\n bottom: \"temp_prob_cls\"\n bottom: \"temp_loss_bbox\"\n}\n\n#-----------------------output------------------------\nlayer {\n name: \"loss\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels_ohem\"\n top: \"loss_cls\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n }\n propagate_down: true\n propagate_down: false\n}\n\nlayer {\n name: \"accuarcy\"\n type: \"Accuracy\"\n bottom: \"cls_score\"\n bottom: \"labels_ohem\"\n top: \"accuarcy\"\n #include: { phase: TEST }\n accuracy_param {\n ignore_label: -1\n }\n propagate_down: false\n propagate_down: false\n}\n\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1LossOHEM\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_loss_weights_ohem\"\n top: \"loss_bbox\"\n loss_weight: 1\n loss_param {\n normalization: PRE_FIXED\n pre_fixed_normalizer: 128\n }\n propagate_down: true\n propagate_down: false\n propagate_down: false\n}\n\n" }, { "path": "models/pascal_voc/ResNet101/faster_rcnn_alt_opt/faster_rcnn_test.pt", "content": "name: \"ResNet101\"\n\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\n\ninput: \"im_info\"\ninput_shape {\n dim: 1\n dim: 3\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"conv1\"\n bottom: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2a\"\n bottom: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2b\"\n bottom: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2a\"\n bottom: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2b\"\n bottom: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2a\"\n bottom: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2b\"\n bottom: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2a\"\n bottom: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2b\"\n bottom: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b1_branch2a\"\n name: \"res3b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2a\"\n name: \"bn3b1_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2a\"\n name: \"scale3b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2a\"\n bottom: \"res3b1_branch2a\"\n name: \"res3b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2b\"\n name: \"res3b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2b\"\n name: \"bn3b1_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2b\"\n name: \"scale3b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2b\"\n bottom: \"res3b1_branch2b\"\n name: \"res3b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2c\"\n name: \"res3b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2c\"\n top: \"res3b1_branch2c\"\n name: \"bn3b1_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2c\"\n top: \"res3b1_branch2c\"\n name: \"scale3b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b1_branch2c\"\n top: \"res3b1\"\n name: \"res3b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b1\"\n name: \"res3b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b2_branch2a\"\n name: \"res3b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2a\"\n name: \"bn3b2_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2a\"\n name: \"scale3b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2a\"\n bottom: \"res3b2_branch2a\"\n name: \"res3b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2b\"\n name: \"res3b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2b\"\n name: \"bn3b2_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2b\"\n name: \"scale3b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2b\"\n bottom: \"res3b2_branch2b\"\n name: \"res3b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2c\"\n name: \"res3b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2c\"\n top: \"res3b2_branch2c\"\n name: \"bn3b2_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2c\"\n top: \"res3b2_branch2c\"\n name: \"scale3b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1\"\n bottom: \"res3b2_branch2c\"\n top: \"res3b2\"\n name: \"res3b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b2\"\n name: \"res3b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b3_branch2a\"\n name: \"res3b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2a\"\n name: \"bn3b3_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2a\"\n name: \"scale3b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2a\"\n bottom: \"res3b3_branch2a\"\n name: \"res3b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2b\"\n name: \"res3b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2b\"\n name: \"bn3b3_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2b\"\n name: \"scale3b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2b\"\n bottom: \"res3b3_branch2b\"\n name: \"res3b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2c\"\n name: \"res3b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2c\"\n top: \"res3b3_branch2c\"\n name: \"bn3b3_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2c\"\n top: \"res3b3_branch2c\"\n name: \"scale3b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2\"\n bottom: \"res3b3_branch2c\"\n top: \"res3b3\"\n name: \"res3b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res3b3\"\n name: \"res3b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2a\"\n bottom: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2b\"\n bottom: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b1_branch2a\"\n name: \"res4b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2a\"\n name: \"bn4b1_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2a\"\n name: \"scale4b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2a\"\n bottom: \"res4b1_branch2a\"\n name: \"res4b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2b\"\n name: \"res4b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2b\"\n name: \"bn4b1_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2b\"\n name: \"scale4b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2b\"\n bottom: \"res4b1_branch2b\"\n name: \"res4b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2c\"\n name: \"res4b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2c\"\n top: \"res4b1_branch2c\"\n name: \"bn4b1_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2c\"\n top: \"res4b1_branch2c\"\n name: \"scale4b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b1_branch2c\"\n top: \"res4b1\"\n name: \"res4b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b1\"\n name: \"res4b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b2_branch2a\"\n name: \"res4b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2a\"\n name: \"bn4b2_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2a\"\n name: \"scale4b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2a\"\n bottom: \"res4b2_branch2a\"\n name: \"res4b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2b\"\n name: \"res4b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2b\"\n name: \"bn4b2_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2b\"\n name: \"scale4b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2b\"\n bottom: \"res4b2_branch2b\"\n name: \"res4b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2c\"\n name: \"res4b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2c\"\n top: \"res4b2_branch2c\"\n name: \"bn4b2_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2c\"\n top: \"res4b2_branch2c\"\n name: \"scale4b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1\"\n bottom: \"res4b2_branch2c\"\n top: \"res4b2\"\n name: \"res4b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b2\"\n name: \"res4b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b3_branch2a\"\n name: \"res4b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2a\"\n name: \"bn4b3_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2a\"\n name: \"scale4b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2a\"\n bottom: \"res4b3_branch2a\"\n name: \"res4b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2b\"\n name: \"res4b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2b\"\n name: \"bn4b3_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2b\"\n name: \"scale4b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2b\"\n bottom: \"res4b3_branch2b\"\n name: \"res4b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2c\"\n name: \"res4b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2c\"\n top: \"res4b3_branch2c\"\n name: \"bn4b3_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2c\"\n top: \"res4b3_branch2c\"\n name: \"scale4b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2\"\n bottom: \"res4b3_branch2c\"\n top: \"res4b3\"\n name: \"res4b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b3\"\n name: \"res4b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b4_branch2a\"\n name: \"res4b4_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2a\"\n name: \"bn4b4_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2a\"\n name: \"scale4b4_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2a\"\n bottom: \"res4b4_branch2a\"\n name: \"res4b4_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2b\"\n name: \"res4b4_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2b\"\n name: \"bn4b4_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2b\"\n name: \"scale4b4_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2b\"\n bottom: \"res4b4_branch2b\"\n name: \"res4b4_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2c\"\n name: \"res4b4_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2c\"\n top: \"res4b4_branch2c\"\n name: \"bn4b4_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2c\"\n top: \"res4b4_branch2c\"\n name: \"scale4b4_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3\"\n bottom: \"res4b4_branch2c\"\n top: \"res4b4\"\n name: \"res4b4\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b4\"\n name: \"res4b4_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b5_branch2a\"\n name: \"res4b5_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2a\"\n name: \"bn4b5_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2a\"\n name: \"scale4b5_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2a\"\n bottom: \"res4b5_branch2a\"\n name: \"res4b5_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2b\"\n name: \"res4b5_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2b\"\n name: \"bn4b5_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2b\"\n name: \"scale4b5_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2b\"\n bottom: \"res4b5_branch2b\"\n name: \"res4b5_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2c\"\n name: \"res4b5_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2c\"\n top: \"res4b5_branch2c\"\n name: \"bn4b5_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2c\"\n top: \"res4b5_branch2c\"\n name: \"scale4b5_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4\"\n bottom: \"res4b5_branch2c\"\n top: \"res4b5\"\n name: \"res4b5\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b5\"\n name: \"res4b5_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b6_branch2a\"\n name: \"res4b6_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2a\"\n name: \"bn4b6_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2a\"\n name: \"scale4b6_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2a\"\n bottom: \"res4b6_branch2a\"\n name: \"res4b6_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2b\"\n name: \"res4b6_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2b\"\n name: \"bn4b6_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2b\"\n name: \"scale4b6_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2b\"\n bottom: \"res4b6_branch2b\"\n name: \"res4b6_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2c\"\n name: \"res4b6_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2c\"\n top: \"res4b6_branch2c\"\n name: \"bn4b6_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2c\"\n top: \"res4b6_branch2c\"\n name: \"scale4b6_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5\"\n bottom: \"res4b6_branch2c\"\n top: \"res4b6\"\n name: \"res4b6\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b6\"\n name: \"res4b6_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b7_branch2a\"\n name: \"res4b7_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2a\"\n name: \"bn4b7_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2a\"\n name: \"scale4b7_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2a\"\n bottom: \"res4b7_branch2a\"\n name: \"res4b7_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2b\"\n name: \"res4b7_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2b\"\n name: \"bn4b7_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2b\"\n name: \"scale4b7_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2b\"\n bottom: \"res4b7_branch2b\"\n name: \"res4b7_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2c\"\n name: \"res4b7_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2c\"\n top: \"res4b7_branch2c\"\n name: \"bn4b7_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2c\"\n top: \"res4b7_branch2c\"\n name: \"scale4b7_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6\"\n bottom: \"res4b7_branch2c\"\n top: \"res4b7\"\n name: \"res4b7\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b7\"\n name: \"res4b7_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b8_branch2a\"\n name: \"res4b8_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2a\"\n name: \"bn4b8_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2a\"\n name: \"scale4b8_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2a\"\n bottom: \"res4b8_branch2a\"\n name: \"res4b8_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2b\"\n name: \"res4b8_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2b\"\n name: \"bn4b8_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2b\"\n name: \"scale4b8_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2b\"\n bottom: \"res4b8_branch2b\"\n name: \"res4b8_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2c\"\n name: \"res4b8_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2c\"\n top: \"res4b8_branch2c\"\n name: \"bn4b8_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2c\"\n top: \"res4b8_branch2c\"\n name: \"scale4b8_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7\"\n bottom: \"res4b8_branch2c\"\n top: \"res4b8\"\n name: \"res4b8\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b8\"\n name: \"res4b8_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b9_branch2a\"\n name: \"res4b9_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2a\"\n name: \"bn4b9_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2a\"\n name: \"scale4b9_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2a\"\n bottom: \"res4b9_branch2a\"\n name: \"res4b9_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2b\"\n name: \"res4b9_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2b\"\n name: \"bn4b9_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2b\"\n name: \"scale4b9_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2b\"\n bottom: \"res4b9_branch2b\"\n name: \"res4b9_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2c\"\n name: \"res4b9_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2c\"\n top: \"res4b9_branch2c\"\n name: \"bn4b9_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2c\"\n top: \"res4b9_branch2c\"\n name: \"scale4b9_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8\"\n bottom: \"res4b9_branch2c\"\n top: \"res4b9\"\n name: \"res4b9\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b9\"\n name: \"res4b9_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b10_branch2a\"\n name: \"res4b10_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2a\"\n name: \"bn4b10_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2a\"\n name: \"scale4b10_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2a\"\n bottom: \"res4b10_branch2a\"\n name: \"res4b10_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2b\"\n name: \"res4b10_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2b\"\n name: \"bn4b10_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2b\"\n name: \"scale4b10_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2b\"\n bottom: \"res4b10_branch2b\"\n name: \"res4b10_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2c\"\n name: \"res4b10_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2c\"\n top: \"res4b10_branch2c\"\n name: \"bn4b10_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2c\"\n top: \"res4b10_branch2c\"\n name: \"scale4b10_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9\"\n bottom: \"res4b10_branch2c\"\n top: \"res4b10\"\n name: \"res4b10\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b10\"\n name: \"res4b10_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b11_branch2a\"\n name: \"res4b11_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2a\"\n name: \"bn4b11_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2a\"\n name: \"scale4b11_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2a\"\n bottom: \"res4b11_branch2a\"\n name: \"res4b11_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2b\"\n name: \"res4b11_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2b\"\n name: \"bn4b11_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2b\"\n name: \"scale4b11_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2b\"\n bottom: \"res4b11_branch2b\"\n name: \"res4b11_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2c\"\n name: \"res4b11_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2c\"\n top: \"res4b11_branch2c\"\n name: \"bn4b11_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2c\"\n top: \"res4b11_branch2c\"\n name: \"scale4b11_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10\"\n bottom: \"res4b11_branch2c\"\n top: \"res4b11\"\n name: \"res4b11\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b11\"\n name: \"res4b11_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b12_branch2a\"\n name: \"res4b12_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2a\"\n name: \"bn4b12_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2a\"\n name: \"scale4b12_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2a\"\n bottom: \"res4b12_branch2a\"\n name: \"res4b12_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2b\"\n name: \"res4b12_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2b\"\n name: \"bn4b12_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2b\"\n name: \"scale4b12_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2b\"\n bottom: \"res4b12_branch2b\"\n name: \"res4b12_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2c\"\n name: \"res4b12_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2c\"\n top: \"res4b12_branch2c\"\n name: \"bn4b12_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2c\"\n top: \"res4b12_branch2c\"\n name: \"scale4b12_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11\"\n bottom: \"res4b12_branch2c\"\n top: \"res4b12\"\n name: \"res4b12\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b12\"\n name: \"res4b12_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b13_branch2a\"\n name: \"res4b13_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2a\"\n name: \"bn4b13_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2a\"\n name: \"scale4b13_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2a\"\n bottom: \"res4b13_branch2a\"\n name: \"res4b13_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2b\"\n name: \"res4b13_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2b\"\n name: \"bn4b13_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2b\"\n name: \"scale4b13_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2b\"\n bottom: \"res4b13_branch2b\"\n name: \"res4b13_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2c\"\n name: \"res4b13_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2c\"\n top: \"res4b13_branch2c\"\n name: \"bn4b13_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2c\"\n top: \"res4b13_branch2c\"\n name: \"scale4b13_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12\"\n bottom: \"res4b13_branch2c\"\n top: \"res4b13\"\n name: \"res4b13\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b13\"\n name: \"res4b13_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b14_branch2a\"\n name: \"res4b14_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2a\"\n name: \"bn4b14_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2a\"\n name: \"scale4b14_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2a\"\n bottom: \"res4b14_branch2a\"\n name: \"res4b14_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2b\"\n name: \"res4b14_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2b\"\n name: \"bn4b14_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2b\"\n name: \"scale4b14_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2b\"\n bottom: \"res4b14_branch2b\"\n name: \"res4b14_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2c\"\n name: \"res4b14_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2c\"\n top: \"res4b14_branch2c\"\n name: \"bn4b14_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2c\"\n top: \"res4b14_branch2c\"\n name: \"scale4b14_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13\"\n bottom: \"res4b14_branch2c\"\n top: \"res4b14\"\n name: \"res4b14\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b14\"\n name: \"res4b14_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b15_branch2a\"\n name: \"res4b15_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2a\"\n name: \"bn4b15_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2a\"\n name: \"scale4b15_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2a\"\n bottom: \"res4b15_branch2a\"\n name: \"res4b15_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2b\"\n name: \"res4b15_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2b\"\n name: \"bn4b15_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2b\"\n name: \"scale4b15_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2b\"\n bottom: \"res4b15_branch2b\"\n name: \"res4b15_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2c\"\n name: \"res4b15_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2c\"\n top: \"res4b15_branch2c\"\n name: \"bn4b15_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2c\"\n top: \"res4b15_branch2c\"\n name: \"scale4b15_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14\"\n bottom: \"res4b15_branch2c\"\n top: \"res4b15\"\n name: \"res4b15\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b15\"\n name: \"res4b15_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b16_branch2a\"\n name: \"res4b16_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2a\"\n name: \"bn4b16_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2a\"\n name: \"scale4b16_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2a\"\n bottom: \"res4b16_branch2a\"\n name: \"res4b16_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2b\"\n name: \"res4b16_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2b\"\n name: \"bn4b16_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2b\"\n name: \"scale4b16_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2b\"\n bottom: \"res4b16_branch2b\"\n name: \"res4b16_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2c\"\n name: \"res4b16_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2c\"\n top: \"res4b16_branch2c\"\n name: \"bn4b16_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2c\"\n top: \"res4b16_branch2c\"\n name: \"scale4b16_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15\"\n bottom: \"res4b16_branch2c\"\n top: \"res4b16\"\n name: \"res4b16\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b16\"\n name: \"res4b16_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b17_branch2a\"\n name: \"res4b17_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2a\"\n name: \"bn4b17_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2a\"\n name: \"scale4b17_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2a\"\n bottom: \"res4b17_branch2a\"\n name: \"res4b17_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2b\"\n name: \"res4b17_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2b\"\n name: \"bn4b17_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2b\"\n name: \"scale4b17_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2b\"\n bottom: \"res4b17_branch2b\"\n name: \"res4b17_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2c\"\n name: \"res4b17_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2c\"\n top: \"res4b17_branch2c\"\n name: \"bn4b17_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2c\"\n top: \"res4b17_branch2c\"\n name: \"scale4b17_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16\"\n bottom: \"res4b17_branch2c\"\n top: \"res4b17\"\n name: \"res4b17\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b17\"\n name: \"res4b17_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b18_branch2a\"\n name: \"res4b18_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2a\"\n name: \"bn4b18_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2a\"\n name: \"scale4b18_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2a\"\n bottom: \"res4b18_branch2a\"\n name: \"res4b18_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2b\"\n name: \"res4b18_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2b\"\n name: \"bn4b18_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2b\"\n name: \"scale4b18_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2b\"\n bottom: \"res4b18_branch2b\"\n name: \"res4b18_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2c\"\n name: \"res4b18_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2c\"\n top: \"res4b18_branch2c\"\n name: \"bn4b18_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2c\"\n top: \"res4b18_branch2c\"\n name: \"scale4b18_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17\"\n bottom: \"res4b18_branch2c\"\n top: \"res4b18\"\n name: \"res4b18\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b18\"\n name: \"res4b18_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b19_branch2a\"\n name: \"res4b19_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2a\"\n name: \"bn4b19_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2a\"\n name: \"scale4b19_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2a\"\n bottom: \"res4b19_branch2a\"\n name: \"res4b19_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2b\"\n name: \"res4b19_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2b\"\n name: \"bn4b19_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2b\"\n name: \"scale4b19_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2b\"\n bottom: \"res4b19_branch2b\"\n name: \"res4b19_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2c\"\n name: \"res4b19_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2c\"\n top: \"res4b19_branch2c\"\n name: \"bn4b19_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2c\"\n top: \"res4b19_branch2c\"\n name: \"scale4b19_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18\"\n bottom: \"res4b19_branch2c\"\n top: \"res4b19\"\n name: \"res4b19\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b19\"\n name: \"res4b19_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b20_branch2a\"\n name: \"res4b20_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2a\"\n name: \"bn4b20_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2a\"\n name: \"scale4b20_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2a\"\n bottom: \"res4b20_branch2a\"\n name: \"res4b20_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2b\"\n name: \"res4b20_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2b\"\n name: \"bn4b20_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2b\"\n name: \"scale4b20_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2b\"\n bottom: \"res4b20_branch2b\"\n name: \"res4b20_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2c\"\n name: \"res4b20_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2c\"\n top: \"res4b20_branch2c\"\n name: \"bn4b20_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2c\"\n top: \"res4b20_branch2c\"\n name: \"scale4b20_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19\"\n bottom: \"res4b20_branch2c\"\n top: \"res4b20\"\n name: \"res4b20\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b20\"\n name: \"res4b20_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b21_branch2a\"\n name: \"res4b21_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2a\"\n name: \"bn4b21_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2a\"\n name: \"scale4b21_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2a\"\n bottom: \"res4b21_branch2a\"\n name: \"res4b21_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2b\"\n name: \"res4b21_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2b\"\n name: \"bn4b21_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2b\"\n name: \"scale4b21_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2b\"\n bottom: \"res4b21_branch2b\"\n name: \"res4b21_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2c\"\n name: \"res4b21_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2c\"\n top: \"res4b21_branch2c\"\n name: \"bn4b21_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2c\"\n top: \"res4b21_branch2c\"\n name: \"scale4b21_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20\"\n bottom: \"res4b21_branch2c\"\n top: \"res4b21\"\n name: \"res4b21\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b21\"\n name: \"res4b21_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b22_branch2a\"\n name: \"res4b22_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2a\"\n name: \"bn4b22_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2a\"\n name: \"scale4b22_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2a\"\n bottom: \"res4b22_branch2a\"\n name: \"res4b22_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2b\"\n name: \"res4b22_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2b\"\n name: \"bn4b22_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2b\"\n name: \"scale4b22_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2b\"\n bottom: \"res4b22_branch2b\"\n name: \"res4b22_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2c\"\n name: \"res4b22_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2c\"\n top: \"res4b22_branch2c\"\n name: \"bn4b22_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2c\"\n top: \"res4b22_branch2c\"\n name: \"scale4b22_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21\"\n bottom: \"res4b22_branch2c\"\n top: \"res4b22\"\n name: \"res4b22\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b22\"\n top: \"res4b22\"\n name: \"res4b22_relu\"\n type: \"ReLU\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4b22\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rois'\n top: 'scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n\n#========= RCNN ============\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"res4b22\"\n bottom: \"rois\"\n top: \"roi_pool5\"\n roi_pooling_param {\n pooled_w: 14\n pooled_h: 14\n spatial_scale: 0.0625 # 1/16\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"bn5a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"bn5a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"bn5a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"bn5a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"bn5b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"bn5b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"bn5b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"bn5c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"bn5c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"bn5c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\n\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\n\nlayer {\n name: \"cls_prob\"\n type: \"Softmax\"\n bottom: \"cls_score\"\n top: \"cls_prob\"\n}\n" }, { "path": "models/pascal_voc/ResNet101/faster_rcnn_alt_opt/rpn_test.pt", "content": "name: \"ResNet101\"\n\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\n\ninput: \"im_info\"\ninput_shape {\n dim: 1\n dim: 3\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"conv1\"\n bottom: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2a\"\n bottom: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2b\"\n bottom: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2a\"\n bottom: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2b\"\n bottom: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2a\"\n bottom: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2b\"\n bottom: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2a\"\n bottom: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2b\"\n bottom: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b1_branch2a\"\n name: \"res3b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2a\"\n name: \"bn3b1_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2a\"\n name: \"scale3b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2a\"\n bottom: \"res3b1_branch2a\"\n name: \"res3b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2b\"\n name: \"res3b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2b\"\n name: \"bn3b1_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2b\"\n name: \"scale3b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2b\"\n bottom: \"res3b1_branch2b\"\n name: \"res3b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2c\"\n name: \"res3b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2c\"\n top: \"res3b1_branch2c\"\n name: \"bn3b1_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2c\"\n top: \"res3b1_branch2c\"\n name: \"scale3b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b1_branch2c\"\n top: \"res3b1\"\n name: \"res3b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b1\"\n name: \"res3b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b2_branch2a\"\n name: \"res3b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2a\"\n name: \"bn3b2_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2a\"\n name: \"scale3b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2a\"\n bottom: \"res3b2_branch2a\"\n name: \"res3b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2b\"\n name: \"res3b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2b\"\n name: \"bn3b2_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2b\"\n name: \"scale3b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2b\"\n bottom: \"res3b2_branch2b\"\n name: \"res3b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2c\"\n name: \"res3b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2c\"\n top: \"res3b2_branch2c\"\n name: \"bn3b2_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2c\"\n top: \"res3b2_branch2c\"\n name: \"scale3b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1\"\n bottom: \"res3b2_branch2c\"\n top: \"res3b2\"\n name: \"res3b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b2\"\n name: \"res3b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b3_branch2a\"\n name: \"res3b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2a\"\n name: \"bn3b3_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2a\"\n name: \"scale3b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2a\"\n bottom: \"res3b3_branch2a\"\n name: \"res3b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2b\"\n name: \"res3b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2b\"\n name: \"bn3b3_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2b\"\n name: \"scale3b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2b\"\n bottom: \"res3b3_branch2b\"\n name: \"res3b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2c\"\n name: \"res3b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2c\"\n top: \"res3b3_branch2c\"\n name: \"bn3b3_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2c\"\n top: \"res3b3_branch2c\"\n name: \"scale3b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2\"\n bottom: \"res3b3_branch2c\"\n top: \"res3b3\"\n name: \"res3b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res3b3\"\n name: \"res3b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2a\"\n bottom: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2b\"\n bottom: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b1_branch2a\"\n name: \"res4b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2a\"\n name: \"bn4b1_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2a\"\n name: \"scale4b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2a\"\n bottom: \"res4b1_branch2a\"\n name: \"res4b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2b\"\n name: \"res4b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2b\"\n name: \"bn4b1_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2b\"\n name: \"scale4b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2b\"\n bottom: \"res4b1_branch2b\"\n name: \"res4b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2c\"\n name: \"res4b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2c\"\n top: \"res4b1_branch2c\"\n name: \"bn4b1_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2c\"\n top: \"res4b1_branch2c\"\n name: \"scale4b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b1_branch2c\"\n top: \"res4b1\"\n name: \"res4b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b1\"\n name: \"res4b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b2_branch2a\"\n name: \"res4b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2a\"\n name: \"bn4b2_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2a\"\n name: \"scale4b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2a\"\n bottom: \"res4b2_branch2a\"\n name: \"res4b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2b\"\n name: \"res4b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2b\"\n name: \"bn4b2_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2b\"\n name: \"scale4b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2b\"\n bottom: \"res4b2_branch2b\"\n name: \"res4b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2c\"\n name: \"res4b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2c\"\n top: \"res4b2_branch2c\"\n name: \"bn4b2_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2c\"\n top: \"res4b2_branch2c\"\n name: \"scale4b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1\"\n bottom: \"res4b2_branch2c\"\n top: \"res4b2\"\n name: \"res4b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b2\"\n name: \"res4b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b3_branch2a\"\n name: \"res4b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2a\"\n name: \"bn4b3_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2a\"\n name: \"scale4b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2a\"\n bottom: \"res4b3_branch2a\"\n name: \"res4b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2b\"\n name: \"res4b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2b\"\n name: \"bn4b3_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2b\"\n name: \"scale4b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2b\"\n bottom: \"res4b3_branch2b\"\n name: \"res4b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2c\"\n name: \"res4b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2c\"\n top: \"res4b3_branch2c\"\n name: \"bn4b3_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2c\"\n top: \"res4b3_branch2c\"\n name: \"scale4b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2\"\n bottom: \"res4b3_branch2c\"\n top: \"res4b3\"\n name: \"res4b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b3\"\n name: \"res4b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b4_branch2a\"\n name: \"res4b4_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2a\"\n name: \"bn4b4_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2a\"\n name: \"scale4b4_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2a\"\n bottom: \"res4b4_branch2a\"\n name: \"res4b4_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2b\"\n name: \"res4b4_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2b\"\n name: \"bn4b4_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2b\"\n name: \"scale4b4_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2b\"\n bottom: \"res4b4_branch2b\"\n name: \"res4b4_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2c\"\n name: \"res4b4_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2c\"\n top: \"res4b4_branch2c\"\n name: \"bn4b4_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2c\"\n top: \"res4b4_branch2c\"\n name: \"scale4b4_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3\"\n bottom: \"res4b4_branch2c\"\n top: \"res4b4\"\n name: \"res4b4\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b4\"\n name: \"res4b4_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b5_branch2a\"\n name: \"res4b5_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2a\"\n name: \"bn4b5_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2a\"\n name: \"scale4b5_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2a\"\n bottom: \"res4b5_branch2a\"\n name: \"res4b5_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2b\"\n name: \"res4b5_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2b\"\n name: \"bn4b5_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2b\"\n name: \"scale4b5_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2b\"\n bottom: \"res4b5_branch2b\"\n name: \"res4b5_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2c\"\n name: \"res4b5_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2c\"\n top: \"res4b5_branch2c\"\n name: \"bn4b5_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2c\"\n top: \"res4b5_branch2c\"\n name: \"scale4b5_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4\"\n bottom: \"res4b5_branch2c\"\n top: \"res4b5\"\n name: \"res4b5\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b5\"\n name: \"res4b5_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b6_branch2a\"\n name: \"res4b6_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2a\"\n name: \"bn4b6_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2a\"\n name: \"scale4b6_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2a\"\n bottom: \"res4b6_branch2a\"\n name: \"res4b6_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2b\"\n name: \"res4b6_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2b\"\n name: \"bn4b6_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2b\"\n name: \"scale4b6_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2b\"\n bottom: \"res4b6_branch2b\"\n name: \"res4b6_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2c\"\n name: \"res4b6_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2c\"\n top: \"res4b6_branch2c\"\n name: \"bn4b6_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2c\"\n top: \"res4b6_branch2c\"\n name: \"scale4b6_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5\"\n bottom: \"res4b6_branch2c\"\n top: \"res4b6\"\n name: \"res4b6\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b6\"\n name: \"res4b6_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b7_branch2a\"\n name: \"res4b7_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2a\"\n name: \"bn4b7_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2a\"\n name: \"scale4b7_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2a\"\n bottom: \"res4b7_branch2a\"\n name: \"res4b7_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2b\"\n name: \"res4b7_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2b\"\n name: \"bn4b7_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2b\"\n name: \"scale4b7_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2b\"\n bottom: \"res4b7_branch2b\"\n name: \"res4b7_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2c\"\n name: \"res4b7_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2c\"\n top: \"res4b7_branch2c\"\n name: \"bn4b7_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2c\"\n top: \"res4b7_branch2c\"\n name: \"scale4b7_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6\"\n bottom: \"res4b7_branch2c\"\n top: \"res4b7\"\n name: \"res4b7\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b7\"\n name: \"res4b7_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b8_branch2a\"\n name: \"res4b8_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2a\"\n name: \"bn4b8_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2a\"\n name: \"scale4b8_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2a\"\n bottom: \"res4b8_branch2a\"\n name: \"res4b8_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2b\"\n name: \"res4b8_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2b\"\n name: \"bn4b8_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2b\"\n name: \"scale4b8_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2b\"\n bottom: \"res4b8_branch2b\"\n name: \"res4b8_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2c\"\n name: \"res4b8_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2c\"\n top: \"res4b8_branch2c\"\n name: \"bn4b8_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2c\"\n top: \"res4b8_branch2c\"\n name: \"scale4b8_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7\"\n bottom: \"res4b8_branch2c\"\n top: \"res4b8\"\n name: \"res4b8\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b8\"\n name: \"res4b8_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b9_branch2a\"\n name: \"res4b9_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2a\"\n name: \"bn4b9_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2a\"\n name: \"scale4b9_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2a\"\n bottom: \"res4b9_branch2a\"\n name: \"res4b9_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2b\"\n name: \"res4b9_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2b\"\n name: \"bn4b9_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2b\"\n name: \"scale4b9_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2b\"\n bottom: \"res4b9_branch2b\"\n name: \"res4b9_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2c\"\n name: \"res4b9_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2c\"\n top: \"res4b9_branch2c\"\n name: \"bn4b9_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2c\"\n top: \"res4b9_branch2c\"\n name: \"scale4b9_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8\"\n bottom: \"res4b9_branch2c\"\n top: \"res4b9\"\n name: \"res4b9\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b9\"\n name: \"res4b9_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b10_branch2a\"\n name: \"res4b10_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2a\"\n name: \"bn4b10_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2a\"\n name: \"scale4b10_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2a\"\n bottom: \"res4b10_branch2a\"\n name: \"res4b10_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2b\"\n name: \"res4b10_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2b\"\n name: \"bn4b10_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2b\"\n name: \"scale4b10_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2b\"\n bottom: \"res4b10_branch2b\"\n name: \"res4b10_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2c\"\n name: \"res4b10_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2c\"\n top: \"res4b10_branch2c\"\n name: \"bn4b10_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2c\"\n top: \"res4b10_branch2c\"\n name: \"scale4b10_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9\"\n bottom: \"res4b10_branch2c\"\n top: \"res4b10\"\n name: \"res4b10\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b10\"\n name: \"res4b10_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b11_branch2a\"\n name: \"res4b11_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2a\"\n name: \"bn4b11_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2a\"\n name: \"scale4b11_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2a\"\n bottom: \"res4b11_branch2a\"\n name: \"res4b11_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2b\"\n name: \"res4b11_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2b\"\n name: \"bn4b11_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2b\"\n name: \"scale4b11_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2b\"\n bottom: \"res4b11_branch2b\"\n name: \"res4b11_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2c\"\n name: \"res4b11_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2c\"\n top: \"res4b11_branch2c\"\n name: \"bn4b11_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2c\"\n top: \"res4b11_branch2c\"\n name: \"scale4b11_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10\"\n bottom: \"res4b11_branch2c\"\n top: \"res4b11\"\n name: \"res4b11\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b11\"\n name: \"res4b11_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b12_branch2a\"\n name: \"res4b12_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2a\"\n name: \"bn4b12_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2a\"\n name: \"scale4b12_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2a\"\n bottom: \"res4b12_branch2a\"\n name: \"res4b12_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2b\"\n name: \"res4b12_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2b\"\n name: \"bn4b12_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2b\"\n name: \"scale4b12_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2b\"\n bottom: \"res4b12_branch2b\"\n name: \"res4b12_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2c\"\n name: \"res4b12_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2c\"\n top: \"res4b12_branch2c\"\n name: \"bn4b12_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2c\"\n top: \"res4b12_branch2c\"\n name: \"scale4b12_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11\"\n bottom: \"res4b12_branch2c\"\n top: \"res4b12\"\n name: \"res4b12\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b12\"\n name: \"res4b12_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b13_branch2a\"\n name: \"res4b13_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2a\"\n name: \"bn4b13_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2a\"\n name: \"scale4b13_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2a\"\n bottom: \"res4b13_branch2a\"\n name: \"res4b13_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2b\"\n name: \"res4b13_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2b\"\n name: \"bn4b13_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2b\"\n name: \"scale4b13_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2b\"\n bottom: \"res4b13_branch2b\"\n name: \"res4b13_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2c\"\n name: \"res4b13_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2c\"\n top: \"res4b13_branch2c\"\n name: \"bn4b13_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2c\"\n top: \"res4b13_branch2c\"\n name: \"scale4b13_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12\"\n bottom: \"res4b13_branch2c\"\n top: \"res4b13\"\n name: \"res4b13\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b13\"\n name: \"res4b13_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b14_branch2a\"\n name: \"res4b14_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2a\"\n name: \"bn4b14_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2a\"\n name: \"scale4b14_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2a\"\n bottom: \"res4b14_branch2a\"\n name: \"res4b14_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2b\"\n name: \"res4b14_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2b\"\n name: \"bn4b14_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2b\"\n name: \"scale4b14_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2b\"\n bottom: \"res4b14_branch2b\"\n name: \"res4b14_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2c\"\n name: \"res4b14_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2c\"\n top: \"res4b14_branch2c\"\n name: \"bn4b14_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2c\"\n top: \"res4b14_branch2c\"\n name: \"scale4b14_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13\"\n bottom: \"res4b14_branch2c\"\n top: \"res4b14\"\n name: \"res4b14\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b14\"\n name: \"res4b14_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b15_branch2a\"\n name: \"res4b15_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2a\"\n name: \"bn4b15_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2a\"\n name: \"scale4b15_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2a\"\n bottom: \"res4b15_branch2a\"\n name: \"res4b15_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2b\"\n name: \"res4b15_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2b\"\n name: \"bn4b15_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2b\"\n name: \"scale4b15_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2b\"\n bottom: \"res4b15_branch2b\"\n name: \"res4b15_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2c\"\n name: \"res4b15_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2c\"\n top: \"res4b15_branch2c\"\n name: \"bn4b15_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2c\"\n top: \"res4b15_branch2c\"\n name: \"scale4b15_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14\"\n bottom: \"res4b15_branch2c\"\n top: \"res4b15\"\n name: \"res4b15\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b15\"\n name: \"res4b15_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b16_branch2a\"\n name: \"res4b16_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2a\"\n name: \"bn4b16_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2a\"\n name: \"scale4b16_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2a\"\n bottom: \"res4b16_branch2a\"\n name: \"res4b16_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2b\"\n name: \"res4b16_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2b\"\n name: \"bn4b16_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2b\"\n name: \"scale4b16_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2b\"\n bottom: \"res4b16_branch2b\"\n name: \"res4b16_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2c\"\n name: \"res4b16_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2c\"\n top: \"res4b16_branch2c\"\n name: \"bn4b16_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2c\"\n top: \"res4b16_branch2c\"\n name: \"scale4b16_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15\"\n bottom: \"res4b16_branch2c\"\n top: \"res4b16\"\n name: \"res4b16\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b16\"\n name: \"res4b16_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b17_branch2a\"\n name: \"res4b17_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2a\"\n name: \"bn4b17_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2a\"\n name: \"scale4b17_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2a\"\n bottom: \"res4b17_branch2a\"\n name: \"res4b17_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2b\"\n name: \"res4b17_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2b\"\n name: \"bn4b17_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2b\"\n name: \"scale4b17_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2b\"\n bottom: \"res4b17_branch2b\"\n name: \"res4b17_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2c\"\n name: \"res4b17_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2c\"\n top: \"res4b17_branch2c\"\n name: \"bn4b17_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2c\"\n top: \"res4b17_branch2c\"\n name: \"scale4b17_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16\"\n bottom: \"res4b17_branch2c\"\n top: \"res4b17\"\n name: \"res4b17\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b17\"\n name: \"res4b17_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b18_branch2a\"\n name: \"res4b18_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2a\"\n name: \"bn4b18_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2a\"\n name: \"scale4b18_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2a\"\n bottom: \"res4b18_branch2a\"\n name: \"res4b18_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2b\"\n name: \"res4b18_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2b\"\n name: \"bn4b18_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2b\"\n name: \"scale4b18_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2b\"\n bottom: \"res4b18_branch2b\"\n name: \"res4b18_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2c\"\n name: \"res4b18_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2c\"\n top: \"res4b18_branch2c\"\n name: \"bn4b18_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2c\"\n top: \"res4b18_branch2c\"\n name: \"scale4b18_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17\"\n bottom: \"res4b18_branch2c\"\n top: \"res4b18\"\n name: \"res4b18\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b18\"\n name: \"res4b18_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b19_branch2a\"\n name: \"res4b19_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2a\"\n name: \"bn4b19_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2a\"\n name: \"scale4b19_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2a\"\n bottom: \"res4b19_branch2a\"\n name: \"res4b19_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2b\"\n name: \"res4b19_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2b\"\n name: \"bn4b19_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2b\"\n name: \"scale4b19_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2b\"\n bottom: \"res4b19_branch2b\"\n name: \"res4b19_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2c\"\n name: \"res4b19_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2c\"\n top: \"res4b19_branch2c\"\n name: \"bn4b19_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2c\"\n top: \"res4b19_branch2c\"\n name: \"scale4b19_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18\"\n bottom: \"res4b19_branch2c\"\n top: \"res4b19\"\n name: \"res4b19\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b19\"\n name: \"res4b19_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b20_branch2a\"\n name: \"res4b20_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2a\"\n name: \"bn4b20_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2a\"\n name: \"scale4b20_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2a\"\n bottom: \"res4b20_branch2a\"\n name: \"res4b20_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2b\"\n name: \"res4b20_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2b\"\n name: \"bn4b20_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2b\"\n name: \"scale4b20_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2b\"\n bottom: \"res4b20_branch2b\"\n name: \"res4b20_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2c\"\n name: \"res4b20_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2c\"\n top: \"res4b20_branch2c\"\n name: \"bn4b20_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2c\"\n top: \"res4b20_branch2c\"\n name: \"scale4b20_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19\"\n bottom: \"res4b20_branch2c\"\n top: \"res4b20\"\n name: \"res4b20\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b20\"\n name: \"res4b20_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b21_branch2a\"\n name: \"res4b21_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2a\"\n name: \"bn4b21_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2a\"\n name: \"scale4b21_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2a\"\n bottom: \"res4b21_branch2a\"\n name: \"res4b21_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2b\"\n name: \"res4b21_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2b\"\n name: \"bn4b21_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2b\"\n name: \"scale4b21_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2b\"\n bottom: \"res4b21_branch2b\"\n name: \"res4b21_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2c\"\n name: \"res4b21_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2c\"\n top: \"res4b21_branch2c\"\n name: \"bn4b21_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2c\"\n top: \"res4b21_branch2c\"\n name: \"scale4b21_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20\"\n bottom: \"res4b21_branch2c\"\n top: \"res4b21\"\n name: \"res4b21\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b21\"\n name: \"res4b21_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b22_branch2a\"\n name: \"res4b22_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2a\"\n name: \"bn4b22_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2a\"\n name: \"scale4b22_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2a\"\n bottom: \"res4b22_branch2a\"\n name: \"res4b22_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2b\"\n name: \"res4b22_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2b\"\n name: \"bn4b22_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2b\"\n name: \"scale4b22_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2b\"\n bottom: \"res4b22_branch2b\"\n name: \"res4b22_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2c\"\n name: \"res4b22_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2c\"\n top: \"res4b22_branch2c\"\n name: \"bn4b22_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2c\"\n top: \"res4b22_branch2c\"\n name: \"scale4b22_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21\"\n bottom: \"res4b22_branch2c\"\n top: \"res4b22\"\n name: \"res4b22\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b22\"\n top: \"res4b22\"\n name: \"res4b22_relu\"\n type: \"ReLU\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4b22\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rois'\n top: 'scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n" }, { "path": "models/pascal_voc/ResNet101/faster_rcnn_alt_opt/stage1_fast_rcnn_solver30k40k.pt", "content": "train_net: \"models/pascal_voc/ResNet101/faster_rcnn_alt_opt/stage1_fast_rcnn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 30000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet101_fast_rcnn\"\n" }, { "path": "models/pascal_voc/ResNet101/faster_rcnn_alt_opt/stage1_fast_rcnn_train.pt", "content": "name: \"ResNet101\"\nlayer {\n name: 'data'\n type: 'Python'\n top: 'data'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"conv1\"\n bottom: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2a\"\n bottom: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2b\"\n bottom: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2a\"\n bottom: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2b\"\n bottom: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2a\"\n bottom: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2b\"\n bottom: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2a\"\n bottom: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2b\"\n bottom: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b1_branch2a\"\n name: \"res3b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2a\"\n name: \"bn3b1_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2a\"\n name: \"scale3b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2a\"\n bottom: \"res3b1_branch2a\"\n name: \"res3b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2b\"\n name: \"res3b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2b\"\n name: \"bn3b1_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2b\"\n name: \"scale3b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2b\"\n bottom: \"res3b1_branch2b\"\n name: \"res3b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2c\"\n name: \"res3b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2c\"\n top: \"res3b1_branch2c\"\n name: \"bn3b1_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2c\"\n top: \"res3b1_branch2c\"\n name: \"scale3b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b1_branch2c\"\n top: \"res3b1\"\n name: \"res3b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b1\"\n name: \"res3b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b2_branch2a\"\n name: \"res3b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2a\"\n name: \"bn3b2_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2a\"\n name: \"scale3b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2a\"\n bottom: \"res3b2_branch2a\"\n name: \"res3b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2b\"\n name: \"res3b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2b\"\n name: \"bn3b2_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2b\"\n name: \"scale3b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2b\"\n bottom: \"res3b2_branch2b\"\n name: \"res3b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2c\"\n name: \"res3b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2c\"\n top: \"res3b2_branch2c\"\n name: \"bn3b2_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2c\"\n top: \"res3b2_branch2c\"\n name: \"scale3b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1\"\n bottom: \"res3b2_branch2c\"\n top: \"res3b2\"\n name: \"res3b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b2\"\n name: \"res3b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b3_branch2a\"\n name: \"res3b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2a\"\n name: \"bn3b3_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2a\"\n name: \"scale3b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2a\"\n bottom: \"res3b3_branch2a\"\n name: \"res3b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2b\"\n name: \"res3b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2b\"\n name: \"bn3b3_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2b\"\n name: \"scale3b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2b\"\n bottom: \"res3b3_branch2b\"\n name: \"res3b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2c\"\n name: \"res3b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2c\"\n top: \"res3b3_branch2c\"\n name: \"bn3b3_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2c\"\n top: \"res3b3_branch2c\"\n name: \"scale3b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2\"\n bottom: \"res3b3_branch2c\"\n top: \"res3b3\"\n name: \"res3b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res3b3\"\n name: \"res3b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2a\"\n bottom: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2b\"\n bottom: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b1_branch2a\"\n name: \"res4b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2a\"\n name: \"bn4b1_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2a\"\n name: \"scale4b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2a\"\n bottom: \"res4b1_branch2a\"\n name: \"res4b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2b\"\n name: \"res4b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2b\"\n name: \"bn4b1_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2b\"\n name: \"scale4b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2b\"\n bottom: \"res4b1_branch2b\"\n name: \"res4b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2c\"\n name: \"res4b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2c\"\n top: \"res4b1_branch2c\"\n name: \"bn4b1_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2c\"\n top: \"res4b1_branch2c\"\n name: \"scale4b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b1_branch2c\"\n top: \"res4b1\"\n name: \"res4b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b1\"\n name: \"res4b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b2_branch2a\"\n name: \"res4b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2a\"\n name: \"bn4b2_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2a\"\n name: \"scale4b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2a\"\n bottom: \"res4b2_branch2a\"\n name: \"res4b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2b\"\n name: \"res4b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2b\"\n name: \"bn4b2_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2b\"\n name: \"scale4b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2b\"\n bottom: \"res4b2_branch2b\"\n name: \"res4b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2c\"\n name: \"res4b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2c\"\n top: \"res4b2_branch2c\"\n name: \"bn4b2_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2c\"\n top: \"res4b2_branch2c\"\n name: \"scale4b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1\"\n bottom: \"res4b2_branch2c\"\n top: \"res4b2\"\n name: \"res4b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b2\"\n name: \"res4b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b3_branch2a\"\n name: \"res4b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2a\"\n name: \"bn4b3_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2a\"\n name: \"scale4b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2a\"\n bottom: \"res4b3_branch2a\"\n name: \"res4b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2b\"\n name: \"res4b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2b\"\n name: \"bn4b3_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2b\"\n name: \"scale4b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2b\"\n bottom: \"res4b3_branch2b\"\n name: \"res4b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2c\"\n name: \"res4b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2c\"\n top: \"res4b3_branch2c\"\n name: \"bn4b3_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2c\"\n top: \"res4b3_branch2c\"\n name: \"scale4b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2\"\n bottom: \"res4b3_branch2c\"\n top: \"res4b3\"\n name: \"res4b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b3\"\n name: \"res4b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b4_branch2a\"\n name: \"res4b4_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2a\"\n name: \"bn4b4_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2a\"\n name: \"scale4b4_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2a\"\n bottom: \"res4b4_branch2a\"\n name: \"res4b4_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2b\"\n name: \"res4b4_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2b\"\n name: \"bn4b4_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2b\"\n name: \"scale4b4_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2b\"\n bottom: \"res4b4_branch2b\"\n name: \"res4b4_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2c\"\n name: \"res4b4_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2c\"\n top: \"res4b4_branch2c\"\n name: \"bn4b4_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2c\"\n top: \"res4b4_branch2c\"\n name: \"scale4b4_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3\"\n bottom: \"res4b4_branch2c\"\n top: \"res4b4\"\n name: \"res4b4\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b4\"\n name: \"res4b4_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b5_branch2a\"\n name: \"res4b5_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2a\"\n name: \"bn4b5_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2a\"\n name: \"scale4b5_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2a\"\n bottom: \"res4b5_branch2a\"\n name: \"res4b5_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2b\"\n name: \"res4b5_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2b\"\n name: \"bn4b5_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2b\"\n name: \"scale4b5_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2b\"\n bottom: \"res4b5_branch2b\"\n name: \"res4b5_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2c\"\n name: \"res4b5_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2c\"\n top: \"res4b5_branch2c\"\n name: \"bn4b5_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2c\"\n top: \"res4b5_branch2c\"\n name: \"scale4b5_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4\"\n bottom: \"res4b5_branch2c\"\n top: \"res4b5\"\n name: \"res4b5\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b5\"\n name: \"res4b5_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b6_branch2a\"\n name: \"res4b6_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2a\"\n name: \"bn4b6_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2a\"\n name: \"scale4b6_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2a\"\n bottom: \"res4b6_branch2a\"\n name: \"res4b6_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2b\"\n name: \"res4b6_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2b\"\n name: \"bn4b6_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2b\"\n name: \"scale4b6_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2b\"\n bottom: \"res4b6_branch2b\"\n name: \"res4b6_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2c\"\n name: \"res4b6_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2c\"\n top: \"res4b6_branch2c\"\n name: \"bn4b6_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2c\"\n top: \"res4b6_branch2c\"\n name: \"scale4b6_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5\"\n bottom: \"res4b6_branch2c\"\n top: \"res4b6\"\n name: \"res4b6\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b6\"\n name: \"res4b6_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b7_branch2a\"\n name: \"res4b7_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2a\"\n name: \"bn4b7_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2a\"\n name: \"scale4b7_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2a\"\n bottom: \"res4b7_branch2a\"\n name: \"res4b7_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2b\"\n name: \"res4b7_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2b\"\n name: \"bn4b7_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2b\"\n name: \"scale4b7_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2b\"\n bottom: \"res4b7_branch2b\"\n name: \"res4b7_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2c\"\n name: \"res4b7_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2c\"\n top: \"res4b7_branch2c\"\n name: \"bn4b7_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2c\"\n top: \"res4b7_branch2c\"\n name: \"scale4b7_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6\"\n bottom: \"res4b7_branch2c\"\n top: \"res4b7\"\n name: \"res4b7\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b7\"\n name: \"res4b7_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b8_branch2a\"\n name: \"res4b8_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2a\"\n name: \"bn4b8_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2a\"\n name: \"scale4b8_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2a\"\n bottom: \"res4b8_branch2a\"\n name: \"res4b8_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2b\"\n name: \"res4b8_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2b\"\n name: \"bn4b8_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2b\"\n name: \"scale4b8_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2b\"\n bottom: \"res4b8_branch2b\"\n name: \"res4b8_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2c\"\n name: \"res4b8_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2c\"\n top: \"res4b8_branch2c\"\n name: \"bn4b8_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2c\"\n top: \"res4b8_branch2c\"\n name: \"scale4b8_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7\"\n bottom: \"res4b8_branch2c\"\n top: \"res4b8\"\n name: \"res4b8\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b8\"\n name: \"res4b8_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b9_branch2a\"\n name: \"res4b9_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2a\"\n name: \"bn4b9_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2a\"\n name: \"scale4b9_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2a\"\n bottom: \"res4b9_branch2a\"\n name: \"res4b9_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2b\"\n name: \"res4b9_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2b\"\n name: \"bn4b9_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2b\"\n name: \"scale4b9_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2b\"\n bottom: \"res4b9_branch2b\"\n name: \"res4b9_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2c\"\n name: \"res4b9_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2c\"\n top: \"res4b9_branch2c\"\n name: \"bn4b9_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2c\"\n top: \"res4b9_branch2c\"\n name: \"scale4b9_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8\"\n bottom: \"res4b9_branch2c\"\n top: \"res4b9\"\n name: \"res4b9\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b9\"\n name: \"res4b9_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b10_branch2a\"\n name: \"res4b10_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2a\"\n name: \"bn4b10_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2a\"\n name: \"scale4b10_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2a\"\n bottom: \"res4b10_branch2a\"\n name: \"res4b10_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2b\"\n name: \"res4b10_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2b\"\n name: \"bn4b10_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2b\"\n name: \"scale4b10_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2b\"\n bottom: \"res4b10_branch2b\"\n name: \"res4b10_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2c\"\n name: \"res4b10_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2c\"\n top: \"res4b10_branch2c\"\n name: \"bn4b10_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2c\"\n top: \"res4b10_branch2c\"\n name: \"scale4b10_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9\"\n bottom: \"res4b10_branch2c\"\n top: \"res4b10\"\n name: \"res4b10\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b10\"\n name: \"res4b10_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b11_branch2a\"\n name: \"res4b11_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2a\"\n name: \"bn4b11_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2a\"\n name: \"scale4b11_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2a\"\n bottom: \"res4b11_branch2a\"\n name: \"res4b11_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2b\"\n name: \"res4b11_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2b\"\n name: \"bn4b11_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2b\"\n name: \"scale4b11_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2b\"\n bottom: \"res4b11_branch2b\"\n name: \"res4b11_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2c\"\n name: \"res4b11_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2c\"\n top: \"res4b11_branch2c\"\n name: \"bn4b11_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2c\"\n top: \"res4b11_branch2c\"\n name: \"scale4b11_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10\"\n bottom: \"res4b11_branch2c\"\n top: \"res4b11\"\n name: \"res4b11\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b11\"\n name: \"res4b11_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b12_branch2a\"\n name: \"res4b12_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2a\"\n name: \"bn4b12_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2a\"\n name: \"scale4b12_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2a\"\n bottom: \"res4b12_branch2a\"\n name: \"res4b12_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2b\"\n name: \"res4b12_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2b\"\n name: \"bn4b12_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2b\"\n name: \"scale4b12_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2b\"\n bottom: \"res4b12_branch2b\"\n name: \"res4b12_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2c\"\n name: \"res4b12_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2c\"\n top: \"res4b12_branch2c\"\n name: \"bn4b12_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2c\"\n top: \"res4b12_branch2c\"\n name: \"scale4b12_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11\"\n bottom: \"res4b12_branch2c\"\n top: \"res4b12\"\n name: \"res4b12\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b12\"\n name: \"res4b12_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b13_branch2a\"\n name: \"res4b13_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2a\"\n name: \"bn4b13_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2a\"\n name: \"scale4b13_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2a\"\n bottom: \"res4b13_branch2a\"\n name: \"res4b13_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2b\"\n name: \"res4b13_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2b\"\n name: \"bn4b13_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2b\"\n name: \"scale4b13_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2b\"\n bottom: \"res4b13_branch2b\"\n name: \"res4b13_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2c\"\n name: \"res4b13_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2c\"\n top: \"res4b13_branch2c\"\n name: \"bn4b13_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2c\"\n top: \"res4b13_branch2c\"\n name: \"scale4b13_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12\"\n bottom: \"res4b13_branch2c\"\n top: \"res4b13\"\n name: \"res4b13\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b13\"\n name: \"res4b13_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b14_branch2a\"\n name: \"res4b14_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2a\"\n name: \"bn4b14_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2a\"\n name: \"scale4b14_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2a\"\n bottom: \"res4b14_branch2a\"\n name: \"res4b14_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2b\"\n name: \"res4b14_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2b\"\n name: \"bn4b14_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2b\"\n name: \"scale4b14_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2b\"\n bottom: \"res4b14_branch2b\"\n name: \"res4b14_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2c\"\n name: \"res4b14_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2c\"\n top: \"res4b14_branch2c\"\n name: \"bn4b14_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2c\"\n top: \"res4b14_branch2c\"\n name: \"scale4b14_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13\"\n bottom: \"res4b14_branch2c\"\n top: \"res4b14\"\n name: \"res4b14\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b14\"\n name: \"res4b14_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b15_branch2a\"\n name: \"res4b15_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2a\"\n name: \"bn4b15_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2a\"\n name: \"scale4b15_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2a\"\n bottom: \"res4b15_branch2a\"\n name: \"res4b15_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2b\"\n name: \"res4b15_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2b\"\n name: \"bn4b15_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2b\"\n name: \"scale4b15_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2b\"\n bottom: \"res4b15_branch2b\"\n name: \"res4b15_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2c\"\n name: \"res4b15_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2c\"\n top: \"res4b15_branch2c\"\n name: \"bn4b15_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2c\"\n top: \"res4b15_branch2c\"\n name: \"scale4b15_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14\"\n bottom: \"res4b15_branch2c\"\n top: \"res4b15\"\n name: \"res4b15\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b15\"\n name: \"res4b15_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b16_branch2a\"\n name: \"res4b16_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2a\"\n name: \"bn4b16_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2a\"\n name: \"scale4b16_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2a\"\n bottom: \"res4b16_branch2a\"\n name: \"res4b16_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2b\"\n name: \"res4b16_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2b\"\n name: \"bn4b16_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2b\"\n name: \"scale4b16_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2b\"\n bottom: \"res4b16_branch2b\"\n name: \"res4b16_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2c\"\n name: \"res4b16_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2c\"\n top: \"res4b16_branch2c\"\n name: \"bn4b16_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2c\"\n top: \"res4b16_branch2c\"\n name: \"scale4b16_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15\"\n bottom: \"res4b16_branch2c\"\n top: \"res4b16\"\n name: \"res4b16\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b16\"\n name: \"res4b16_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b17_branch2a\"\n name: \"res4b17_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2a\"\n name: \"bn4b17_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2a\"\n name: \"scale4b17_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2a\"\n bottom: \"res4b17_branch2a\"\n name: \"res4b17_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2b\"\n name: \"res4b17_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2b\"\n name: \"bn4b17_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2b\"\n name: \"scale4b17_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2b\"\n bottom: \"res4b17_branch2b\"\n name: \"res4b17_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2c\"\n name: \"res4b17_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2c\"\n top: \"res4b17_branch2c\"\n name: \"bn4b17_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2c\"\n top: \"res4b17_branch2c\"\n name: \"scale4b17_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16\"\n bottom: \"res4b17_branch2c\"\n top: \"res4b17\"\n name: \"res4b17\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b17\"\n name: \"res4b17_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b18_branch2a\"\n name: \"res4b18_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2a\"\n name: \"bn4b18_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2a\"\n name: \"scale4b18_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2a\"\n bottom: \"res4b18_branch2a\"\n name: \"res4b18_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2b\"\n name: \"res4b18_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2b\"\n name: \"bn4b18_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2b\"\n name: \"scale4b18_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2b\"\n bottom: \"res4b18_branch2b\"\n name: \"res4b18_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2c\"\n name: \"res4b18_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2c\"\n top: \"res4b18_branch2c\"\n name: \"bn4b18_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2c\"\n top: \"res4b18_branch2c\"\n name: \"scale4b18_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17\"\n bottom: \"res4b18_branch2c\"\n top: \"res4b18\"\n name: \"res4b18\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b18\"\n name: \"res4b18_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b19_branch2a\"\n name: \"res4b19_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2a\"\n name: \"bn4b19_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2a\"\n name: \"scale4b19_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2a\"\n bottom: \"res4b19_branch2a\"\n name: \"res4b19_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2b\"\n name: \"res4b19_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2b\"\n name: \"bn4b19_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2b\"\n name: \"scale4b19_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2b\"\n bottom: \"res4b19_branch2b\"\n name: \"res4b19_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2c\"\n name: \"res4b19_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2c\"\n top: \"res4b19_branch2c\"\n name: \"bn4b19_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2c\"\n top: \"res4b19_branch2c\"\n name: \"scale4b19_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18\"\n bottom: \"res4b19_branch2c\"\n top: \"res4b19\"\n name: \"res4b19\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b19\"\n name: \"res4b19_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b20_branch2a\"\n name: \"res4b20_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2a\"\n name: \"bn4b20_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2a\"\n name: \"scale4b20_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2a\"\n bottom: \"res4b20_branch2a\"\n name: \"res4b20_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2b\"\n name: \"res4b20_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2b\"\n name: \"bn4b20_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2b\"\n name: \"scale4b20_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2b\"\n bottom: \"res4b20_branch2b\"\n name: \"res4b20_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2c\"\n name: \"res4b20_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2c\"\n top: \"res4b20_branch2c\"\n name: \"bn4b20_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2c\"\n top: \"res4b20_branch2c\"\n name: \"scale4b20_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19\"\n bottom: \"res4b20_branch2c\"\n top: \"res4b20\"\n name: \"res4b20\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b20\"\n name: \"res4b20_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b21_branch2a\"\n name: \"res4b21_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2a\"\n name: \"bn4b21_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2a\"\n name: \"scale4b21_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2a\"\n bottom: \"res4b21_branch2a\"\n name: \"res4b21_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2b\"\n name: \"res4b21_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2b\"\n name: \"bn4b21_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2b\"\n name: \"scale4b21_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2b\"\n bottom: \"res4b21_branch2b\"\n name: \"res4b21_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2c\"\n name: \"res4b21_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2c\"\n top: \"res4b21_branch2c\"\n name: \"bn4b21_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2c\"\n top: \"res4b21_branch2c\"\n name: \"scale4b21_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20\"\n bottom: \"res4b21_branch2c\"\n top: \"res4b21\"\n name: \"res4b21\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b21\"\n name: \"res4b21_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b22_branch2a\"\n name: \"res4b22_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2a\"\n name: \"bn4b22_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2a\"\n name: \"scale4b22_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2a\"\n bottom: \"res4b22_branch2a\"\n name: \"res4b22_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2b\"\n name: \"res4b22_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2b\"\n name: \"bn4b22_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2b\"\n name: \"scale4b22_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2b\"\n bottom: \"res4b22_branch2b\"\n name: \"res4b22_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2c\"\n name: \"res4b22_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2c\"\n top: \"res4b22_branch2c\"\n name: \"bn4b22_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2c\"\n top: \"res4b22_branch2c\"\n name: \"scale4b22_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21\"\n bottom: \"res4b22_branch2c\"\n top: \"res4b22\"\n name: \"res4b22\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b22\"\n top: \"res4b22\"\n name: \"res4b22_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"res4b22\"\n bottom: \"rois\"\n top: \"roi_pool5\"\n roi_pooling_param {\n pooled_w: 14\n pooled_h: 14\n spatial_scale: 0.0625 # 1/16\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"bn5a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"bn5a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"bn5a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"bn5a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"bn5b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"bn5b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"bn5b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"bn5c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"bn5c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"bn5c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\n\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"loss_bbox\"\n loss_weight: 1\n}\n\n\n#========= RPN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4b22\"\n top: \"rpn/output\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"silence_rpn_cls_score\"\n type: \"Silence\"\n bottom: \"rpn_cls_score\"\n}\nlayer {\n name: \"silence_rpn_bbox_pred\"\n type: \"Silence\"\n bottom: \"rpn_bbox_pred\"\n}\n" }, { "path": "models/pascal_voc/ResNet101/faster_rcnn_alt_opt/stage1_rpn_solver60k80k.pt", "content": "train_net: \"models/pascal_voc/ResNet101/faster_rcnn_alt_opt/stage1_rpn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 60000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet101_rpn\"\n" }, { "path": "models/pascal_voc/ResNet101/faster_rcnn_alt_opt/stage1_rpn_train.pt", "content": "name: \"ResNet101\"\n\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"conv1\"\n bottom: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2a\"\n bottom: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2b\"\n bottom: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2a\"\n bottom: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2b\"\n bottom: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2a\"\n bottom: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2b\"\n bottom: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2a\"\n bottom: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2b\"\n bottom: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b1_branch2a\"\n name: \"res3b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2a\"\n name: \"bn3b1_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2a\"\n name: \"scale3b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2a\"\n bottom: \"res3b1_branch2a\"\n name: \"res3b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2b\"\n name: \"res3b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2b\"\n name: \"bn3b1_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2b\"\n name: \"scale3b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2b\"\n bottom: \"res3b1_branch2b\"\n name: \"res3b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2c\"\n name: \"res3b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2c\"\n top: \"res3b1_branch2c\"\n name: \"bn3b1_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2c\"\n top: \"res3b1_branch2c\"\n name: \"scale3b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b1_branch2c\"\n top: \"res3b1\"\n name: \"res3b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b1\"\n name: \"res3b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b2_branch2a\"\n name: \"res3b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2a\"\n name: \"bn3b2_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2a\"\n name: \"scale3b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2a\"\n bottom: \"res3b2_branch2a\"\n name: \"res3b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2b\"\n name: \"res3b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2b\"\n name: \"bn3b2_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2b\"\n name: \"scale3b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2b\"\n bottom: \"res3b2_branch2b\"\n name: \"res3b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2c\"\n name: \"res3b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2c\"\n top: \"res3b2_branch2c\"\n name: \"bn3b2_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2c\"\n top: \"res3b2_branch2c\"\n name: \"scale3b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1\"\n bottom: \"res3b2_branch2c\"\n top: \"res3b2\"\n name: \"res3b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b2\"\n name: \"res3b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b3_branch2a\"\n name: \"res3b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2a\"\n name: \"bn3b3_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2a\"\n name: \"scale3b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2a\"\n bottom: \"res3b3_branch2a\"\n name: \"res3b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2b\"\n name: \"res3b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2b\"\n name: \"bn3b3_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2b\"\n name: \"scale3b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2b\"\n bottom: \"res3b3_branch2b\"\n name: \"res3b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2c\"\n name: \"res3b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2c\"\n top: \"res3b3_branch2c\"\n name: \"bn3b3_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2c\"\n top: \"res3b3_branch2c\"\n name: \"scale3b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2\"\n bottom: \"res3b3_branch2c\"\n top: \"res3b3\"\n name: \"res3b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res3b3\"\n name: \"res3b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2a\"\n bottom: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2b\"\n bottom: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b1_branch2a\"\n name: \"res4b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2a\"\n name: \"bn4b1_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2a\"\n name: \"scale4b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2a\"\n bottom: \"res4b1_branch2a\"\n name: \"res4b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2b\"\n name: \"res4b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2b\"\n name: \"bn4b1_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2b\"\n name: \"scale4b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2b\"\n bottom: \"res4b1_branch2b\"\n name: \"res4b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2c\"\n name: \"res4b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2c\"\n top: \"res4b1_branch2c\"\n name: \"bn4b1_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2c\"\n top: \"res4b1_branch2c\"\n name: \"scale4b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b1_branch2c\"\n top: \"res4b1\"\n name: \"res4b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b1\"\n name: \"res4b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b2_branch2a\"\n name: \"res4b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2a\"\n name: \"bn4b2_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2a\"\n name: \"scale4b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2a\"\n bottom: \"res4b2_branch2a\"\n name: \"res4b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2b\"\n name: \"res4b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2b\"\n name: \"bn4b2_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2b\"\n name: \"scale4b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2b\"\n bottom: \"res4b2_branch2b\"\n name: \"res4b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2c\"\n name: \"res4b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2c\"\n top: \"res4b2_branch2c\"\n name: \"bn4b2_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2c\"\n top: \"res4b2_branch2c\"\n name: \"scale4b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1\"\n bottom: \"res4b2_branch2c\"\n top: \"res4b2\"\n name: \"res4b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b2\"\n name: \"res4b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b3_branch2a\"\n name: \"res4b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2a\"\n name: \"bn4b3_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2a\"\n name: \"scale4b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2a\"\n bottom: \"res4b3_branch2a\"\n name: \"res4b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2b\"\n name: \"res4b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2b\"\n name: \"bn4b3_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2b\"\n name: \"scale4b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2b\"\n bottom: \"res4b3_branch2b\"\n name: \"res4b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2c\"\n name: \"res4b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2c\"\n top: \"res4b3_branch2c\"\n name: \"bn4b3_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2c\"\n top: \"res4b3_branch2c\"\n name: \"scale4b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2\"\n bottom: \"res4b3_branch2c\"\n top: \"res4b3\"\n name: \"res4b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b3\"\n name: \"res4b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b4_branch2a\"\n name: \"res4b4_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2a\"\n name: \"bn4b4_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2a\"\n name: \"scale4b4_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2a\"\n bottom: \"res4b4_branch2a\"\n name: \"res4b4_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2b\"\n name: \"res4b4_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2b\"\n name: \"bn4b4_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2b\"\n name: \"scale4b4_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2b\"\n bottom: \"res4b4_branch2b\"\n name: \"res4b4_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2c\"\n name: \"res4b4_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2c\"\n top: \"res4b4_branch2c\"\n name: \"bn4b4_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2c\"\n top: \"res4b4_branch2c\"\n name: \"scale4b4_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3\"\n bottom: \"res4b4_branch2c\"\n top: \"res4b4\"\n name: \"res4b4\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b4\"\n name: \"res4b4_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b5_branch2a\"\n name: \"res4b5_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2a\"\n name: \"bn4b5_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2a\"\n name: \"scale4b5_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2a\"\n bottom: \"res4b5_branch2a\"\n name: \"res4b5_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2b\"\n name: \"res4b5_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2b\"\n name: \"bn4b5_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2b\"\n name: \"scale4b5_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2b\"\n bottom: \"res4b5_branch2b\"\n name: \"res4b5_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2c\"\n name: \"res4b5_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2c\"\n top: \"res4b5_branch2c\"\n name: \"bn4b5_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2c\"\n top: \"res4b5_branch2c\"\n name: \"scale4b5_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4\"\n bottom: \"res4b5_branch2c\"\n top: \"res4b5\"\n name: \"res4b5\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b5\"\n name: \"res4b5_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b6_branch2a\"\n name: \"res4b6_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2a\"\n name: \"bn4b6_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2a\"\n name: \"scale4b6_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2a\"\n bottom: \"res4b6_branch2a\"\n name: \"res4b6_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2b\"\n name: \"res4b6_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2b\"\n name: \"bn4b6_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2b\"\n name: \"scale4b6_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2b\"\n bottom: \"res4b6_branch2b\"\n name: \"res4b6_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2c\"\n name: \"res4b6_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2c\"\n top: \"res4b6_branch2c\"\n name: \"bn4b6_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2c\"\n top: \"res4b6_branch2c\"\n name: \"scale4b6_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5\"\n bottom: \"res4b6_branch2c\"\n top: \"res4b6\"\n name: \"res4b6\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b6\"\n name: \"res4b6_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b7_branch2a\"\n name: \"res4b7_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2a\"\n name: \"bn4b7_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2a\"\n name: \"scale4b7_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2a\"\n bottom: \"res4b7_branch2a\"\n name: \"res4b7_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2b\"\n name: \"res4b7_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2b\"\n name: \"bn4b7_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2b\"\n name: \"scale4b7_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2b\"\n bottom: \"res4b7_branch2b\"\n name: \"res4b7_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2c\"\n name: \"res4b7_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2c\"\n top: \"res4b7_branch2c\"\n name: \"bn4b7_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2c\"\n top: \"res4b7_branch2c\"\n name: \"scale4b7_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6\"\n bottom: \"res4b7_branch2c\"\n top: \"res4b7\"\n name: \"res4b7\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b7\"\n name: \"res4b7_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b8_branch2a\"\n name: \"res4b8_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2a\"\n name: \"bn4b8_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2a\"\n name: \"scale4b8_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2a\"\n bottom: \"res4b8_branch2a\"\n name: \"res4b8_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2b\"\n name: \"res4b8_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2b\"\n name: \"bn4b8_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2b\"\n name: \"scale4b8_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2b\"\n bottom: \"res4b8_branch2b\"\n name: \"res4b8_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2c\"\n name: \"res4b8_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2c\"\n top: \"res4b8_branch2c\"\n name: \"bn4b8_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2c\"\n top: \"res4b8_branch2c\"\n name: \"scale4b8_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7\"\n bottom: \"res4b8_branch2c\"\n top: \"res4b8\"\n name: \"res4b8\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b8\"\n name: \"res4b8_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b9_branch2a\"\n name: \"res4b9_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2a\"\n name: \"bn4b9_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2a\"\n name: \"scale4b9_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2a\"\n bottom: \"res4b9_branch2a\"\n name: \"res4b9_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2b\"\n name: \"res4b9_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2b\"\n name: \"bn4b9_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2b\"\n name: \"scale4b9_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2b\"\n bottom: \"res4b9_branch2b\"\n name: \"res4b9_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2c\"\n name: \"res4b9_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2c\"\n top: \"res4b9_branch2c\"\n name: \"bn4b9_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2c\"\n top: \"res4b9_branch2c\"\n name: \"scale4b9_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8\"\n bottom: \"res4b9_branch2c\"\n top: \"res4b9\"\n name: \"res4b9\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b9\"\n name: \"res4b9_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b10_branch2a\"\n name: \"res4b10_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2a\"\n name: \"bn4b10_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2a\"\n name: \"scale4b10_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2a\"\n bottom: \"res4b10_branch2a\"\n name: \"res4b10_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2b\"\n name: \"res4b10_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2b\"\n name: \"bn4b10_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2b\"\n name: \"scale4b10_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2b\"\n bottom: \"res4b10_branch2b\"\n name: \"res4b10_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2c\"\n name: \"res4b10_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2c\"\n top: \"res4b10_branch2c\"\n name: \"bn4b10_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2c\"\n top: \"res4b10_branch2c\"\n name: \"scale4b10_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9\"\n bottom: \"res4b10_branch2c\"\n top: \"res4b10\"\n name: \"res4b10\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b10\"\n name: \"res4b10_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b11_branch2a\"\n name: \"res4b11_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2a\"\n name: \"bn4b11_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2a\"\n name: \"scale4b11_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2a\"\n bottom: \"res4b11_branch2a\"\n name: \"res4b11_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2b\"\n name: \"res4b11_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2b\"\n name: \"bn4b11_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2b\"\n name: \"scale4b11_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2b\"\n bottom: \"res4b11_branch2b\"\n name: \"res4b11_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2c\"\n name: \"res4b11_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2c\"\n top: \"res4b11_branch2c\"\n name: \"bn4b11_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2c\"\n top: \"res4b11_branch2c\"\n name: \"scale4b11_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10\"\n bottom: \"res4b11_branch2c\"\n top: \"res4b11\"\n name: \"res4b11\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b11\"\n name: \"res4b11_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b12_branch2a\"\n name: \"res4b12_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2a\"\n name: \"bn4b12_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2a\"\n name: \"scale4b12_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2a\"\n bottom: \"res4b12_branch2a\"\n name: \"res4b12_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2b\"\n name: \"res4b12_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2b\"\n name: \"bn4b12_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2b\"\n name: \"scale4b12_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2b\"\n bottom: \"res4b12_branch2b\"\n name: \"res4b12_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2c\"\n name: \"res4b12_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2c\"\n top: \"res4b12_branch2c\"\n name: \"bn4b12_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2c\"\n top: \"res4b12_branch2c\"\n name: \"scale4b12_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11\"\n bottom: \"res4b12_branch2c\"\n top: \"res4b12\"\n name: \"res4b12\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b12\"\n name: \"res4b12_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b13_branch2a\"\n name: \"res4b13_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2a\"\n name: \"bn4b13_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2a\"\n name: \"scale4b13_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2a\"\n bottom: \"res4b13_branch2a\"\n name: \"res4b13_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2b\"\n name: \"res4b13_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2b\"\n name: \"bn4b13_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2b\"\n name: \"scale4b13_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2b\"\n bottom: \"res4b13_branch2b\"\n name: \"res4b13_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2c\"\n name: \"res4b13_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2c\"\n top: \"res4b13_branch2c\"\n name: \"bn4b13_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2c\"\n top: \"res4b13_branch2c\"\n name: \"scale4b13_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12\"\n bottom: \"res4b13_branch2c\"\n top: \"res4b13\"\n name: \"res4b13\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b13\"\n name: \"res4b13_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b14_branch2a\"\n name: \"res4b14_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2a\"\n name: \"bn4b14_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2a\"\n name: \"scale4b14_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2a\"\n bottom: \"res4b14_branch2a\"\n name: \"res4b14_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2b\"\n name: \"res4b14_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2b\"\n name: \"bn4b14_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2b\"\n name: \"scale4b14_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2b\"\n bottom: \"res4b14_branch2b\"\n name: \"res4b14_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2c\"\n name: \"res4b14_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2c\"\n top: \"res4b14_branch2c\"\n name: \"bn4b14_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2c\"\n top: \"res4b14_branch2c\"\n name: \"scale4b14_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13\"\n bottom: \"res4b14_branch2c\"\n top: \"res4b14\"\n name: \"res4b14\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b14\"\n name: \"res4b14_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b15_branch2a\"\n name: \"res4b15_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2a\"\n name: \"bn4b15_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2a\"\n name: \"scale4b15_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2a\"\n bottom: \"res4b15_branch2a\"\n name: \"res4b15_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2b\"\n name: \"res4b15_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2b\"\n name: \"bn4b15_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2b\"\n name: \"scale4b15_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2b\"\n bottom: \"res4b15_branch2b\"\n name: \"res4b15_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2c\"\n name: \"res4b15_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2c\"\n top: \"res4b15_branch2c\"\n name: \"bn4b15_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2c\"\n top: \"res4b15_branch2c\"\n name: \"scale4b15_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14\"\n bottom: \"res4b15_branch2c\"\n top: \"res4b15\"\n name: \"res4b15\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b15\"\n name: \"res4b15_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b16_branch2a\"\n name: \"res4b16_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2a\"\n name: \"bn4b16_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2a\"\n name: \"scale4b16_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2a\"\n bottom: \"res4b16_branch2a\"\n name: \"res4b16_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2b\"\n name: \"res4b16_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2b\"\n name: \"bn4b16_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2b\"\n name: \"scale4b16_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2b\"\n bottom: \"res4b16_branch2b\"\n name: \"res4b16_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2c\"\n name: \"res4b16_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2c\"\n top: \"res4b16_branch2c\"\n name: \"bn4b16_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2c\"\n top: \"res4b16_branch2c\"\n name: \"scale4b16_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15\"\n bottom: \"res4b16_branch2c\"\n top: \"res4b16\"\n name: \"res4b16\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b16\"\n name: \"res4b16_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b17_branch2a\"\n name: \"res4b17_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2a\"\n name: \"bn4b17_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2a\"\n name: \"scale4b17_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2a\"\n bottom: \"res4b17_branch2a\"\n name: \"res4b17_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2b\"\n name: \"res4b17_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2b\"\n name: \"bn4b17_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2b\"\n name: \"scale4b17_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2b\"\n bottom: \"res4b17_branch2b\"\n name: \"res4b17_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2c\"\n name: \"res4b17_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2c\"\n top: \"res4b17_branch2c\"\n name: \"bn4b17_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2c\"\n top: \"res4b17_branch2c\"\n name: \"scale4b17_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16\"\n bottom: \"res4b17_branch2c\"\n top: \"res4b17\"\n name: \"res4b17\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b17\"\n name: \"res4b17_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b18_branch2a\"\n name: \"res4b18_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2a\"\n name: \"bn4b18_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2a\"\n name: \"scale4b18_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2a\"\n bottom: \"res4b18_branch2a\"\n name: \"res4b18_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2b\"\n name: \"res4b18_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2b\"\n name: \"bn4b18_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2b\"\n name: \"scale4b18_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2b\"\n bottom: \"res4b18_branch2b\"\n name: \"res4b18_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2c\"\n name: \"res4b18_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2c\"\n top: \"res4b18_branch2c\"\n name: \"bn4b18_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2c\"\n top: \"res4b18_branch2c\"\n name: \"scale4b18_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17\"\n bottom: \"res4b18_branch2c\"\n top: \"res4b18\"\n name: \"res4b18\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b18\"\n name: \"res4b18_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b19_branch2a\"\n name: \"res4b19_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2a\"\n name: \"bn4b19_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2a\"\n name: \"scale4b19_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2a\"\n bottom: \"res4b19_branch2a\"\n name: \"res4b19_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2b\"\n name: \"res4b19_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2b\"\n name: \"bn4b19_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2b\"\n name: \"scale4b19_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2b\"\n bottom: \"res4b19_branch2b\"\n name: \"res4b19_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2c\"\n name: \"res4b19_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2c\"\n top: \"res4b19_branch2c\"\n name: \"bn4b19_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2c\"\n top: \"res4b19_branch2c\"\n name: \"scale4b19_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18\"\n bottom: \"res4b19_branch2c\"\n top: \"res4b19\"\n name: \"res4b19\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b19\"\n name: \"res4b19_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b20_branch2a\"\n name: \"res4b20_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2a\"\n name: \"bn4b20_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2a\"\n name: \"scale4b20_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2a\"\n bottom: \"res4b20_branch2a\"\n name: \"res4b20_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2b\"\n name: \"res4b20_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2b\"\n name: \"bn4b20_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2b\"\n name: \"scale4b20_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2b\"\n bottom: \"res4b20_branch2b\"\n name: \"res4b20_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2c\"\n name: \"res4b20_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2c\"\n top: \"res4b20_branch2c\"\n name: \"bn4b20_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2c\"\n top: \"res4b20_branch2c\"\n name: \"scale4b20_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19\"\n bottom: \"res4b20_branch2c\"\n top: \"res4b20\"\n name: \"res4b20\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b20\"\n name: \"res4b20_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b21_branch2a\"\n name: \"res4b21_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2a\"\n name: \"bn4b21_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2a\"\n name: \"scale4b21_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2a\"\n bottom: \"res4b21_branch2a\"\n name: \"res4b21_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2b\"\n name: \"res4b21_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2b\"\n name: \"bn4b21_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2b\"\n name: \"scale4b21_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2b\"\n bottom: \"res4b21_branch2b\"\n name: \"res4b21_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2c\"\n name: \"res4b21_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2c\"\n top: \"res4b21_branch2c\"\n name: \"bn4b21_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2c\"\n top: \"res4b21_branch2c\"\n name: \"scale4b21_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20\"\n bottom: \"res4b21_branch2c\"\n top: \"res4b21\"\n name: \"res4b21\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b21\"\n name: \"res4b21_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b22_branch2a\"\n name: \"res4b22_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2a\"\n name: \"bn4b22_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2a\"\n name: \"scale4b22_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2a\"\n bottom: \"res4b22_branch2a\"\n name: \"res4b22_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2b\"\n name: \"res4b22_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2b\"\n name: \"bn4b22_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2b\"\n name: \"scale4b22_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2b\"\n bottom: \"res4b22_branch2b\"\n name: \"res4b22_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2c\"\n name: \"res4b22_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2c\"\n top: \"res4b22_branch2c\"\n name: \"bn4b22_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2c\"\n top: \"res4b22_branch2c\"\n name: \"scale4b22_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21\"\n bottom: \"res4b22_branch2c\"\n top: \"res4b22\"\n name: \"res4b22\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b22\"\n top: \"res4b22\"\n name: \"res4b22_relu\"\n type: \"ReLU\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4b22\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RCNN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"dummy_roi_pool_res4b22\"\n type: \"DummyData\"\n top: \"dummy_roi_pool_res4b22\"\n dummy_data_param {\n shape { dim: 1 dim: 1024 dim: 14 dim: 14 }\n data_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"dummy_roi_pool_res4b22\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"bn5a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"dummy_roi_pool_res4b22\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"bn5a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"bn5a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"bn5a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"bn5b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"bn5b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"bn5b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"bn5c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"bn5c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"bn5c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\nlayer {\n name: \"silence_pool5\"\n type: \"Silence\"\n bottom: \"pool5\"\n}\n" }, { "path": "models/pascal_voc/ResNet101/faster_rcnn_alt_opt/stage2_fast_rcnn_solver30k40k.pt", "content": "train_net: \"models/pascal_voc/ResNet101/faster_rcnn_alt_opt/stage2_fast_rcnn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 30000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet101_fast_rcnn\"\n" }, { "path": "models/pascal_voc/ResNet101/faster_rcnn_alt_opt/stage2_fast_rcnn_train.pt", "content": "name: \"ResNet101\"\nlayer {\n name: 'data'\n type: 'Python'\n top: 'data'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"conv1\"\n bottom: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2a\"\n bottom: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2b\"\n bottom: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2a\"\n bottom: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2b\"\n bottom: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2a\"\n bottom: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2b\"\n bottom: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2a\"\n bottom: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2b\"\n bottom: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b1_branch2a\"\n name: \"res3b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2a\"\n name: \"bn3b1_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2a\"\n name: \"scale3b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2a\"\n bottom: \"res3b1_branch2a\"\n name: \"res3b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2b\"\n name: \"res3b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2b\"\n name: \"bn3b1_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2b\"\n name: \"scale3b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2b\"\n bottom: \"res3b1_branch2b\"\n name: \"res3b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2c\"\n name: \"res3b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2c\"\n top: \"res3b1_branch2c\"\n name: \"bn3b1_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2c\"\n top: \"res3b1_branch2c\"\n name: \"scale3b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b1_branch2c\"\n top: \"res3b1\"\n name: \"res3b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b1\"\n name: \"res3b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b2_branch2a\"\n name: \"res3b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2a\"\n name: \"bn3b2_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2a\"\n name: \"scale3b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2a\"\n bottom: \"res3b2_branch2a\"\n name: \"res3b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2b\"\n name: \"res3b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2b\"\n name: \"bn3b2_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2b\"\n name: \"scale3b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2b\"\n bottom: \"res3b2_branch2b\"\n name: \"res3b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2c\"\n name: \"res3b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2c\"\n top: \"res3b2_branch2c\"\n name: \"bn3b2_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2c\"\n top: \"res3b2_branch2c\"\n name: \"scale3b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1\"\n bottom: \"res3b2_branch2c\"\n top: \"res3b2\"\n name: \"res3b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b2\"\n name: \"res3b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b3_branch2a\"\n name: \"res3b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2a\"\n name: \"bn3b3_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2a\"\n name: \"scale3b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2a\"\n bottom: \"res3b3_branch2a\"\n name: \"res3b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2b\"\n name: \"res3b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2b\"\n name: \"bn3b3_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2b\"\n name: \"scale3b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2b\"\n bottom: \"res3b3_branch2b\"\n name: \"res3b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2c\"\n name: \"res3b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2c\"\n top: \"res3b3_branch2c\"\n name: \"bn3b3_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2c\"\n top: \"res3b3_branch2c\"\n name: \"scale3b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2\"\n bottom: \"res3b3_branch2c\"\n top: \"res3b3\"\n name: \"res3b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res3b3\"\n name: \"res3b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2a\"\n bottom: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2b\"\n bottom: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b1_branch2a\"\n name: \"res4b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2a\"\n name: \"bn4b1_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2a\"\n name: \"scale4b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2a\"\n bottom: \"res4b1_branch2a\"\n name: \"res4b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2b\"\n name: \"res4b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2b\"\n name: \"bn4b1_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2b\"\n name: \"scale4b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2b\"\n bottom: \"res4b1_branch2b\"\n name: \"res4b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2c\"\n name: \"res4b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2c\"\n top: \"res4b1_branch2c\"\n name: \"bn4b1_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2c\"\n top: \"res4b1_branch2c\"\n name: \"scale4b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b1_branch2c\"\n top: \"res4b1\"\n name: \"res4b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b1\"\n name: \"res4b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b2_branch2a\"\n name: \"res4b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2a\"\n name: \"bn4b2_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2a\"\n name: \"scale4b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2a\"\n bottom: \"res4b2_branch2a\"\n name: \"res4b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2b\"\n name: \"res4b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2b\"\n name: \"bn4b2_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2b\"\n name: \"scale4b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2b\"\n bottom: \"res4b2_branch2b\"\n name: \"res4b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2c\"\n name: \"res4b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2c\"\n top: \"res4b2_branch2c\"\n name: \"bn4b2_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2c\"\n top: \"res4b2_branch2c\"\n name: \"scale4b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1\"\n bottom: \"res4b2_branch2c\"\n top: \"res4b2\"\n name: \"res4b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b2\"\n name: \"res4b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b3_branch2a\"\n name: \"res4b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2a\"\n name: \"bn4b3_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2a\"\n name: \"scale4b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2a\"\n bottom: \"res4b3_branch2a\"\n name: \"res4b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2b\"\n name: \"res4b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2b\"\n name: \"bn4b3_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2b\"\n name: \"scale4b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2b\"\n bottom: \"res4b3_branch2b\"\n name: \"res4b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2c\"\n name: \"res4b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2c\"\n top: \"res4b3_branch2c\"\n name: \"bn4b3_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2c\"\n top: \"res4b3_branch2c\"\n name: \"scale4b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2\"\n bottom: \"res4b3_branch2c\"\n top: \"res4b3\"\n name: \"res4b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b3\"\n name: \"res4b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b4_branch2a\"\n name: \"res4b4_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2a\"\n name: \"bn4b4_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2a\"\n name: \"scale4b4_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2a\"\n bottom: \"res4b4_branch2a\"\n name: \"res4b4_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2b\"\n name: \"res4b4_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2b\"\n name: \"bn4b4_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2b\"\n name: \"scale4b4_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2b\"\n bottom: \"res4b4_branch2b\"\n name: \"res4b4_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2c\"\n name: \"res4b4_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2c\"\n top: \"res4b4_branch2c\"\n name: \"bn4b4_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2c\"\n top: \"res4b4_branch2c\"\n name: \"scale4b4_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3\"\n bottom: \"res4b4_branch2c\"\n top: \"res4b4\"\n name: \"res4b4\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b4\"\n name: \"res4b4_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b5_branch2a\"\n name: \"res4b5_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2a\"\n name: \"bn4b5_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2a\"\n name: \"scale4b5_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2a\"\n bottom: \"res4b5_branch2a\"\n name: \"res4b5_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2b\"\n name: \"res4b5_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2b\"\n name: \"bn4b5_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2b\"\n name: \"scale4b5_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2b\"\n bottom: \"res4b5_branch2b\"\n name: \"res4b5_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2c\"\n name: \"res4b5_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2c\"\n top: \"res4b5_branch2c\"\n name: \"bn4b5_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2c\"\n top: \"res4b5_branch2c\"\n name: \"scale4b5_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4\"\n bottom: \"res4b5_branch2c\"\n top: \"res4b5\"\n name: \"res4b5\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b5\"\n name: \"res4b5_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b6_branch2a\"\n name: \"res4b6_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2a\"\n name: \"bn4b6_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2a\"\n name: \"scale4b6_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2a\"\n bottom: \"res4b6_branch2a\"\n name: \"res4b6_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2b\"\n name: \"res4b6_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2b\"\n name: \"bn4b6_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2b\"\n name: \"scale4b6_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2b\"\n bottom: \"res4b6_branch2b\"\n name: \"res4b6_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2c\"\n name: \"res4b6_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2c\"\n top: \"res4b6_branch2c\"\n name: \"bn4b6_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2c\"\n top: \"res4b6_branch2c\"\n name: \"scale4b6_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5\"\n bottom: \"res4b6_branch2c\"\n top: \"res4b6\"\n name: \"res4b6\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b6\"\n name: \"res4b6_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b7_branch2a\"\n name: \"res4b7_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2a\"\n name: \"bn4b7_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2a\"\n name: \"scale4b7_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2a\"\n bottom: \"res4b7_branch2a\"\n name: \"res4b7_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2b\"\n name: \"res4b7_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2b\"\n name: \"bn4b7_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2b\"\n name: \"scale4b7_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2b\"\n bottom: \"res4b7_branch2b\"\n name: \"res4b7_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2c\"\n name: \"res4b7_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2c\"\n top: \"res4b7_branch2c\"\n name: \"bn4b7_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2c\"\n top: \"res4b7_branch2c\"\n name: \"scale4b7_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6\"\n bottom: \"res4b7_branch2c\"\n top: \"res4b7\"\n name: \"res4b7\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b7\"\n name: \"res4b7_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b8_branch2a\"\n name: \"res4b8_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2a\"\n name: \"bn4b8_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2a\"\n name: \"scale4b8_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2a\"\n bottom: \"res4b8_branch2a\"\n name: \"res4b8_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2b\"\n name: \"res4b8_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2b\"\n name: \"bn4b8_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2b\"\n name: \"scale4b8_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2b\"\n bottom: \"res4b8_branch2b\"\n name: \"res4b8_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2c\"\n name: \"res4b8_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2c\"\n top: \"res4b8_branch2c\"\n name: \"bn4b8_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2c\"\n top: \"res4b8_branch2c\"\n name: \"scale4b8_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7\"\n bottom: \"res4b8_branch2c\"\n top: \"res4b8\"\n name: \"res4b8\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b8\"\n name: \"res4b8_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b9_branch2a\"\n name: \"res4b9_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2a\"\n name: \"bn4b9_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2a\"\n name: \"scale4b9_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2a\"\n bottom: \"res4b9_branch2a\"\n name: \"res4b9_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2b\"\n name: \"res4b9_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2b\"\n name: \"bn4b9_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2b\"\n name: \"scale4b9_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2b\"\n bottom: \"res4b9_branch2b\"\n name: \"res4b9_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2c\"\n name: \"res4b9_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2c\"\n top: \"res4b9_branch2c\"\n name: \"bn4b9_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2c\"\n top: \"res4b9_branch2c\"\n name: \"scale4b9_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8\"\n bottom: \"res4b9_branch2c\"\n top: \"res4b9\"\n name: \"res4b9\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b9\"\n name: \"res4b9_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b10_branch2a\"\n name: \"res4b10_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2a\"\n name: \"bn4b10_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2a\"\n name: \"scale4b10_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2a\"\n bottom: \"res4b10_branch2a\"\n name: \"res4b10_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2b\"\n name: \"res4b10_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2b\"\n name: \"bn4b10_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2b\"\n name: \"scale4b10_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2b\"\n bottom: \"res4b10_branch2b\"\n name: \"res4b10_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2c\"\n name: \"res4b10_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2c\"\n top: \"res4b10_branch2c\"\n name: \"bn4b10_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2c\"\n top: \"res4b10_branch2c\"\n name: \"scale4b10_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9\"\n bottom: \"res4b10_branch2c\"\n top: \"res4b10\"\n name: \"res4b10\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b10\"\n name: \"res4b10_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b11_branch2a\"\n name: \"res4b11_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2a\"\n name: \"bn4b11_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2a\"\n name: \"scale4b11_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2a\"\n bottom: \"res4b11_branch2a\"\n name: \"res4b11_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2b\"\n name: \"res4b11_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2b\"\n name: \"bn4b11_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2b\"\n name: \"scale4b11_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2b\"\n bottom: \"res4b11_branch2b\"\n name: \"res4b11_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2c\"\n name: \"res4b11_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2c\"\n top: \"res4b11_branch2c\"\n name: \"bn4b11_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2c\"\n top: \"res4b11_branch2c\"\n name: \"scale4b11_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10\"\n bottom: \"res4b11_branch2c\"\n top: \"res4b11\"\n name: \"res4b11\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b11\"\n name: \"res4b11_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b12_branch2a\"\n name: \"res4b12_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2a\"\n name: \"bn4b12_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2a\"\n name: \"scale4b12_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2a\"\n bottom: \"res4b12_branch2a\"\n name: \"res4b12_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2b\"\n name: \"res4b12_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2b\"\n name: \"bn4b12_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2b\"\n name: \"scale4b12_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2b\"\n bottom: \"res4b12_branch2b\"\n name: \"res4b12_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2c\"\n name: \"res4b12_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2c\"\n top: \"res4b12_branch2c\"\n name: \"bn4b12_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2c\"\n top: \"res4b12_branch2c\"\n name: \"scale4b12_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11\"\n bottom: \"res4b12_branch2c\"\n top: \"res4b12\"\n name: \"res4b12\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b12\"\n name: \"res4b12_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b13_branch2a\"\n name: \"res4b13_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2a\"\n name: \"bn4b13_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2a\"\n name: \"scale4b13_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2a\"\n bottom: \"res4b13_branch2a\"\n name: \"res4b13_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2b\"\n name: \"res4b13_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2b\"\n name: \"bn4b13_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2b\"\n name: \"scale4b13_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2b\"\n bottom: \"res4b13_branch2b\"\n name: \"res4b13_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2c\"\n name: \"res4b13_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2c\"\n top: \"res4b13_branch2c\"\n name: \"bn4b13_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2c\"\n top: \"res4b13_branch2c\"\n name: \"scale4b13_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12\"\n bottom: \"res4b13_branch2c\"\n top: \"res4b13\"\n name: \"res4b13\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b13\"\n name: \"res4b13_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b14_branch2a\"\n name: \"res4b14_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2a\"\n name: \"bn4b14_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2a\"\n name: \"scale4b14_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2a\"\n bottom: \"res4b14_branch2a\"\n name: \"res4b14_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2b\"\n name: \"res4b14_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2b\"\n name: \"bn4b14_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2b\"\n name: \"scale4b14_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2b\"\n bottom: \"res4b14_branch2b\"\n name: \"res4b14_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2c\"\n name: \"res4b14_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2c\"\n top: \"res4b14_branch2c\"\n name: \"bn4b14_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2c\"\n top: \"res4b14_branch2c\"\n name: \"scale4b14_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13\"\n bottom: \"res4b14_branch2c\"\n top: \"res4b14\"\n name: \"res4b14\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b14\"\n name: \"res4b14_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b15_branch2a\"\n name: \"res4b15_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2a\"\n name: \"bn4b15_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2a\"\n name: \"scale4b15_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2a\"\n bottom: \"res4b15_branch2a\"\n name: \"res4b15_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2b\"\n name: \"res4b15_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2b\"\n name: \"bn4b15_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2b\"\n name: \"scale4b15_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2b\"\n bottom: \"res4b15_branch2b\"\n name: \"res4b15_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2c\"\n name: \"res4b15_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2c\"\n top: \"res4b15_branch2c\"\n name: \"bn4b15_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2c\"\n top: \"res4b15_branch2c\"\n name: \"scale4b15_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14\"\n bottom: \"res4b15_branch2c\"\n top: \"res4b15\"\n name: \"res4b15\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b15\"\n name: \"res4b15_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b16_branch2a\"\n name: \"res4b16_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2a\"\n name: \"bn4b16_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2a\"\n name: \"scale4b16_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2a\"\n bottom: \"res4b16_branch2a\"\n name: \"res4b16_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2b\"\n name: \"res4b16_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2b\"\n name: \"bn4b16_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2b\"\n name: \"scale4b16_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2b\"\n bottom: \"res4b16_branch2b\"\n name: \"res4b16_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2c\"\n name: \"res4b16_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2c\"\n top: \"res4b16_branch2c\"\n name: \"bn4b16_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2c\"\n top: \"res4b16_branch2c\"\n name: \"scale4b16_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15\"\n bottom: \"res4b16_branch2c\"\n top: \"res4b16\"\n name: \"res4b16\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b16\"\n name: \"res4b16_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b17_branch2a\"\n name: \"res4b17_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2a\"\n name: \"bn4b17_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2a\"\n name: \"scale4b17_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2a\"\n bottom: \"res4b17_branch2a\"\n name: \"res4b17_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2b\"\n name: \"res4b17_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2b\"\n name: \"bn4b17_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2b\"\n name: \"scale4b17_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2b\"\n bottom: \"res4b17_branch2b\"\n name: \"res4b17_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2c\"\n name: \"res4b17_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2c\"\n top: \"res4b17_branch2c\"\n name: \"bn4b17_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2c\"\n top: \"res4b17_branch2c\"\n name: \"scale4b17_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16\"\n bottom: \"res4b17_branch2c\"\n top: \"res4b17\"\n name: \"res4b17\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b17\"\n name: \"res4b17_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b18_branch2a\"\n name: \"res4b18_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2a\"\n name: \"bn4b18_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2a\"\n name: \"scale4b18_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2a\"\n bottom: \"res4b18_branch2a\"\n name: \"res4b18_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2b\"\n name: \"res4b18_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2b\"\n name: \"bn4b18_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2b\"\n name: \"scale4b18_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2b\"\n bottom: \"res4b18_branch2b\"\n name: \"res4b18_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2c\"\n name: \"res4b18_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2c\"\n top: \"res4b18_branch2c\"\n name: \"bn4b18_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2c\"\n top: \"res4b18_branch2c\"\n name: \"scale4b18_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17\"\n bottom: \"res4b18_branch2c\"\n top: \"res4b18\"\n name: \"res4b18\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b18\"\n name: \"res4b18_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b19_branch2a\"\n name: \"res4b19_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2a\"\n name: \"bn4b19_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2a\"\n name: \"scale4b19_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2a\"\n bottom: \"res4b19_branch2a\"\n name: \"res4b19_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2b\"\n name: \"res4b19_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2b\"\n name: \"bn4b19_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2b\"\n name: \"scale4b19_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2b\"\n bottom: \"res4b19_branch2b\"\n name: \"res4b19_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2c\"\n name: \"res4b19_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2c\"\n top: \"res4b19_branch2c\"\n name: \"bn4b19_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2c\"\n top: \"res4b19_branch2c\"\n name: \"scale4b19_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18\"\n bottom: \"res4b19_branch2c\"\n top: \"res4b19\"\n name: \"res4b19\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b19\"\n name: \"res4b19_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b20_branch2a\"\n name: \"res4b20_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2a\"\n name: \"bn4b20_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2a\"\n name: \"scale4b20_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2a\"\n bottom: \"res4b20_branch2a\"\n name: \"res4b20_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2b\"\n name: \"res4b20_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2b\"\n name: \"bn4b20_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2b\"\n name: \"scale4b20_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2b\"\n bottom: \"res4b20_branch2b\"\n name: \"res4b20_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2c\"\n name: \"res4b20_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2c\"\n top: \"res4b20_branch2c\"\n name: \"bn4b20_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2c\"\n top: \"res4b20_branch2c\"\n name: \"scale4b20_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19\"\n bottom: \"res4b20_branch2c\"\n top: \"res4b20\"\n name: \"res4b20\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b20\"\n name: \"res4b20_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b21_branch2a\"\n name: \"res4b21_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2a\"\n name: \"bn4b21_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2a\"\n name: \"scale4b21_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2a\"\n bottom: \"res4b21_branch2a\"\n name: \"res4b21_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2b\"\n name: \"res4b21_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2b\"\n name: \"bn4b21_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2b\"\n name: \"scale4b21_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2b\"\n bottom: \"res4b21_branch2b\"\n name: \"res4b21_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2c\"\n name: \"res4b21_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2c\"\n top: \"res4b21_branch2c\"\n name: \"bn4b21_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2c\"\n top: \"res4b21_branch2c\"\n name: \"scale4b21_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20\"\n bottom: \"res4b21_branch2c\"\n top: \"res4b21\"\n name: \"res4b21\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b21\"\n name: \"res4b21_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b22_branch2a\"\n name: \"res4b22_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2a\"\n name: \"bn4b22_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2a\"\n name: \"scale4b22_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2a\"\n bottom: \"res4b22_branch2a\"\n name: \"res4b22_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2b\"\n name: \"res4b22_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2b\"\n name: \"bn4b22_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2b\"\n name: \"scale4b22_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2b\"\n bottom: \"res4b22_branch2b\"\n name: \"res4b22_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2c\"\n name: \"res4b22_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2c\"\n top: \"res4b22_branch2c\"\n name: \"bn4b22_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2c\"\n top: \"res4b22_branch2c\"\n name: \"scale4b22_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21\"\n bottom: \"res4b22_branch2c\"\n top: \"res4b22\"\n name: \"res4b22\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b22\"\n top: \"res4b22\"\n name: \"res4b22_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"res4b22\"\n bottom: \"rois\"\n top: \"roi_pool5\"\n roi_pooling_param {\n pooled_w: 14\n pooled_h: 14\n spatial_scale: 0.0625 # 1/16\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"bn5a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"bn5a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"bn5a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"bn5a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"bn5b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"bn5b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"bn5b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"bn5c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"bn5c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"bn5c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\n\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"loss_bbox\"\n loss_weight: 1\n}\n\n\n#========= RPN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4b22\"\n top: \"rpn/output\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"silence_rpn_cls_score\"\n type: \"Silence\"\n bottom: \"rpn_cls_score\"\n}\nlayer {\n name: \"silence_rpn_bbox_pred\"\n type: \"Silence\"\n bottom: \"rpn_bbox_pred\"\n}\n" }, { "path": "models/pascal_voc/ResNet101/faster_rcnn_alt_opt/stage2_rpn_solver60k80k.pt", "content": "train_net: \"models/pascal_voc/ResNet101/faster_rcnn_alt_opt/stage2_rpn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 60000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet101_rpn\"\n" }, { "path": "models/pascal_voc/ResNet101/faster_rcnn_alt_opt/stage2_rpn_train.pt", "content": "name: \"ResNet101\"\n\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"bn_conv1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"conv1\"\n bottom: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"bn2a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"bn2a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2a\"\n bottom: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"bn2a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2b\"\n bottom: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"bn2a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"bn2b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2a\"\n bottom: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"bn2b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2b\"\n bottom: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"bn2b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"bn2c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2a\"\n bottom: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"bn2c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2b\"\n bottom: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"bn2c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"bn3a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"bn3a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2a\"\n bottom: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"bn3a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2b\"\n bottom: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"bn3a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b1_branch2a\"\n name: \"res3b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2a\"\n name: \"bn3b1_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2a\"\n name: \"scale3b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2a\"\n bottom: \"res3b1_branch2a\"\n name: \"res3b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2b\"\n name: \"res3b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2b\"\n name: \"bn3b1_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2b\"\n name: \"scale3b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2b\"\n bottom: \"res3b1_branch2b\"\n name: \"res3b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2c\"\n name: \"res3b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2c\"\n top: \"res3b1_branch2c\"\n name: \"bn3b1_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2c\"\n top: \"res3b1_branch2c\"\n name: \"scale3b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b1_branch2c\"\n top: \"res3b1\"\n name: \"res3b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b1\"\n name: \"res3b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b2_branch2a\"\n name: \"res3b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2a\"\n name: \"bn3b2_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2a\"\n name: \"scale3b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2a\"\n bottom: \"res3b2_branch2a\"\n name: \"res3b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2b\"\n name: \"res3b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2b\"\n name: \"bn3b2_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2b\"\n name: \"scale3b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2b\"\n bottom: \"res3b2_branch2b\"\n name: \"res3b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2c\"\n name: \"res3b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2c\"\n top: \"res3b2_branch2c\"\n name: \"bn3b2_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2c\"\n top: \"res3b2_branch2c\"\n name: \"scale3b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1\"\n bottom: \"res3b2_branch2c\"\n top: \"res3b2\"\n name: \"res3b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b2\"\n name: \"res3b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b3_branch2a\"\n name: \"res3b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2a\"\n name: \"bn3b3_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2a\"\n name: \"scale3b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2a\"\n bottom: \"res3b3_branch2a\"\n name: \"res3b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2b\"\n name: \"res3b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2b\"\n name: \"bn3b3_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2b\"\n name: \"scale3b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2b\"\n bottom: \"res3b3_branch2b\"\n name: \"res3b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2c\"\n name: \"res3b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2c\"\n top: \"res3b3_branch2c\"\n name: \"bn3b3_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2c\"\n top: \"res3b3_branch2c\"\n name: \"scale3b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2\"\n bottom: \"res3b3_branch2c\"\n top: \"res3b3\"\n name: \"res3b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res3b3\"\n name: \"res3b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"bn4a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"bn4a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2a\"\n bottom: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"bn4a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2b\"\n bottom: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"bn4a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b1_branch2a\"\n name: \"res4b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2a\"\n name: \"bn4b1_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2a\"\n name: \"scale4b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2a\"\n bottom: \"res4b1_branch2a\"\n name: \"res4b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2b\"\n name: \"res4b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2b\"\n name: \"bn4b1_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2b\"\n name: \"scale4b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2b\"\n bottom: \"res4b1_branch2b\"\n name: \"res4b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2c\"\n name: \"res4b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2c\"\n top: \"res4b1_branch2c\"\n name: \"bn4b1_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2c\"\n top: \"res4b1_branch2c\"\n name: \"scale4b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b1_branch2c\"\n top: \"res4b1\"\n name: \"res4b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b1\"\n name: \"res4b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b2_branch2a\"\n name: \"res4b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2a\"\n name: \"bn4b2_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2a\"\n name: \"scale4b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2a\"\n bottom: \"res4b2_branch2a\"\n name: \"res4b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2b\"\n name: \"res4b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2b\"\n name: \"bn4b2_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2b\"\n name: \"scale4b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2b\"\n bottom: \"res4b2_branch2b\"\n name: \"res4b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2c\"\n name: \"res4b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2c\"\n top: \"res4b2_branch2c\"\n name: \"bn4b2_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2c\"\n top: \"res4b2_branch2c\"\n name: \"scale4b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1\"\n bottom: \"res4b2_branch2c\"\n top: \"res4b2\"\n name: \"res4b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b2\"\n name: \"res4b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b3_branch2a\"\n name: \"res4b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2a\"\n name: \"bn4b3_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2a\"\n name: \"scale4b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2a\"\n bottom: \"res4b3_branch2a\"\n name: \"res4b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2b\"\n name: \"res4b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2b\"\n name: \"bn4b3_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2b\"\n name: \"scale4b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2b\"\n bottom: \"res4b3_branch2b\"\n name: \"res4b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2c\"\n name: \"res4b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2c\"\n top: \"res4b3_branch2c\"\n name: \"bn4b3_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2c\"\n top: \"res4b3_branch2c\"\n name: \"scale4b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2\"\n bottom: \"res4b3_branch2c\"\n top: \"res4b3\"\n name: \"res4b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b3\"\n name: \"res4b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b4_branch2a\"\n name: \"res4b4_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2a\"\n name: \"bn4b4_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2a\"\n name: \"scale4b4_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2a\"\n bottom: \"res4b4_branch2a\"\n name: \"res4b4_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2b\"\n name: \"res4b4_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2b\"\n name: \"bn4b4_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2b\"\n name: \"scale4b4_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2b\"\n bottom: \"res4b4_branch2b\"\n name: \"res4b4_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2c\"\n name: \"res4b4_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2c\"\n top: \"res4b4_branch2c\"\n name: \"bn4b4_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2c\"\n top: \"res4b4_branch2c\"\n name: \"scale4b4_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3\"\n bottom: \"res4b4_branch2c\"\n top: \"res4b4\"\n name: \"res4b4\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b4\"\n name: \"res4b4_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b5_branch2a\"\n name: \"res4b5_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2a\"\n name: \"bn4b5_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2a\"\n name: \"scale4b5_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2a\"\n bottom: \"res4b5_branch2a\"\n name: \"res4b5_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2b\"\n name: \"res4b5_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2b\"\n name: \"bn4b5_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2b\"\n name: \"scale4b5_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2b\"\n bottom: \"res4b5_branch2b\"\n name: \"res4b5_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2c\"\n name: \"res4b5_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2c\"\n top: \"res4b5_branch2c\"\n name: \"bn4b5_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2c\"\n top: \"res4b5_branch2c\"\n name: \"scale4b5_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4\"\n bottom: \"res4b5_branch2c\"\n top: \"res4b5\"\n name: \"res4b5\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b5\"\n name: \"res4b5_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b6_branch2a\"\n name: \"res4b6_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2a\"\n name: \"bn4b6_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2a\"\n name: \"scale4b6_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2a\"\n bottom: \"res4b6_branch2a\"\n name: \"res4b6_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2b\"\n name: \"res4b6_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2b\"\n name: \"bn4b6_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2b\"\n name: \"scale4b6_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2b\"\n bottom: \"res4b6_branch2b\"\n name: \"res4b6_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2c\"\n name: \"res4b6_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2c\"\n top: \"res4b6_branch2c\"\n name: \"bn4b6_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2c\"\n top: \"res4b6_branch2c\"\n name: \"scale4b6_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5\"\n bottom: \"res4b6_branch2c\"\n top: \"res4b6\"\n name: \"res4b6\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b6\"\n name: \"res4b6_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b7_branch2a\"\n name: \"res4b7_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2a\"\n name: \"bn4b7_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2a\"\n name: \"scale4b7_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2a\"\n bottom: \"res4b7_branch2a\"\n name: \"res4b7_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2b\"\n name: \"res4b7_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2b\"\n name: \"bn4b7_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2b\"\n name: \"scale4b7_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2b\"\n bottom: \"res4b7_branch2b\"\n name: \"res4b7_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2c\"\n name: \"res4b7_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2c\"\n top: \"res4b7_branch2c\"\n name: \"bn4b7_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2c\"\n top: \"res4b7_branch2c\"\n name: \"scale4b7_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6\"\n bottom: \"res4b7_branch2c\"\n top: \"res4b7\"\n name: \"res4b7\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b7\"\n name: \"res4b7_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b8_branch2a\"\n name: \"res4b8_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2a\"\n name: \"bn4b8_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2a\"\n name: \"scale4b8_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2a\"\n bottom: \"res4b8_branch2a\"\n name: \"res4b8_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2b\"\n name: \"res4b8_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2b\"\n name: \"bn4b8_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2b\"\n name: \"scale4b8_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2b\"\n bottom: \"res4b8_branch2b\"\n name: \"res4b8_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2c\"\n name: \"res4b8_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2c\"\n top: \"res4b8_branch2c\"\n name: \"bn4b8_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2c\"\n top: \"res4b8_branch2c\"\n name: \"scale4b8_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7\"\n bottom: \"res4b8_branch2c\"\n top: \"res4b8\"\n name: \"res4b8\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b8\"\n name: \"res4b8_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b9_branch2a\"\n name: \"res4b9_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2a\"\n name: \"bn4b9_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2a\"\n name: \"scale4b9_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2a\"\n bottom: \"res4b9_branch2a\"\n name: \"res4b9_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2b\"\n name: \"res4b9_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2b\"\n name: \"bn4b9_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2b\"\n name: \"scale4b9_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2b\"\n bottom: \"res4b9_branch2b\"\n name: \"res4b9_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2c\"\n name: \"res4b9_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2c\"\n top: \"res4b9_branch2c\"\n name: \"bn4b9_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2c\"\n top: \"res4b9_branch2c\"\n name: \"scale4b9_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8\"\n bottom: \"res4b9_branch2c\"\n top: \"res4b9\"\n name: \"res4b9\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b9\"\n name: \"res4b9_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b10_branch2a\"\n name: \"res4b10_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2a\"\n name: \"bn4b10_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2a\"\n name: \"scale4b10_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2a\"\n bottom: \"res4b10_branch2a\"\n name: \"res4b10_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2b\"\n name: \"res4b10_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2b\"\n name: \"bn4b10_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2b\"\n name: \"scale4b10_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2b\"\n bottom: \"res4b10_branch2b\"\n name: \"res4b10_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2c\"\n name: \"res4b10_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2c\"\n top: \"res4b10_branch2c\"\n name: \"bn4b10_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2c\"\n top: \"res4b10_branch2c\"\n name: \"scale4b10_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9\"\n bottom: \"res4b10_branch2c\"\n top: \"res4b10\"\n name: \"res4b10\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b10\"\n name: \"res4b10_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b11_branch2a\"\n name: \"res4b11_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2a\"\n name: \"bn4b11_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2a\"\n name: \"scale4b11_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2a\"\n bottom: \"res4b11_branch2a\"\n name: \"res4b11_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2b\"\n name: \"res4b11_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2b\"\n name: \"bn4b11_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2b\"\n name: \"scale4b11_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2b\"\n bottom: \"res4b11_branch2b\"\n name: \"res4b11_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2c\"\n name: \"res4b11_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2c\"\n top: \"res4b11_branch2c\"\n name: \"bn4b11_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2c\"\n top: \"res4b11_branch2c\"\n name: \"scale4b11_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10\"\n bottom: \"res4b11_branch2c\"\n top: \"res4b11\"\n name: \"res4b11\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b11\"\n name: \"res4b11_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b12_branch2a\"\n name: \"res4b12_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2a\"\n name: \"bn4b12_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2a\"\n name: \"scale4b12_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2a\"\n bottom: \"res4b12_branch2a\"\n name: \"res4b12_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2b\"\n name: \"res4b12_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2b\"\n name: \"bn4b12_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2b\"\n name: \"scale4b12_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2b\"\n bottom: \"res4b12_branch2b\"\n name: \"res4b12_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2c\"\n name: \"res4b12_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2c\"\n top: \"res4b12_branch2c\"\n name: \"bn4b12_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2c\"\n top: \"res4b12_branch2c\"\n name: \"scale4b12_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11\"\n bottom: \"res4b12_branch2c\"\n top: \"res4b12\"\n name: \"res4b12\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b12\"\n name: \"res4b12_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b13_branch2a\"\n name: \"res4b13_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2a\"\n name: \"bn4b13_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2a\"\n name: \"scale4b13_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2a\"\n bottom: \"res4b13_branch2a\"\n name: \"res4b13_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2b\"\n name: \"res4b13_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2b\"\n name: \"bn4b13_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2b\"\n name: \"scale4b13_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2b\"\n bottom: \"res4b13_branch2b\"\n name: \"res4b13_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2c\"\n name: \"res4b13_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2c\"\n top: \"res4b13_branch2c\"\n name: \"bn4b13_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2c\"\n top: \"res4b13_branch2c\"\n name: \"scale4b13_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12\"\n bottom: \"res4b13_branch2c\"\n top: \"res4b13\"\n name: \"res4b13\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b13\"\n name: \"res4b13_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b14_branch2a\"\n name: \"res4b14_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2a\"\n name: \"bn4b14_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2a\"\n name: \"scale4b14_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2a\"\n bottom: \"res4b14_branch2a\"\n name: \"res4b14_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2b\"\n name: \"res4b14_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2b\"\n name: \"bn4b14_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2b\"\n name: \"scale4b14_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2b\"\n bottom: \"res4b14_branch2b\"\n name: \"res4b14_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2c\"\n name: \"res4b14_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2c\"\n top: \"res4b14_branch2c\"\n name: \"bn4b14_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2c\"\n top: \"res4b14_branch2c\"\n name: \"scale4b14_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13\"\n bottom: \"res4b14_branch2c\"\n top: \"res4b14\"\n name: \"res4b14\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b14\"\n name: \"res4b14_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b15_branch2a\"\n name: \"res4b15_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2a\"\n name: \"bn4b15_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2a\"\n name: \"scale4b15_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2a\"\n bottom: \"res4b15_branch2a\"\n name: \"res4b15_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2b\"\n name: \"res4b15_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2b\"\n name: \"bn4b15_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2b\"\n name: \"scale4b15_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2b\"\n bottom: \"res4b15_branch2b\"\n name: \"res4b15_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2c\"\n name: \"res4b15_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2c\"\n top: \"res4b15_branch2c\"\n name: \"bn4b15_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2c\"\n top: \"res4b15_branch2c\"\n name: \"scale4b15_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14\"\n bottom: \"res4b15_branch2c\"\n top: \"res4b15\"\n name: \"res4b15\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b15\"\n name: \"res4b15_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b16_branch2a\"\n name: \"res4b16_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2a\"\n name: \"bn4b16_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2a\"\n name: \"scale4b16_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2a\"\n bottom: \"res4b16_branch2a\"\n name: \"res4b16_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2b\"\n name: \"res4b16_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2b\"\n name: \"bn4b16_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2b\"\n name: \"scale4b16_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2b\"\n bottom: \"res4b16_branch2b\"\n name: \"res4b16_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2c\"\n name: \"res4b16_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2c\"\n top: \"res4b16_branch2c\"\n name: \"bn4b16_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2c\"\n top: \"res4b16_branch2c\"\n name: \"scale4b16_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15\"\n bottom: \"res4b16_branch2c\"\n top: \"res4b16\"\n name: \"res4b16\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b16\"\n name: \"res4b16_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b17_branch2a\"\n name: \"res4b17_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2a\"\n name: \"bn4b17_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2a\"\n name: \"scale4b17_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2a\"\n bottom: \"res4b17_branch2a\"\n name: \"res4b17_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2b\"\n name: \"res4b17_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2b\"\n name: \"bn4b17_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2b\"\n name: \"scale4b17_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2b\"\n bottom: \"res4b17_branch2b\"\n name: \"res4b17_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2c\"\n name: \"res4b17_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2c\"\n top: \"res4b17_branch2c\"\n name: \"bn4b17_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2c\"\n top: \"res4b17_branch2c\"\n name: \"scale4b17_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16\"\n bottom: \"res4b17_branch2c\"\n top: \"res4b17\"\n name: \"res4b17\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b17\"\n name: \"res4b17_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b18_branch2a\"\n name: \"res4b18_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2a\"\n name: \"bn4b18_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2a\"\n name: \"scale4b18_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2a\"\n bottom: \"res4b18_branch2a\"\n name: \"res4b18_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2b\"\n name: \"res4b18_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2b\"\n name: \"bn4b18_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2b\"\n name: \"scale4b18_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2b\"\n bottom: \"res4b18_branch2b\"\n name: \"res4b18_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2c\"\n name: \"res4b18_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2c\"\n top: \"res4b18_branch2c\"\n name: \"bn4b18_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2c\"\n top: \"res4b18_branch2c\"\n name: \"scale4b18_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17\"\n bottom: \"res4b18_branch2c\"\n top: \"res4b18\"\n name: \"res4b18\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b18\"\n name: \"res4b18_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b19_branch2a\"\n name: \"res4b19_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2a\"\n name: \"bn4b19_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2a\"\n name: \"scale4b19_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2a\"\n bottom: \"res4b19_branch2a\"\n name: \"res4b19_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2b\"\n name: \"res4b19_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2b\"\n name: \"bn4b19_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2b\"\n name: \"scale4b19_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2b\"\n bottom: \"res4b19_branch2b\"\n name: \"res4b19_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2c\"\n name: \"res4b19_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2c\"\n top: \"res4b19_branch2c\"\n name: \"bn4b19_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2c\"\n top: \"res4b19_branch2c\"\n name: \"scale4b19_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18\"\n bottom: \"res4b19_branch2c\"\n top: \"res4b19\"\n name: \"res4b19\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b19\"\n name: \"res4b19_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b20_branch2a\"\n name: \"res4b20_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2a\"\n name: \"bn4b20_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2a\"\n name: \"scale4b20_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2a\"\n bottom: \"res4b20_branch2a\"\n name: \"res4b20_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2b\"\n name: \"res4b20_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2b\"\n name: \"bn4b20_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2b\"\n name: \"scale4b20_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2b\"\n bottom: \"res4b20_branch2b\"\n name: \"res4b20_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2c\"\n name: \"res4b20_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2c\"\n top: \"res4b20_branch2c\"\n name: \"bn4b20_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2c\"\n top: \"res4b20_branch2c\"\n name: \"scale4b20_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19\"\n bottom: \"res4b20_branch2c\"\n top: \"res4b20\"\n name: \"res4b20\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b20\"\n name: \"res4b20_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b21_branch2a\"\n name: \"res4b21_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2a\"\n name: \"bn4b21_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2a\"\n name: \"scale4b21_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2a\"\n bottom: \"res4b21_branch2a\"\n name: \"res4b21_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2b\"\n name: \"res4b21_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2b\"\n name: \"bn4b21_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2b\"\n name: \"scale4b21_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2b\"\n bottom: \"res4b21_branch2b\"\n name: \"res4b21_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2c\"\n name: \"res4b21_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2c\"\n top: \"res4b21_branch2c\"\n name: \"bn4b21_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2c\"\n top: \"res4b21_branch2c\"\n name: \"scale4b21_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20\"\n bottom: \"res4b21_branch2c\"\n top: \"res4b21\"\n name: \"res4b21\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b21\"\n name: \"res4b21_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b22_branch2a\"\n name: \"res4b22_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2a\"\n name: \"bn4b22_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2a\"\n name: \"scale4b22_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2a\"\n bottom: \"res4b22_branch2a\"\n name: \"res4b22_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2b\"\n name: \"res4b22_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2b\"\n name: \"bn4b22_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2b\"\n name: \"scale4b22_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2b\"\n bottom: \"res4b22_branch2b\"\n name: \"res4b22_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2c\"\n name: \"res4b22_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2c\"\n top: \"res4b22_branch2c\"\n name: \"bn4b22_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2c\"\n top: \"res4b22_branch2c\"\n name: \"scale4b22_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21\"\n bottom: \"res4b22_branch2c\"\n top: \"res4b22\"\n name: \"res4b22\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b22\"\n top: \"res4b22\"\n name: \"res4b22_relu\"\n type: \"ReLU\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4b22\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RCNN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"dummy_roi_pool_res4b22\"\n type: \"DummyData\"\n top: \"dummy_roi_pool_res4b22\"\n dummy_data_param {\n shape { dim: 1 dim: 1024 dim: 14 dim: 14 }\n data_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"dummy_roi_pool_res4b22\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"bn5a_branch1\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"dummy_roi_pool_res4b22\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"bn5a_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"bn5a_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"bn5a_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"bn5b_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"bn5b_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"bn5b_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"bn5c_branch2a\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"bn5c_branch2b\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"bn5c_branch2c\"\n type: \"BatchNorm\"\n batch_norm_param {\n use_global_stats: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\nlayer {\n name: \"silence_pool5\"\n type: \"Silence\"\n bottom: \"pool5\"\n}\n" }, { "path": "models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_alt_opt/faster_rcnn_test.pt", "content": "name: \"ResNet101_BN_SCALE_Merged\"\n\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\n\ninput: \"im_info\"\ninput_shape {\n dim: 1\n dim: 3\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"conv1\"\n bottom: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2a\"\n bottom: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2b\"\n bottom: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2a\"\n bottom: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2b\"\n bottom: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2a\"\n bottom: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2b\"\n bottom: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2a\"\n bottom: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2b\"\n bottom: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b1_branch2a\"\n name: \"res3b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2a\"\n name: \"scale3b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2a\"\n bottom: \"res3b1_branch2a\"\n name: \"res3b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2b\"\n name: \"res3b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2b\"\n name: \"scale3b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2b\"\n bottom: \"res3b1_branch2b\"\n name: \"res3b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2c\"\n name: \"res3b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2c\"\n top: \"res3b1_branch2c\"\n name: \"scale3b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b1_branch2c\"\n top: \"res3b1\"\n name: \"res3b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b1\"\n name: \"res3b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b2_branch2a\"\n name: \"res3b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2a\"\n name: \"scale3b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2a\"\n bottom: \"res3b2_branch2a\"\n name: \"res3b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2b\"\n name: \"res3b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2b\"\n name: \"scale3b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2b\"\n bottom: \"res3b2_branch2b\"\n name: \"res3b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2c\"\n name: \"res3b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2c\"\n top: \"res3b2_branch2c\"\n name: \"scale3b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1\"\n bottom: \"res3b2_branch2c\"\n top: \"res3b2\"\n name: \"res3b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b2\"\n name: \"res3b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b3_branch2a\"\n name: \"res3b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2a\"\n name: \"scale3b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2a\"\n bottom: \"res3b3_branch2a\"\n name: \"res3b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2b\"\n name: \"res3b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2b\"\n name: \"scale3b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2b\"\n bottom: \"res3b3_branch2b\"\n name: \"res3b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2c\"\n name: \"res3b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2c\"\n top: \"res3b3_branch2c\"\n name: \"scale3b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2\"\n bottom: \"res3b3_branch2c\"\n top: \"res3b3\"\n name: \"res3b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res3b3\"\n name: \"res3b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2a\"\n bottom: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2b\"\n bottom: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b1_branch2a\"\n name: \"res4b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2a\"\n name: \"scale4b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2a\"\n bottom: \"res4b1_branch2a\"\n name: \"res4b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2b\"\n name: \"res4b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2b\"\n name: \"scale4b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2b\"\n bottom: \"res4b1_branch2b\"\n name: \"res4b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2c\"\n name: \"res4b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2c\"\n top: \"res4b1_branch2c\"\n name: \"scale4b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b1_branch2c\"\n top: \"res4b1\"\n name: \"res4b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b1\"\n name: \"res4b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b2_branch2a\"\n name: \"res4b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2a\"\n name: \"scale4b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2a\"\n bottom: \"res4b2_branch2a\"\n name: \"res4b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2b\"\n name: \"res4b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2b\"\n name: \"scale4b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2b\"\n bottom: \"res4b2_branch2b\"\n name: \"res4b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2c\"\n name: \"res4b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2c\"\n top: \"res4b2_branch2c\"\n name: \"scale4b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1\"\n bottom: \"res4b2_branch2c\"\n top: \"res4b2\"\n name: \"res4b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b2\"\n name: \"res4b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b3_branch2a\"\n name: \"res4b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2a\"\n name: \"scale4b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2a\"\n bottom: \"res4b3_branch2a\"\n name: \"res4b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2b\"\n name: \"res4b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2b\"\n name: \"scale4b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2b\"\n bottom: \"res4b3_branch2b\"\n name: \"res4b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2c\"\n name: \"res4b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2c\"\n top: \"res4b3_branch2c\"\n name: \"scale4b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2\"\n bottom: \"res4b3_branch2c\"\n top: \"res4b3\"\n name: \"res4b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b3\"\n name: \"res4b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b4_branch2a\"\n name: \"res4b4_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2a\"\n name: \"scale4b4_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2a\"\n bottom: \"res4b4_branch2a\"\n name: \"res4b4_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2b\"\n name: \"res4b4_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2b\"\n name: \"scale4b4_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2b\"\n bottom: \"res4b4_branch2b\"\n name: \"res4b4_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2c\"\n name: \"res4b4_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2c\"\n top: \"res4b4_branch2c\"\n name: \"scale4b4_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3\"\n bottom: \"res4b4_branch2c\"\n top: \"res4b4\"\n name: \"res4b4\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b4\"\n name: \"res4b4_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b5_branch2a\"\n name: \"res4b5_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2a\"\n name: \"scale4b5_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2a\"\n bottom: \"res4b5_branch2a\"\n name: \"res4b5_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2b\"\n name: \"res4b5_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2b\"\n name: \"scale4b5_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2b\"\n bottom: \"res4b5_branch2b\"\n name: \"res4b5_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2c\"\n name: \"res4b5_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2c\"\n top: \"res4b5_branch2c\"\n name: \"scale4b5_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4\"\n bottom: \"res4b5_branch2c\"\n top: \"res4b5\"\n name: \"res4b5\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b5\"\n name: \"res4b5_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b6_branch2a\"\n name: \"res4b6_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2a\"\n name: \"scale4b6_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2a\"\n bottom: \"res4b6_branch2a\"\n name: \"res4b6_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2b\"\n name: \"res4b6_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2b\"\n name: \"scale4b6_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2b\"\n bottom: \"res4b6_branch2b\"\n name: \"res4b6_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2c\"\n name: \"res4b6_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2c\"\n top: \"res4b6_branch2c\"\n name: \"scale4b6_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5\"\n bottom: \"res4b6_branch2c\"\n top: \"res4b6\"\n name: \"res4b6\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b6\"\n name: \"res4b6_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b7_branch2a\"\n name: \"res4b7_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2a\"\n name: \"scale4b7_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2a\"\n bottom: \"res4b7_branch2a\"\n name: \"res4b7_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2b\"\n name: \"res4b7_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2b\"\n name: \"scale4b7_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2b\"\n bottom: \"res4b7_branch2b\"\n name: \"res4b7_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2c\"\n name: \"res4b7_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2c\"\n top: \"res4b7_branch2c\"\n name: \"scale4b7_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6\"\n bottom: \"res4b7_branch2c\"\n top: \"res4b7\"\n name: \"res4b7\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b7\"\n name: \"res4b7_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b8_branch2a\"\n name: \"res4b8_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2a\"\n name: \"scale4b8_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2a\"\n bottom: \"res4b8_branch2a\"\n name: \"res4b8_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2b\"\n name: \"res4b8_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2b\"\n name: \"scale4b8_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2b\"\n bottom: \"res4b8_branch2b\"\n name: \"res4b8_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2c\"\n name: \"res4b8_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2c\"\n top: \"res4b8_branch2c\"\n name: \"scale4b8_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7\"\n bottom: \"res4b8_branch2c\"\n top: \"res4b8\"\n name: \"res4b8\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b8\"\n name: \"res4b8_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b9_branch2a\"\n name: \"res4b9_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2a\"\n name: \"scale4b9_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2a\"\n bottom: \"res4b9_branch2a\"\n name: \"res4b9_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2b\"\n name: \"res4b9_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2b\"\n name: \"scale4b9_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2b\"\n bottom: \"res4b9_branch2b\"\n name: \"res4b9_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2c\"\n name: \"res4b9_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2c\"\n top: \"res4b9_branch2c\"\n name: \"scale4b9_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8\"\n bottom: \"res4b9_branch2c\"\n top: \"res4b9\"\n name: \"res4b9\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b9\"\n name: \"res4b9_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b10_branch2a\"\n name: \"res4b10_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2a\"\n name: \"scale4b10_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2a\"\n bottom: \"res4b10_branch2a\"\n name: \"res4b10_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2b\"\n name: \"res4b10_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2b\"\n name: \"scale4b10_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2b\"\n bottom: \"res4b10_branch2b\"\n name: \"res4b10_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2c\"\n name: \"res4b10_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b10_branch2c\"\n top: \"res4b10_branch2c\"\n name: \"scale4b10_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9\"\n bottom: \"res4b10_branch2c\"\n top: \"res4b10\"\n name: \"res4b10\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b10\"\n name: \"res4b10_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b11_branch2a\"\n name: \"res4b11_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2a\"\n name: \"scale4b11_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2a\"\n bottom: \"res4b11_branch2a\"\n name: \"res4b11_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2b\"\n name: \"res4b11_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2b\"\n name: \"scale4b11_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2b\"\n bottom: \"res4b11_branch2b\"\n name: \"res4b11_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2c\"\n name: \"res4b11_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2c\"\n top: \"res4b11_branch2c\"\n name: \"scale4b11_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10\"\n bottom: \"res4b11_branch2c\"\n top: \"res4b11\"\n name: \"res4b11\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b11\"\n name: \"res4b11_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b12_branch2a\"\n name: \"res4b12_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2a\"\n name: \"scale4b12_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2a\"\n bottom: \"res4b12_branch2a\"\n name: \"res4b12_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2b\"\n name: \"res4b12_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2b\"\n name: \"scale4b12_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2b\"\n bottom: \"res4b12_branch2b\"\n name: \"res4b12_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2c\"\n name: \"res4b12_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2c\"\n top: \"res4b12_branch2c\"\n name: \"scale4b12_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11\"\n bottom: \"res4b12_branch2c\"\n top: \"res4b12\"\n name: \"res4b12\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b12\"\n name: \"res4b12_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b13_branch2a\"\n name: \"res4b13_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2a\"\n name: \"scale4b13_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2a\"\n bottom: \"res4b13_branch2a\"\n name: \"res4b13_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2b\"\n name: \"res4b13_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2b\"\n name: \"scale4b13_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2b\"\n bottom: \"res4b13_branch2b\"\n name: \"res4b13_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2c\"\n name: \"res4b13_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2c\"\n top: \"res4b13_branch2c\"\n name: \"scale4b13_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12\"\n bottom: \"res4b13_branch2c\"\n top: \"res4b13\"\n name: \"res4b13\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b13\"\n name: \"res4b13_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b14_branch2a\"\n name: \"res4b14_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2a\"\n name: \"scale4b14_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2a\"\n bottom: \"res4b14_branch2a\"\n name: \"res4b14_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2b\"\n name: \"res4b14_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2b\"\n name: \"scale4b14_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2b\"\n bottom: \"res4b14_branch2b\"\n name: \"res4b14_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2c\"\n name: \"res4b14_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2c\"\n top: \"res4b14_branch2c\"\n name: \"scale4b14_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13\"\n bottom: \"res4b14_branch2c\"\n top: \"res4b14\"\n name: \"res4b14\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b14\"\n name: \"res4b14_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b15_branch2a\"\n name: \"res4b15_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2a\"\n name: \"scale4b15_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2a\"\n bottom: \"res4b15_branch2a\"\n name: \"res4b15_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2b\"\n name: \"res4b15_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2b\"\n name: \"scale4b15_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2b\"\n bottom: \"res4b15_branch2b\"\n name: \"res4b15_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2c\"\n name: \"res4b15_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2c\"\n top: \"res4b15_branch2c\"\n name: \"scale4b15_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14\"\n bottom: \"res4b15_branch2c\"\n top: \"res4b15\"\n name: \"res4b15\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b15\"\n name: \"res4b15_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b16_branch2a\"\n name: \"res4b16_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2a\"\n name: \"scale4b16_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2a\"\n bottom: \"res4b16_branch2a\"\n name: \"res4b16_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2b\"\n name: \"res4b16_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2b\"\n name: \"scale4b16_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2b\"\n bottom: \"res4b16_branch2b\"\n name: \"res4b16_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2c\"\n name: \"res4b16_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2c\"\n top: \"res4b16_branch2c\"\n name: \"scale4b16_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15\"\n bottom: \"res4b16_branch2c\"\n top: \"res4b16\"\n name: \"res4b16\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b16\"\n name: \"res4b16_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b17_branch2a\"\n name: \"res4b17_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2a\"\n name: \"scale4b17_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2a\"\n bottom: \"res4b17_branch2a\"\n name: \"res4b17_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2b\"\n name: \"res4b17_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2b\"\n name: \"scale4b17_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2b\"\n bottom: \"res4b17_branch2b\"\n name: \"res4b17_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2c\"\n name: \"res4b17_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2c\"\n top: \"res4b17_branch2c\"\n name: \"scale4b17_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16\"\n bottom: \"res4b17_branch2c\"\n top: \"res4b17\"\n name: \"res4b17\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b17\"\n name: \"res4b17_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b18_branch2a\"\n name: \"res4b18_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2a\"\n name: \"scale4b18_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2a\"\n bottom: \"res4b18_branch2a\"\n name: \"res4b18_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2b\"\n name: \"res4b18_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2b\"\n name: \"scale4b18_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2b\"\n bottom: \"res4b18_branch2b\"\n name: \"res4b18_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2c\"\n name: \"res4b18_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b18_branch2c\"\n top: \"res4b18_branch2c\"\n name: \"scale4b18_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17\"\n bottom: \"res4b18_branch2c\"\n top: \"res4b18\"\n name: \"res4b18\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b18\"\n name: \"res4b18_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b19_branch2a\"\n name: \"res4b19_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2a\"\n name: \"scale4b19_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2a\"\n bottom: \"res4b19_branch2a\"\n name: \"res4b19_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2b\"\n name: \"res4b19_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2b\"\n name: \"scale4b19_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2b\"\n bottom: \"res4b19_branch2b\"\n name: \"res4b19_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2c\"\n name: \"res4b19_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b19_branch2c\"\n top: \"res4b19_branch2c\"\n name: \"scale4b19_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18\"\n bottom: \"res4b19_branch2c\"\n top: \"res4b19\"\n name: \"res4b19\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b19\"\n name: \"res4b19_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b20_branch2a\"\n name: \"res4b20_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2a\"\n name: \"scale4b20_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2a\"\n bottom: \"res4b20_branch2a\"\n name: \"res4b20_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2b\"\n name: \"res4b20_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2b\"\n name: \"scale4b20_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2b\"\n bottom: \"res4b20_branch2b\"\n name: \"res4b20_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2c\"\n name: \"res4b20_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2c\"\n top: \"res4b20_branch2c\"\n name: \"scale4b20_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19\"\n bottom: \"res4b20_branch2c\"\n top: \"res4b20\"\n name: \"res4b20\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b20\"\n name: \"res4b20_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b21_branch2a\"\n name: \"res4b21_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2a\"\n name: \"scale4b21_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2a\"\n bottom: \"res4b21_branch2a\"\n name: \"res4b21_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2b\"\n name: \"res4b21_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2b\"\n name: \"scale4b21_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2b\"\n bottom: \"res4b21_branch2b\"\n name: \"res4b21_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2c\"\n name: \"res4b21_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2c\"\n top: \"res4b21_branch2c\"\n name: \"scale4b21_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20\"\n bottom: \"res4b21_branch2c\"\n top: \"res4b21\"\n name: \"res4b21\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b21\"\n name: \"res4b21_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b22_branch2a\"\n name: \"res4b22_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2a\"\n name: \"scale4b22_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2a\"\n bottom: \"res4b22_branch2a\"\n name: \"res4b22_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2b\"\n name: \"res4b22_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2b\"\n name: \"scale4b22_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2b\"\n bottom: \"res4b22_branch2b\"\n name: \"res4b22_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2c\"\n name: \"res4b22_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b22_branch2c\"\n top: \"res4b22_branch2c\"\n name: \"scale4b22_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21\"\n bottom: \"res4b22_branch2c\"\n top: \"res4b22\"\n name: \"res4b22\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b22\"\n top: \"res4b22\"\n name: \"res4b22_relu\"\n type: \"ReLU\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4b22\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rois'\n top: 'scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n\n#========= RCNN ============\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"res4b22\"\n bottom: \"rois\"\n top: \"roi_pool5\"\n roi_pooling_param {\n pooled_w: 14\n pooled_h: 14\n spatial_scale: 0.0625 # 1/16\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\n\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\n\nlayer {\n name: \"cls_prob\"\n type: \"Softmax\"\n bottom: \"cls_score\"\n top: \"cls_prob\"\n}\n" }, { "path": "models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_alt_opt/rpn_test.pt", "content": "name: \"ResNet101_BN_SCALE_Merged\"\n\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\n\ninput: \"im_info\"\ninput_shape {\n dim: 1\n dim: 3\n}\n\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"conv1\"\n bottom: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2a\"\n bottom: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2b\"\n bottom: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2a\"\n bottom: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2b\"\n bottom: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2a\"\n bottom: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2b\"\n bottom: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2a\"\n bottom: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2b\"\n bottom: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b1_branch2a\"\n name: \"res3b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2a\"\n name: \"scale3b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2a\"\n bottom: \"res3b1_branch2a\"\n name: \"res3b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2b\"\n name: \"res3b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2b\"\n name: \"scale3b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2b\"\n bottom: \"res3b1_branch2b\"\n name: \"res3b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2c\"\n name: \"res3b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2c\"\n top: \"res3b1_branch2c\"\n name: \"scale3b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b1_branch2c\"\n top: \"res3b1\"\n name: \"res3b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b1\"\n name: \"res3b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b2_branch2a\"\n name: \"res3b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2a\"\n name: \"scale3b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2a\"\n bottom: \"res3b2_branch2a\"\n name: \"res3b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2b\"\n name: \"res3b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2b\"\n name: \"scale3b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2b\"\n bottom: \"res3b2_branch2b\"\n name: \"res3b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2c\"\n name: \"res3b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2c\"\n top: \"res3b2_branch2c\"\n name: \"scale3b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1\"\n bottom: \"res3b2_branch2c\"\n top: \"res3b2\"\n name: \"res3b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b2\"\n name: \"res3b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b3_branch2a\"\n name: \"res3b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2a\"\n name: \"scale3b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2a\"\n bottom: \"res3b3_branch2a\"\n name: \"res3b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2b\"\n name: \"res3b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2b\"\n name: \"scale3b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2b\"\n bottom: \"res3b3_branch2b\"\n name: \"res3b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2c\"\n name: \"res3b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2c\"\n top: \"res3b3_branch2c\"\n name: \"scale3b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2\"\n bottom: \"res3b3_branch2c\"\n top: \"res3b3\"\n name: \"res3b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res3b3\"\n name: \"res3b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2a\"\n bottom: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2b\"\n bottom: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b1_branch2a\"\n name: \"res4b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2a\"\n name: \"scale4b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2a\"\n bottom: \"res4b1_branch2a\"\n name: \"res4b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2b\"\n name: \"res4b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2b\"\n name: \"scale4b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2b\"\n bottom: \"res4b1_branch2b\"\n name: \"res4b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2c\"\n name: \"res4b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2c\"\n top: \"res4b1_branch2c\"\n name: \"scale4b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b1_branch2c\"\n top: \"res4b1\"\n name: \"res4b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b1\"\n name: \"res4b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b2_branch2a\"\n name: \"res4b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2a\"\n name: \"scale4b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2a\"\n bottom: \"res4b2_branch2a\"\n name: \"res4b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2b\"\n name: \"res4b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2b\"\n name: \"scale4b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2b\"\n bottom: \"res4b2_branch2b\"\n name: \"res4b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2c\"\n name: \"res4b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2c\"\n top: \"res4b2_branch2c\"\n name: \"scale4b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1\"\n bottom: \"res4b2_branch2c\"\n top: \"res4b2\"\n name: \"res4b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b2\"\n name: \"res4b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b3_branch2a\"\n name: \"res4b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2a\"\n name: \"scale4b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2a\"\n bottom: \"res4b3_branch2a\"\n name: \"res4b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2b\"\n name: \"res4b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2b\"\n name: \"scale4b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2b\"\n bottom: \"res4b3_branch2b\"\n name: \"res4b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2c\"\n name: \"res4b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2c\"\n top: \"res4b3_branch2c\"\n name: \"scale4b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2\"\n bottom: \"res4b3_branch2c\"\n top: \"res4b3\"\n name: \"res4b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b3\"\n name: \"res4b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b4_branch2a\"\n name: \"res4b4_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2a\"\n name: \"scale4b4_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2a\"\n bottom: \"res4b4_branch2a\"\n name: \"res4b4_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2b\"\n name: \"res4b4_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2b\"\n name: \"scale4b4_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2b\"\n bottom: \"res4b4_branch2b\"\n name: \"res4b4_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2c\"\n name: \"res4b4_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2c\"\n top: \"res4b4_branch2c\"\n name: \"scale4b4_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3\"\n bottom: \"res4b4_branch2c\"\n top: \"res4b4\"\n name: \"res4b4\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b4\"\n name: \"res4b4_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b5_branch2a\"\n name: \"res4b5_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2a\"\n name: \"scale4b5_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2a\"\n bottom: \"res4b5_branch2a\"\n name: \"res4b5_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2b\"\n name: \"res4b5_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2b\"\n name: \"scale4b5_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2b\"\n bottom: \"res4b5_branch2b\"\n name: \"res4b5_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2c\"\n name: \"res4b5_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2c\"\n top: \"res4b5_branch2c\"\n name: \"scale4b5_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4\"\n bottom: \"res4b5_branch2c\"\n top: \"res4b5\"\n name: \"res4b5\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b5\"\n name: \"res4b5_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b6_branch2a\"\n name: \"res4b6_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2a\"\n name: \"scale4b6_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2a\"\n bottom: \"res4b6_branch2a\"\n name: \"res4b6_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2b\"\n name: \"res4b6_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2b\"\n name: \"scale4b6_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2b\"\n bottom: \"res4b6_branch2b\"\n name: \"res4b6_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2c\"\n name: \"res4b6_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2c\"\n top: \"res4b6_branch2c\"\n name: \"scale4b6_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5\"\n bottom: \"res4b6_branch2c\"\n top: \"res4b6\"\n name: \"res4b6\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b6\"\n name: \"res4b6_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b7_branch2a\"\n name: \"res4b7_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2a\"\n name: \"scale4b7_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2a\"\n bottom: \"res4b7_branch2a\"\n name: \"res4b7_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2b\"\n name: \"res4b7_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2b\"\n name: \"scale4b7_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2b\"\n bottom: \"res4b7_branch2b\"\n name: \"res4b7_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2c\"\n name: \"res4b7_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2c\"\n top: \"res4b7_branch2c\"\n name: \"scale4b7_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6\"\n bottom: \"res4b7_branch2c\"\n top: \"res4b7\"\n name: \"res4b7\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b7\"\n name: \"res4b7_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b8_branch2a\"\n name: \"res4b8_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2a\"\n name: \"scale4b8_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2a\"\n bottom: \"res4b8_branch2a\"\n name: \"res4b8_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2b\"\n name: \"res4b8_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2b\"\n name: \"scale4b8_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2b\"\n bottom: \"res4b8_branch2b\"\n name: \"res4b8_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2c\"\n name: \"res4b8_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2c\"\n top: \"res4b8_branch2c\"\n name: \"scale4b8_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7\"\n bottom: \"res4b8_branch2c\"\n top: \"res4b8\"\n name: \"res4b8\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b8\"\n name: \"res4b8_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b9_branch2a\"\n name: \"res4b9_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2a\"\n name: \"scale4b9_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2a\"\n bottom: \"res4b9_branch2a\"\n name: \"res4b9_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2b\"\n name: \"res4b9_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2b\"\n name: \"scale4b9_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2b\"\n bottom: \"res4b9_branch2b\"\n name: \"res4b9_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2c\"\n name: \"res4b9_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2c\"\n top: \"res4b9_branch2c\"\n name: \"scale4b9_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8\"\n bottom: \"res4b9_branch2c\"\n top: \"res4b9\"\n name: \"res4b9\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b9\"\n name: \"res4b9_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b10_branch2a\"\n name: \"res4b10_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2a\"\n name: \"scale4b10_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2a\"\n bottom: \"res4b10_branch2a\"\n name: \"res4b10_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2b\"\n name: \"res4b10_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2b\"\n name: \"scale4b10_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2b\"\n bottom: \"res4b10_branch2b\"\n name: \"res4b10_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2c\"\n name: \"res4b10_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b10_branch2c\"\n top: \"res4b10_branch2c\"\n name: \"scale4b10_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9\"\n bottom: \"res4b10_branch2c\"\n top: \"res4b10\"\n name: \"res4b10\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b10\"\n name: \"res4b10_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b11_branch2a\"\n name: \"res4b11_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2a\"\n name: \"scale4b11_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2a\"\n bottom: \"res4b11_branch2a\"\n name: \"res4b11_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2b\"\n name: \"res4b11_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2b\"\n name: \"scale4b11_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2b\"\n bottom: \"res4b11_branch2b\"\n name: \"res4b11_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2c\"\n name: \"res4b11_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2c\"\n top: \"res4b11_branch2c\"\n name: \"scale4b11_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10\"\n bottom: \"res4b11_branch2c\"\n top: \"res4b11\"\n name: \"res4b11\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b11\"\n name: \"res4b11_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b12_branch2a\"\n name: \"res4b12_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2a\"\n name: \"scale4b12_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2a\"\n bottom: \"res4b12_branch2a\"\n name: \"res4b12_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2b\"\n name: \"res4b12_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2b\"\n name: \"scale4b12_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2b\"\n bottom: \"res4b12_branch2b\"\n name: \"res4b12_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2c\"\n name: \"res4b12_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2c\"\n top: \"res4b12_branch2c\"\n name: \"scale4b12_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11\"\n bottom: \"res4b12_branch2c\"\n top: \"res4b12\"\n name: \"res4b12\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b12\"\n name: \"res4b12_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b13_branch2a\"\n name: \"res4b13_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2a\"\n name: \"scale4b13_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2a\"\n bottom: \"res4b13_branch2a\"\n name: \"res4b13_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2b\"\n name: \"res4b13_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2b\"\n name: \"scale4b13_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2b\"\n bottom: \"res4b13_branch2b\"\n name: \"res4b13_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2c\"\n name: \"res4b13_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2c\"\n top: \"res4b13_branch2c\"\n name: \"scale4b13_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12\"\n bottom: \"res4b13_branch2c\"\n top: \"res4b13\"\n name: \"res4b13\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b13\"\n name: \"res4b13_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b14_branch2a\"\n name: \"res4b14_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2a\"\n name: \"scale4b14_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2a\"\n bottom: \"res4b14_branch2a\"\n name: \"res4b14_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2b\"\n name: \"res4b14_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2b\"\n name: \"scale4b14_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2b\"\n bottom: \"res4b14_branch2b\"\n name: \"res4b14_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2c\"\n name: \"res4b14_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2c\"\n top: \"res4b14_branch2c\"\n name: \"scale4b14_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13\"\n bottom: \"res4b14_branch2c\"\n top: \"res4b14\"\n name: \"res4b14\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b14\"\n name: \"res4b14_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b15_branch2a\"\n name: \"res4b15_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2a\"\n name: \"scale4b15_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2a\"\n bottom: \"res4b15_branch2a\"\n name: \"res4b15_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2b\"\n name: \"res4b15_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2b\"\n name: \"scale4b15_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2b\"\n bottom: \"res4b15_branch2b\"\n name: \"res4b15_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2c\"\n name: \"res4b15_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2c\"\n top: \"res4b15_branch2c\"\n name: \"scale4b15_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14\"\n bottom: \"res4b15_branch2c\"\n top: \"res4b15\"\n name: \"res4b15\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b15\"\n name: \"res4b15_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b16_branch2a\"\n name: \"res4b16_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2a\"\n name: \"scale4b16_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2a\"\n bottom: \"res4b16_branch2a\"\n name: \"res4b16_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2b\"\n name: \"res4b16_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2b\"\n name: \"scale4b16_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2b\"\n bottom: \"res4b16_branch2b\"\n name: \"res4b16_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2c\"\n name: \"res4b16_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2c\"\n top: \"res4b16_branch2c\"\n name: \"scale4b16_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15\"\n bottom: \"res4b16_branch2c\"\n top: \"res4b16\"\n name: \"res4b16\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b16\"\n name: \"res4b16_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b17_branch2a\"\n name: \"res4b17_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2a\"\n name: \"scale4b17_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2a\"\n bottom: \"res4b17_branch2a\"\n name: \"res4b17_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2b\"\n name: \"res4b17_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2b\"\n name: \"scale4b17_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2b\"\n bottom: \"res4b17_branch2b\"\n name: \"res4b17_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2c\"\n name: \"res4b17_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2c\"\n top: \"res4b17_branch2c\"\n name: \"scale4b17_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16\"\n bottom: \"res4b17_branch2c\"\n top: \"res4b17\"\n name: \"res4b17\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b17\"\n name: \"res4b17_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b18_branch2a\"\n name: \"res4b18_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2a\"\n name: \"scale4b18_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2a\"\n bottom: \"res4b18_branch2a\"\n name: \"res4b18_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2b\"\n name: \"res4b18_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2b\"\n name: \"scale4b18_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2b\"\n bottom: \"res4b18_branch2b\"\n name: \"res4b18_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2c\"\n name: \"res4b18_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b18_branch2c\"\n top: \"res4b18_branch2c\"\n name: \"scale4b18_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17\"\n bottom: \"res4b18_branch2c\"\n top: \"res4b18\"\n name: \"res4b18\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b18\"\n name: \"res4b18_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b19_branch2a\"\n name: \"res4b19_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2a\"\n name: \"scale4b19_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2a\"\n bottom: \"res4b19_branch2a\"\n name: \"res4b19_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2b\"\n name: \"res4b19_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2b\"\n name: \"scale4b19_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2b\"\n bottom: \"res4b19_branch2b\"\n name: \"res4b19_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2c\"\n name: \"res4b19_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b19_branch2c\"\n top: \"res4b19_branch2c\"\n name: \"scale4b19_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18\"\n bottom: \"res4b19_branch2c\"\n top: \"res4b19\"\n name: \"res4b19\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b19\"\n name: \"res4b19_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b20_branch2a\"\n name: \"res4b20_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2a\"\n name: \"scale4b20_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2a\"\n bottom: \"res4b20_branch2a\"\n name: \"res4b20_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2b\"\n name: \"res4b20_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2b\"\n name: \"scale4b20_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2b\"\n bottom: \"res4b20_branch2b\"\n name: \"res4b20_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2c\"\n name: \"res4b20_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2c\"\n top: \"res4b20_branch2c\"\n name: \"scale4b20_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19\"\n bottom: \"res4b20_branch2c\"\n top: \"res4b20\"\n name: \"res4b20\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b20\"\n name: \"res4b20_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b21_branch2a\"\n name: \"res4b21_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2a\"\n name: \"scale4b21_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2a\"\n bottom: \"res4b21_branch2a\"\n name: \"res4b21_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2b\"\n name: \"res4b21_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2b\"\n name: \"scale4b21_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2b\"\n bottom: \"res4b21_branch2b\"\n name: \"res4b21_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2c\"\n name: \"res4b21_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2c\"\n top: \"res4b21_branch2c\"\n name: \"scale4b21_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20\"\n bottom: \"res4b21_branch2c\"\n top: \"res4b21\"\n name: \"res4b21\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b21\"\n name: \"res4b21_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b22_branch2a\"\n name: \"res4b22_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2a\"\n name: \"scale4b22_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2a\"\n bottom: \"res4b22_branch2a\"\n name: \"res4b22_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2b\"\n name: \"res4b22_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2b\"\n name: \"scale4b22_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2b\"\n bottom: \"res4b22_branch2b\"\n name: \"res4b22_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2c\"\n name: \"res4b22_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b22_branch2c\"\n top: \"res4b22_branch2c\"\n name: \"scale4b22_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21\"\n bottom: \"res4b22_branch2c\"\n top: \"res4b22\"\n name: \"res4b22\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b22\"\n top: \"res4b22\"\n name: \"res4b22_relu\"\n type: \"ReLU\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4b22\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rois'\n top: 'scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n" }, { "path": "models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_alt_opt/stage1_fast_rcnn_solver30k40k.pt", "content": "train_net: \"models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_alt_opt/stage1_fast_rcnn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 30000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet101_bn_scale_merged_fast_rcnn\"\n" }, { "path": "models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_alt_opt/stage1_fast_rcnn_train.pt", "content": "name: \"ResNet101_BN_SCALE_Merged\"\nlayer {\n name: 'data'\n type: 'Python'\n top: 'data'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"conv1\"\n bottom: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2a\"\n bottom: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2b\"\n bottom: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2a\"\n bottom: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2b\"\n bottom: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2a\"\n bottom: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2b\"\n bottom: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2a\"\n bottom: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2b\"\n bottom: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b1_branch2a\"\n name: \"res3b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2a\"\n name: \"scale3b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2a\"\n bottom: \"res3b1_branch2a\"\n name: \"res3b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2b\"\n name: \"res3b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2b\"\n name: \"scale3b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2b\"\n bottom: \"res3b1_branch2b\"\n name: \"res3b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2c\"\n name: \"res3b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2c\"\n top: \"res3b1_branch2c\"\n name: \"scale3b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b1_branch2c\"\n top: \"res3b1\"\n name: \"res3b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b1\"\n name: \"res3b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b2_branch2a\"\n name: \"res3b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2a\"\n name: \"scale3b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2a\"\n bottom: \"res3b2_branch2a\"\n name: \"res3b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2b\"\n name: \"res3b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2b\"\n name: \"scale3b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2b\"\n bottom: \"res3b2_branch2b\"\n name: \"res3b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2c\"\n name: \"res3b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2c\"\n top: \"res3b2_branch2c\"\n name: \"scale3b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1\"\n bottom: \"res3b2_branch2c\"\n top: \"res3b2\"\n name: \"res3b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b2\"\n name: \"res3b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b3_branch2a\"\n name: \"res3b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2a\"\n name: \"scale3b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2a\"\n bottom: \"res3b3_branch2a\"\n name: \"res3b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2b\"\n name: \"res3b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2b\"\n name: \"scale3b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2b\"\n bottom: \"res3b3_branch2b\"\n name: \"res3b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2c\"\n name: \"res3b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2c\"\n top: \"res3b3_branch2c\"\n name: \"scale3b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2\"\n bottom: \"res3b3_branch2c\"\n top: \"res3b3\"\n name: \"res3b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res3b3\"\n name: \"res3b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2a\"\n bottom: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2b\"\n bottom: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b1_branch2a\"\n name: \"res4b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2a\"\n name: \"scale4b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2a\"\n bottom: \"res4b1_branch2a\"\n name: \"res4b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2b\"\n name: \"res4b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2b\"\n name: \"scale4b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2b\"\n bottom: \"res4b1_branch2b\"\n name: \"res4b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2c\"\n name: \"res4b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2c\"\n top: \"res4b1_branch2c\"\n name: \"scale4b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b1_branch2c\"\n top: \"res4b1\"\n name: \"res4b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b1\"\n name: \"res4b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b2_branch2a\"\n name: \"res4b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2a\"\n name: \"scale4b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2a\"\n bottom: \"res4b2_branch2a\"\n name: \"res4b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2b\"\n name: \"res4b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2b\"\n name: \"scale4b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2b\"\n bottom: \"res4b2_branch2b\"\n name: \"res4b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2c\"\n name: \"res4b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2c\"\n top: \"res4b2_branch2c\"\n name: \"scale4b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1\"\n bottom: \"res4b2_branch2c\"\n top: \"res4b2\"\n name: \"res4b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b2\"\n name: \"res4b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b3_branch2a\"\n name: \"res4b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2a\"\n name: \"scale4b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2a\"\n bottom: \"res4b3_branch2a\"\n name: \"res4b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2b\"\n name: \"res4b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2b\"\n name: \"scale4b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2b\"\n bottom: \"res4b3_branch2b\"\n name: \"res4b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2c\"\n name: \"res4b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2c\"\n top: \"res4b3_branch2c\"\n name: \"scale4b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2\"\n bottom: \"res4b3_branch2c\"\n top: \"res4b3\"\n name: \"res4b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b3\"\n name: \"res4b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b4_branch2a\"\n name: \"res4b4_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2a\"\n name: \"scale4b4_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2a\"\n bottom: \"res4b4_branch2a\"\n name: \"res4b4_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2b\"\n name: \"res4b4_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2b\"\n name: \"scale4b4_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2b\"\n bottom: \"res4b4_branch2b\"\n name: \"res4b4_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2c\"\n name: \"res4b4_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2c\"\n top: \"res4b4_branch2c\"\n name: \"scale4b4_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3\"\n bottom: \"res4b4_branch2c\"\n top: \"res4b4\"\n name: \"res4b4\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b4\"\n name: \"res4b4_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b5_branch2a\"\n name: \"res4b5_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2a\"\n name: \"scale4b5_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2a\"\n bottom: \"res4b5_branch2a\"\n name: \"res4b5_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2b\"\n name: \"res4b5_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2b\"\n name: \"scale4b5_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2b\"\n bottom: \"res4b5_branch2b\"\n name: \"res4b5_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2c\"\n name: \"res4b5_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2c\"\n top: \"res4b5_branch2c\"\n name: \"scale4b5_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4\"\n bottom: \"res4b5_branch2c\"\n top: \"res4b5\"\n name: \"res4b5\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b5\"\n name: \"res4b5_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b6_branch2a\"\n name: \"res4b6_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2a\"\n name: \"scale4b6_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2a\"\n bottom: \"res4b6_branch2a\"\n name: \"res4b6_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2b\"\n name: \"res4b6_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2b\"\n name: \"scale4b6_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2b\"\n bottom: \"res4b6_branch2b\"\n name: \"res4b6_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2c\"\n name: \"res4b6_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2c\"\n top: \"res4b6_branch2c\"\n name: \"scale4b6_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5\"\n bottom: \"res4b6_branch2c\"\n top: \"res4b6\"\n name: \"res4b6\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b6\"\n name: \"res4b6_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b7_branch2a\"\n name: \"res4b7_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2a\"\n name: \"scale4b7_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2a\"\n bottom: \"res4b7_branch2a\"\n name: \"res4b7_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2b\"\n name: \"res4b7_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2b\"\n name: \"scale4b7_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2b\"\n bottom: \"res4b7_branch2b\"\n name: \"res4b7_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2c\"\n name: \"res4b7_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2c\"\n top: \"res4b7_branch2c\"\n name: \"scale4b7_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6\"\n bottom: \"res4b7_branch2c\"\n top: \"res4b7\"\n name: \"res4b7\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b7\"\n name: \"res4b7_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b8_branch2a\"\n name: \"res4b8_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2a\"\n name: \"scale4b8_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2a\"\n bottom: \"res4b8_branch2a\"\n name: \"res4b8_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2b\"\n name: \"res4b8_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2b\"\n name: \"scale4b8_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2b\"\n bottom: \"res4b8_branch2b\"\n name: \"res4b8_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2c\"\n name: \"res4b8_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2c\"\n top: \"res4b8_branch2c\"\n name: \"scale4b8_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7\"\n bottom: \"res4b8_branch2c\"\n top: \"res4b8\"\n name: \"res4b8\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b8\"\n name: \"res4b8_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b9_branch2a\"\n name: \"res4b9_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2a\"\n name: \"scale4b9_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2a\"\n bottom: \"res4b9_branch2a\"\n name: \"res4b9_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2b\"\n name: \"res4b9_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2b\"\n name: \"scale4b9_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2b\"\n bottom: \"res4b9_branch2b\"\n name: \"res4b9_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2c\"\n name: \"res4b9_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2c\"\n top: \"res4b9_branch2c\"\n name: \"scale4b9_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8\"\n bottom: \"res4b9_branch2c\"\n top: \"res4b9\"\n name: \"res4b9\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b9\"\n name: \"res4b9_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b10_branch2a\"\n name: \"res4b10_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2a\"\n name: \"scale4b10_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2a\"\n bottom: \"res4b10_branch2a\"\n name: \"res4b10_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2b\"\n name: \"res4b10_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2b\"\n name: \"scale4b10_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2b\"\n bottom: \"res4b10_branch2b\"\n name: \"res4b10_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2c\"\n name: \"res4b10_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b10_branch2c\"\n top: \"res4b10_branch2c\"\n name: \"scale4b10_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9\"\n bottom: \"res4b10_branch2c\"\n top: \"res4b10\"\n name: \"res4b10\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b10\"\n name: \"res4b10_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b11_branch2a\"\n name: \"res4b11_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2a\"\n name: \"scale4b11_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2a\"\n bottom: \"res4b11_branch2a\"\n name: \"res4b11_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2b\"\n name: \"res4b11_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2b\"\n name: \"scale4b11_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2b\"\n bottom: \"res4b11_branch2b\"\n name: \"res4b11_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2c\"\n name: \"res4b11_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2c\"\n top: \"res4b11_branch2c\"\n name: \"scale4b11_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10\"\n bottom: \"res4b11_branch2c\"\n top: \"res4b11\"\n name: \"res4b11\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b11\"\n name: \"res4b11_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b12_branch2a\"\n name: \"res4b12_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2a\"\n name: \"scale4b12_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2a\"\n bottom: \"res4b12_branch2a\"\n name: \"res4b12_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2b\"\n name: \"res4b12_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2b\"\n name: \"scale4b12_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2b\"\n bottom: \"res4b12_branch2b\"\n name: \"res4b12_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2c\"\n name: \"res4b12_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2c\"\n top: \"res4b12_branch2c\"\n name: \"scale4b12_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11\"\n bottom: \"res4b12_branch2c\"\n top: \"res4b12\"\n name: \"res4b12\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b12\"\n name: \"res4b12_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b13_branch2a\"\n name: \"res4b13_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2a\"\n name: \"scale4b13_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2a\"\n bottom: \"res4b13_branch2a\"\n name: \"res4b13_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2b\"\n name: \"res4b13_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2b\"\n name: \"scale4b13_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2b\"\n bottom: \"res4b13_branch2b\"\n name: \"res4b13_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2c\"\n name: \"res4b13_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2c\"\n top: \"res4b13_branch2c\"\n name: \"scale4b13_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12\"\n bottom: \"res4b13_branch2c\"\n top: \"res4b13\"\n name: \"res4b13\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b13\"\n name: \"res4b13_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b14_branch2a\"\n name: \"res4b14_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2a\"\n name: \"scale4b14_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2a\"\n bottom: \"res4b14_branch2a\"\n name: \"res4b14_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2b\"\n name: \"res4b14_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2b\"\n name: \"scale4b14_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2b\"\n bottom: \"res4b14_branch2b\"\n name: \"res4b14_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2c\"\n name: \"res4b14_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2c\"\n top: \"res4b14_branch2c\"\n name: \"scale4b14_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13\"\n bottom: \"res4b14_branch2c\"\n top: \"res4b14\"\n name: \"res4b14\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b14\"\n name: \"res4b14_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b15_branch2a\"\n name: \"res4b15_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2a\"\n name: \"scale4b15_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2a\"\n bottom: \"res4b15_branch2a\"\n name: \"res4b15_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2b\"\n name: \"res4b15_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2b\"\n name: \"scale4b15_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2b\"\n bottom: \"res4b15_branch2b\"\n name: \"res4b15_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2c\"\n name: \"res4b15_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2c\"\n top: \"res4b15_branch2c\"\n name: \"scale4b15_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14\"\n bottom: \"res4b15_branch2c\"\n top: \"res4b15\"\n name: \"res4b15\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b15\"\n name: \"res4b15_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b16_branch2a\"\n name: \"res4b16_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2a\"\n name: \"scale4b16_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2a\"\n bottom: \"res4b16_branch2a\"\n name: \"res4b16_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2b\"\n name: \"res4b16_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2b\"\n name: \"scale4b16_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2b\"\n bottom: \"res4b16_branch2b\"\n name: \"res4b16_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2c\"\n name: \"res4b16_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2c\"\n top: \"res4b16_branch2c\"\n name: \"scale4b16_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15\"\n bottom: \"res4b16_branch2c\"\n top: \"res4b16\"\n name: \"res4b16\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b16\"\n name: \"res4b16_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b17_branch2a\"\n name: \"res4b17_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2a\"\n name: \"scale4b17_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2a\"\n bottom: \"res4b17_branch2a\"\n name: \"res4b17_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2b\"\n name: \"res4b17_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2b\"\n name: \"scale4b17_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2b\"\n bottom: \"res4b17_branch2b\"\n name: \"res4b17_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2c\"\n name: \"res4b17_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2c\"\n top: \"res4b17_branch2c\"\n name: \"scale4b17_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16\"\n bottom: \"res4b17_branch2c\"\n top: \"res4b17\"\n name: \"res4b17\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b17\"\n name: \"res4b17_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b18_branch2a\"\n name: \"res4b18_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2a\"\n name: \"scale4b18_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2a\"\n bottom: \"res4b18_branch2a\"\n name: \"res4b18_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2b\"\n name: \"res4b18_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2b\"\n name: \"scale4b18_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2b\"\n bottom: \"res4b18_branch2b\"\n name: \"res4b18_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2c\"\n name: \"res4b18_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b18_branch2c\"\n top: \"res4b18_branch2c\"\n name: \"scale4b18_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17\"\n bottom: \"res4b18_branch2c\"\n top: \"res4b18\"\n name: \"res4b18\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b18\"\n name: \"res4b18_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b19_branch2a\"\n name: \"res4b19_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2a\"\n name: \"scale4b19_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2a\"\n bottom: \"res4b19_branch2a\"\n name: \"res4b19_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2b\"\n name: \"res4b19_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2b\"\n name: \"scale4b19_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2b\"\n bottom: \"res4b19_branch2b\"\n name: \"res4b19_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2c\"\n name: \"res4b19_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b19_branch2c\"\n top: \"res4b19_branch2c\"\n name: \"scale4b19_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18\"\n bottom: \"res4b19_branch2c\"\n top: \"res4b19\"\n name: \"res4b19\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b19\"\n name: \"res4b19_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b20_branch2a\"\n name: \"res4b20_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2a\"\n name: \"scale4b20_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2a\"\n bottom: \"res4b20_branch2a\"\n name: \"res4b20_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2b\"\n name: \"res4b20_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2b\"\n name: \"scale4b20_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2b\"\n bottom: \"res4b20_branch2b\"\n name: \"res4b20_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2c\"\n name: \"res4b20_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2c\"\n top: \"res4b20_branch2c\"\n name: \"scale4b20_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19\"\n bottom: \"res4b20_branch2c\"\n top: \"res4b20\"\n name: \"res4b20\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b20\"\n name: \"res4b20_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b21_branch2a\"\n name: \"res4b21_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2a\"\n name: \"scale4b21_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2a\"\n bottom: \"res4b21_branch2a\"\n name: \"res4b21_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2b\"\n name: \"res4b21_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2b\"\n name: \"scale4b21_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2b\"\n bottom: \"res4b21_branch2b\"\n name: \"res4b21_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2c\"\n name: \"res4b21_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2c\"\n top: \"res4b21_branch2c\"\n name: \"scale4b21_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20\"\n bottom: \"res4b21_branch2c\"\n top: \"res4b21\"\n name: \"res4b21\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b21\"\n name: \"res4b21_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b22_branch2a\"\n name: \"res4b22_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2a\"\n name: \"scale4b22_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2a\"\n bottom: \"res4b22_branch2a\"\n name: \"res4b22_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2b\"\n name: \"res4b22_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2b\"\n name: \"scale4b22_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2b\"\n bottom: \"res4b22_branch2b\"\n name: \"res4b22_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2c\"\n name: \"res4b22_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b22_branch2c\"\n top: \"res4b22_branch2c\"\n name: \"scale4b22_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21\"\n bottom: \"res4b22_branch2c\"\n top: \"res4b22\"\n name: \"res4b22\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b22\"\n top: \"res4b22\"\n name: \"res4b22_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"res4b22\"\n bottom: \"rois\"\n top: \"roi_pool5\"\n roi_pooling_param {\n pooled_w: 14\n pooled_h: 14\n spatial_scale: 0.0625 # 1/16\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\n\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"loss_bbox\"\n loss_weight: 1\n}\n\n\n#========= RPN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4b22\"\n top: \"rpn/output\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"silence_rpn_cls_score\"\n type: \"Silence\"\n bottom: \"rpn_cls_score\"\n}\nlayer {\n name: \"silence_rpn_bbox_pred\"\n type: \"Silence\"\n bottom: \"rpn_bbox_pred\"\n}\n" }, { "path": "models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_alt_opt/stage1_rpn_solver60k80k.pt", "content": "train_net: \"models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_alt_opt/stage1_rpn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 60000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet101_bn_scale_merged_rpn\"\n" }, { "path": "models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_alt_opt/stage1_rpn_train.pt", "content": "name: \"ResNet101_BN_SCALE_Merged\"\n\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"conv1\"\n bottom: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2a\"\n bottom: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2b\"\n bottom: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2a\"\n bottom: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2b\"\n bottom: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2a\"\n bottom: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2b\"\n bottom: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2a\"\n bottom: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2b\"\n bottom: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b1_branch2a\"\n name: \"res3b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2a\"\n name: \"scale3b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2a\"\n bottom: \"res3b1_branch2a\"\n name: \"res3b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2b\"\n name: \"res3b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2b\"\n name: \"scale3b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2b\"\n bottom: \"res3b1_branch2b\"\n name: \"res3b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2c\"\n name: \"res3b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2c\"\n top: \"res3b1_branch2c\"\n name: \"scale3b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b1_branch2c\"\n top: \"res3b1\"\n name: \"res3b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b1\"\n name: \"res3b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b2_branch2a\"\n name: \"res3b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2a\"\n name: \"scale3b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2a\"\n bottom: \"res3b2_branch2a\"\n name: \"res3b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2b\"\n name: \"res3b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2b\"\n name: \"scale3b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2b\"\n bottom: \"res3b2_branch2b\"\n name: \"res3b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2c\"\n name: \"res3b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2c\"\n top: \"res3b2_branch2c\"\n name: \"scale3b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1\"\n bottom: \"res3b2_branch2c\"\n top: \"res3b2\"\n name: \"res3b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b2\"\n name: \"res3b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b3_branch2a\"\n name: \"res3b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2a\"\n name: \"scale3b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2a\"\n bottom: \"res3b3_branch2a\"\n name: \"res3b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2b\"\n name: \"res3b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2b\"\n name: \"scale3b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2b\"\n bottom: \"res3b3_branch2b\"\n name: \"res3b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2c\"\n name: \"res3b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2c\"\n top: \"res3b3_branch2c\"\n name: \"scale3b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2\"\n bottom: \"res3b3_branch2c\"\n top: \"res3b3\"\n name: \"res3b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res3b3\"\n name: \"res3b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2a\"\n bottom: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2b\"\n bottom: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b1_branch2a\"\n name: \"res4b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2a\"\n name: \"scale4b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2a\"\n bottom: \"res4b1_branch2a\"\n name: \"res4b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2b\"\n name: \"res4b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2b\"\n name: \"scale4b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2b\"\n bottom: \"res4b1_branch2b\"\n name: \"res4b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2c\"\n name: \"res4b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2c\"\n top: \"res4b1_branch2c\"\n name: \"scale4b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b1_branch2c\"\n top: \"res4b1\"\n name: \"res4b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b1\"\n name: \"res4b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b2_branch2a\"\n name: \"res4b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2a\"\n name: \"scale4b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2a\"\n bottom: \"res4b2_branch2a\"\n name: \"res4b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2b\"\n name: \"res4b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2b\"\n name: \"scale4b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2b\"\n bottom: \"res4b2_branch2b\"\n name: \"res4b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2c\"\n name: \"res4b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2c\"\n top: \"res4b2_branch2c\"\n name: \"scale4b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1\"\n bottom: \"res4b2_branch2c\"\n top: \"res4b2\"\n name: \"res4b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b2\"\n name: \"res4b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b3_branch2a\"\n name: \"res4b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2a\"\n name: \"scale4b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2a\"\n bottom: \"res4b3_branch2a\"\n name: \"res4b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2b\"\n name: \"res4b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2b\"\n name: \"scale4b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2b\"\n bottom: \"res4b3_branch2b\"\n name: \"res4b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2c\"\n name: \"res4b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2c\"\n top: \"res4b3_branch2c\"\n name: \"scale4b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2\"\n bottom: \"res4b3_branch2c\"\n top: \"res4b3\"\n name: \"res4b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b3\"\n name: \"res4b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b4_branch2a\"\n name: \"res4b4_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2a\"\n name: \"scale4b4_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2a\"\n bottom: \"res4b4_branch2a\"\n name: \"res4b4_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2b\"\n name: \"res4b4_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2b\"\n name: \"scale4b4_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2b\"\n bottom: \"res4b4_branch2b\"\n name: \"res4b4_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2c\"\n name: \"res4b4_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2c\"\n top: \"res4b4_branch2c\"\n name: \"scale4b4_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3\"\n bottom: \"res4b4_branch2c\"\n top: \"res4b4\"\n name: \"res4b4\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b4\"\n name: \"res4b4_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b5_branch2a\"\n name: \"res4b5_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2a\"\n name: \"scale4b5_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2a\"\n bottom: \"res4b5_branch2a\"\n name: \"res4b5_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2b\"\n name: \"res4b5_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2b\"\n name: \"scale4b5_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2b\"\n bottom: \"res4b5_branch2b\"\n name: \"res4b5_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2c\"\n name: \"res4b5_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2c\"\n top: \"res4b5_branch2c\"\n name: \"scale4b5_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4\"\n bottom: \"res4b5_branch2c\"\n top: \"res4b5\"\n name: \"res4b5\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b5\"\n name: \"res4b5_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b6_branch2a\"\n name: \"res4b6_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2a\"\n name: \"scale4b6_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2a\"\n bottom: \"res4b6_branch2a\"\n name: \"res4b6_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2b\"\n name: \"res4b6_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2b\"\n name: \"scale4b6_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2b\"\n bottom: \"res4b6_branch2b\"\n name: \"res4b6_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2c\"\n name: \"res4b6_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2c\"\n top: \"res4b6_branch2c\"\n name: \"scale4b6_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5\"\n bottom: \"res4b6_branch2c\"\n top: \"res4b6\"\n name: \"res4b6\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b6\"\n name: \"res4b6_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b7_branch2a\"\n name: \"res4b7_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2a\"\n name: \"scale4b7_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2a\"\n bottom: \"res4b7_branch2a\"\n name: \"res4b7_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2b\"\n name: \"res4b7_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2b\"\n name: \"scale4b7_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2b\"\n bottom: \"res4b7_branch2b\"\n name: \"res4b7_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2c\"\n name: \"res4b7_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2c\"\n top: \"res4b7_branch2c\"\n name: \"scale4b7_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6\"\n bottom: \"res4b7_branch2c\"\n top: \"res4b7\"\n name: \"res4b7\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b7\"\n name: \"res4b7_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b8_branch2a\"\n name: \"res4b8_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2a\"\n name: \"scale4b8_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2a\"\n bottom: \"res4b8_branch2a\"\n name: \"res4b8_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2b\"\n name: \"res4b8_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2b\"\n name: \"scale4b8_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2b\"\n bottom: \"res4b8_branch2b\"\n name: \"res4b8_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2c\"\n name: \"res4b8_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2c\"\n top: \"res4b8_branch2c\"\n name: \"scale4b8_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7\"\n bottom: \"res4b8_branch2c\"\n top: \"res4b8\"\n name: \"res4b8\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b8\"\n name: \"res4b8_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b9_branch2a\"\n name: \"res4b9_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2a\"\n name: \"scale4b9_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2a\"\n bottom: \"res4b9_branch2a\"\n name: \"res4b9_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2b\"\n name: \"res4b9_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2b\"\n name: \"scale4b9_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2b\"\n bottom: \"res4b9_branch2b\"\n name: \"res4b9_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2c\"\n name: \"res4b9_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2c\"\n top: \"res4b9_branch2c\"\n name: \"scale4b9_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8\"\n bottom: \"res4b9_branch2c\"\n top: \"res4b9\"\n name: \"res4b9\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b9\"\n name: \"res4b9_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b10_branch2a\"\n name: \"res4b10_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2a\"\n name: \"scale4b10_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2a\"\n bottom: \"res4b10_branch2a\"\n name: \"res4b10_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2b\"\n name: \"res4b10_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2b\"\n name: \"scale4b10_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2b\"\n bottom: \"res4b10_branch2b\"\n name: \"res4b10_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2c\"\n name: \"res4b10_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b10_branch2c\"\n top: \"res4b10_branch2c\"\n name: \"scale4b10_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9\"\n bottom: \"res4b10_branch2c\"\n top: \"res4b10\"\n name: \"res4b10\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b10\"\n name: \"res4b10_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b11_branch2a\"\n name: \"res4b11_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2a\"\n name: \"scale4b11_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2a\"\n bottom: \"res4b11_branch2a\"\n name: \"res4b11_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2b\"\n name: \"res4b11_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2b\"\n name: \"scale4b11_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2b\"\n bottom: \"res4b11_branch2b\"\n name: \"res4b11_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2c\"\n name: \"res4b11_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2c\"\n top: \"res4b11_branch2c\"\n name: \"scale4b11_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10\"\n bottom: \"res4b11_branch2c\"\n top: \"res4b11\"\n name: \"res4b11\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b11\"\n name: \"res4b11_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b12_branch2a\"\n name: \"res4b12_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2a\"\n name: \"scale4b12_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2a\"\n bottom: \"res4b12_branch2a\"\n name: \"res4b12_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2b\"\n name: \"res4b12_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2b\"\n name: \"scale4b12_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2b\"\n bottom: \"res4b12_branch2b\"\n name: \"res4b12_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2c\"\n name: \"res4b12_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2c\"\n top: \"res4b12_branch2c\"\n name: \"scale4b12_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11\"\n bottom: \"res4b12_branch2c\"\n top: \"res4b12\"\n name: \"res4b12\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b12\"\n name: \"res4b12_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b13_branch2a\"\n name: \"res4b13_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2a\"\n name: \"scale4b13_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2a\"\n bottom: \"res4b13_branch2a\"\n name: \"res4b13_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2b\"\n name: \"res4b13_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2b\"\n name: \"scale4b13_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2b\"\n bottom: \"res4b13_branch2b\"\n name: \"res4b13_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2c\"\n name: \"res4b13_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2c\"\n top: \"res4b13_branch2c\"\n name: \"scale4b13_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12\"\n bottom: \"res4b13_branch2c\"\n top: \"res4b13\"\n name: \"res4b13\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b13\"\n name: \"res4b13_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b14_branch2a\"\n name: \"res4b14_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2a\"\n name: \"scale4b14_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2a\"\n bottom: \"res4b14_branch2a\"\n name: \"res4b14_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2b\"\n name: \"res4b14_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2b\"\n name: \"scale4b14_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2b\"\n bottom: \"res4b14_branch2b\"\n name: \"res4b14_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2c\"\n name: \"res4b14_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2c\"\n top: \"res4b14_branch2c\"\n name: \"scale4b14_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13\"\n bottom: \"res4b14_branch2c\"\n top: \"res4b14\"\n name: \"res4b14\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b14\"\n name: \"res4b14_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b15_branch2a\"\n name: \"res4b15_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2a\"\n name: \"scale4b15_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2a\"\n bottom: \"res4b15_branch2a\"\n name: \"res4b15_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2b\"\n name: \"res4b15_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2b\"\n name: \"scale4b15_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2b\"\n bottom: \"res4b15_branch2b\"\n name: \"res4b15_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2c\"\n name: \"res4b15_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2c\"\n top: \"res4b15_branch2c\"\n name: \"scale4b15_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14\"\n bottom: \"res4b15_branch2c\"\n top: \"res4b15\"\n name: \"res4b15\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b15\"\n name: \"res4b15_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b16_branch2a\"\n name: \"res4b16_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2a\"\n name: \"scale4b16_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2a\"\n bottom: \"res4b16_branch2a\"\n name: \"res4b16_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2b\"\n name: \"res4b16_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2b\"\n name: \"scale4b16_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2b\"\n bottom: \"res4b16_branch2b\"\n name: \"res4b16_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2c\"\n name: \"res4b16_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2c\"\n top: \"res4b16_branch2c\"\n name: \"scale4b16_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15\"\n bottom: \"res4b16_branch2c\"\n top: \"res4b16\"\n name: \"res4b16\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b16\"\n name: \"res4b16_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b17_branch2a\"\n name: \"res4b17_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2a\"\n name: \"scale4b17_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2a\"\n bottom: \"res4b17_branch2a\"\n name: \"res4b17_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2b\"\n name: \"res4b17_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2b\"\n name: \"scale4b17_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2b\"\n bottom: \"res4b17_branch2b\"\n name: \"res4b17_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2c\"\n name: \"res4b17_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2c\"\n top: \"res4b17_branch2c\"\n name: \"scale4b17_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16\"\n bottom: \"res4b17_branch2c\"\n top: \"res4b17\"\n name: \"res4b17\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b17\"\n name: \"res4b17_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b18_branch2a\"\n name: \"res4b18_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2a\"\n name: \"scale4b18_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2a\"\n bottom: \"res4b18_branch2a\"\n name: \"res4b18_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2b\"\n name: \"res4b18_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2b\"\n name: \"scale4b18_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2b\"\n bottom: \"res4b18_branch2b\"\n name: \"res4b18_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2c\"\n name: \"res4b18_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b18_branch2c\"\n top: \"res4b18_branch2c\"\n name: \"scale4b18_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17\"\n bottom: \"res4b18_branch2c\"\n top: \"res4b18\"\n name: \"res4b18\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b18\"\n name: \"res4b18_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b19_branch2a\"\n name: \"res4b19_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2a\"\n name: \"scale4b19_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2a\"\n bottom: \"res4b19_branch2a\"\n name: \"res4b19_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2b\"\n name: \"res4b19_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2b\"\n name: \"scale4b19_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2b\"\n bottom: \"res4b19_branch2b\"\n name: \"res4b19_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2c\"\n name: \"res4b19_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b19_branch2c\"\n top: \"res4b19_branch2c\"\n name: \"scale4b19_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18\"\n bottom: \"res4b19_branch2c\"\n top: \"res4b19\"\n name: \"res4b19\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b19\"\n name: \"res4b19_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b20_branch2a\"\n name: \"res4b20_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2a\"\n name: \"scale4b20_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2a\"\n bottom: \"res4b20_branch2a\"\n name: \"res4b20_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2b\"\n name: \"res4b20_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2b\"\n name: \"scale4b20_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2b\"\n bottom: \"res4b20_branch2b\"\n name: \"res4b20_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2c\"\n name: \"res4b20_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2c\"\n top: \"res4b20_branch2c\"\n name: \"scale4b20_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19\"\n bottom: \"res4b20_branch2c\"\n top: \"res4b20\"\n name: \"res4b20\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b20\"\n name: \"res4b20_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b21_branch2a\"\n name: \"res4b21_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2a\"\n name: \"scale4b21_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2a\"\n bottom: \"res4b21_branch2a\"\n name: \"res4b21_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2b\"\n name: \"res4b21_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2b\"\n name: \"scale4b21_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2b\"\n bottom: \"res4b21_branch2b\"\n name: \"res4b21_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2c\"\n name: \"res4b21_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2c\"\n top: \"res4b21_branch2c\"\n name: \"scale4b21_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20\"\n bottom: \"res4b21_branch2c\"\n top: \"res4b21\"\n name: \"res4b21\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b21\"\n name: \"res4b21_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b22_branch2a\"\n name: \"res4b22_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2a\"\n name: \"scale4b22_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2a\"\n bottom: \"res4b22_branch2a\"\n name: \"res4b22_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2b\"\n name: \"res4b22_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2b\"\n name: \"scale4b22_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2b\"\n bottom: \"res4b22_branch2b\"\n name: \"res4b22_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2c\"\n name: \"res4b22_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b22_branch2c\"\n top: \"res4b22_branch2c\"\n name: \"scale4b22_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21\"\n bottom: \"res4b22_branch2c\"\n top: \"res4b22\"\n name: \"res4b22\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b22\"\n top: \"res4b22\"\n name: \"res4b22_relu\"\n type: \"ReLU\"\n}\n\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4b22\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RCNN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"dummy_roi_pool_res4b22\"\n type: \"DummyData\"\n top: \"dummy_roi_pool_res4b22\"\n dummy_data_param {\n shape { dim: 1 dim: 1024 dim: 14 dim: 14 }\n data_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"dummy_roi_pool_res4b22\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"dummy_roi_pool_res4b22\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\nlayer {\n name: \"silence_pool5\"\n type: \"Silence\"\n bottom: \"pool5\"\n}\n" }, { "path": "models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_alt_opt/stage2_fast_rcnn_solver30k40k.pt", "content": "train_net: \"models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_alt_opt/stage2_fast_rcnn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 30000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet101_bn_scale_merged_fast_rcnn\"\n" }, { "path": "models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_alt_opt/stage2_fast_rcnn_train.pt", "content": "name: \"ResNet101_BN_SCALE_Merged\"\nlayer {\n name: 'data'\n type: 'Python'\n top: 'data'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"conv1\"\n bottom: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2a\"\n bottom: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2b\"\n bottom: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2a\"\n bottom: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2b\"\n bottom: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2a\"\n bottom: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2b\"\n bottom: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2a\"\n bottom: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2b\"\n bottom: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b1_branch2a\"\n name: \"res3b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2a\"\n name: \"scale3b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2a\"\n bottom: \"res3b1_branch2a\"\n name: \"res3b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2b\"\n name: \"res3b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2b\"\n name: \"scale3b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2b\"\n bottom: \"res3b1_branch2b\"\n name: \"res3b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2c\"\n name: \"res3b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2c\"\n top: \"res3b1_branch2c\"\n name: \"scale3b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b1_branch2c\"\n top: \"res3b1\"\n name: \"res3b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b1\"\n name: \"res3b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b2_branch2a\"\n name: \"res3b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2a\"\n name: \"scale3b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2a\"\n bottom: \"res3b2_branch2a\"\n name: \"res3b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2b\"\n name: \"res3b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2b\"\n name: \"scale3b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2b\"\n bottom: \"res3b2_branch2b\"\n name: \"res3b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2c\"\n name: \"res3b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2c\"\n top: \"res3b2_branch2c\"\n name: \"scale3b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1\"\n bottom: \"res3b2_branch2c\"\n top: \"res3b2\"\n name: \"res3b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b2\"\n name: \"res3b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b3_branch2a\"\n name: \"res3b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2a\"\n name: \"scale3b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2a\"\n bottom: \"res3b3_branch2a\"\n name: \"res3b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2b\"\n name: \"res3b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2b\"\n name: \"scale3b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2b\"\n bottom: \"res3b3_branch2b\"\n name: \"res3b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2c\"\n name: \"res3b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2c\"\n top: \"res3b3_branch2c\"\n name: \"scale3b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2\"\n bottom: \"res3b3_branch2c\"\n top: \"res3b3\"\n name: \"res3b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res3b3\"\n name: \"res3b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2a\"\n bottom: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2b\"\n bottom: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b1_branch2a\"\n name: \"res4b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2a\"\n name: \"scale4b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2a\"\n bottom: \"res4b1_branch2a\"\n name: \"res4b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2b\"\n name: \"res4b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2b\"\n name: \"scale4b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2b\"\n bottom: \"res4b1_branch2b\"\n name: \"res4b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2c\"\n name: \"res4b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2c\"\n top: \"res4b1_branch2c\"\n name: \"scale4b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b1_branch2c\"\n top: \"res4b1\"\n name: \"res4b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b1\"\n name: \"res4b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b2_branch2a\"\n name: \"res4b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2a\"\n name: \"scale4b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2a\"\n bottom: \"res4b2_branch2a\"\n name: \"res4b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2b\"\n name: \"res4b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2b\"\n name: \"scale4b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2b\"\n bottom: \"res4b2_branch2b\"\n name: \"res4b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2c\"\n name: \"res4b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2c\"\n top: \"res4b2_branch2c\"\n name: \"scale4b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1\"\n bottom: \"res4b2_branch2c\"\n top: \"res4b2\"\n name: \"res4b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b2\"\n name: \"res4b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b3_branch2a\"\n name: \"res4b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2a\"\n name: \"scale4b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2a\"\n bottom: \"res4b3_branch2a\"\n name: \"res4b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2b\"\n name: \"res4b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2b\"\n name: \"scale4b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2b\"\n bottom: \"res4b3_branch2b\"\n name: \"res4b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2c\"\n name: \"res4b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2c\"\n top: \"res4b3_branch2c\"\n name: \"scale4b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2\"\n bottom: \"res4b3_branch2c\"\n top: \"res4b3\"\n name: \"res4b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b3\"\n name: \"res4b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b4_branch2a\"\n name: \"res4b4_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2a\"\n name: \"scale4b4_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2a\"\n bottom: \"res4b4_branch2a\"\n name: \"res4b4_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2b\"\n name: \"res4b4_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2b\"\n name: \"scale4b4_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2b\"\n bottom: \"res4b4_branch2b\"\n name: \"res4b4_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2c\"\n name: \"res4b4_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2c\"\n top: \"res4b4_branch2c\"\n name: \"scale4b4_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3\"\n bottom: \"res4b4_branch2c\"\n top: \"res4b4\"\n name: \"res4b4\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b4\"\n name: \"res4b4_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b5_branch2a\"\n name: \"res4b5_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2a\"\n name: \"scale4b5_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2a\"\n bottom: \"res4b5_branch2a\"\n name: \"res4b5_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2b\"\n name: \"res4b5_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2b\"\n name: \"scale4b5_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2b\"\n bottom: \"res4b5_branch2b\"\n name: \"res4b5_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2c\"\n name: \"res4b5_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2c\"\n top: \"res4b5_branch2c\"\n name: \"scale4b5_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4\"\n bottom: \"res4b5_branch2c\"\n top: \"res4b5\"\n name: \"res4b5\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b5\"\n name: \"res4b5_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b6_branch2a\"\n name: \"res4b6_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2a\"\n name: \"scale4b6_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2a\"\n bottom: \"res4b6_branch2a\"\n name: \"res4b6_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2b\"\n name: \"res4b6_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2b\"\n name: \"scale4b6_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2b\"\n bottom: \"res4b6_branch2b\"\n name: \"res4b6_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2c\"\n name: \"res4b6_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2c\"\n top: \"res4b6_branch2c\"\n name: \"scale4b6_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5\"\n bottom: \"res4b6_branch2c\"\n top: \"res4b6\"\n name: \"res4b6\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b6\"\n name: \"res4b6_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b7_branch2a\"\n name: \"res4b7_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2a\"\n name: \"scale4b7_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2a\"\n bottom: \"res4b7_branch2a\"\n name: \"res4b7_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2b\"\n name: \"res4b7_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2b\"\n name: \"scale4b7_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2b\"\n bottom: \"res4b7_branch2b\"\n name: \"res4b7_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2c\"\n name: \"res4b7_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2c\"\n top: \"res4b7_branch2c\"\n name: \"scale4b7_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6\"\n bottom: \"res4b7_branch2c\"\n top: \"res4b7\"\n name: \"res4b7\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b7\"\n name: \"res4b7_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b8_branch2a\"\n name: \"res4b8_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2a\"\n name: \"scale4b8_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2a\"\n bottom: \"res4b8_branch2a\"\n name: \"res4b8_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2b\"\n name: \"res4b8_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2b\"\n name: \"scale4b8_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2b\"\n bottom: \"res4b8_branch2b\"\n name: \"res4b8_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2c\"\n name: \"res4b8_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2c\"\n top: \"res4b8_branch2c\"\n name: \"scale4b8_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7\"\n bottom: \"res4b8_branch2c\"\n top: \"res4b8\"\n name: \"res4b8\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b8\"\n name: \"res4b8_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b9_branch2a\"\n name: \"res4b9_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2a\"\n name: \"scale4b9_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2a\"\n bottom: \"res4b9_branch2a\"\n name: \"res4b9_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2b\"\n name: \"res4b9_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2b\"\n name: \"scale4b9_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2b\"\n bottom: \"res4b9_branch2b\"\n name: \"res4b9_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2c\"\n name: \"res4b9_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2c\"\n top: \"res4b9_branch2c\"\n name: \"scale4b9_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8\"\n bottom: \"res4b9_branch2c\"\n top: \"res4b9\"\n name: \"res4b9\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b9\"\n name: \"res4b9_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b10_branch2a\"\n name: \"res4b10_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2a\"\n name: \"scale4b10_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2a\"\n bottom: \"res4b10_branch2a\"\n name: \"res4b10_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2b\"\n name: \"res4b10_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2b\"\n name: \"scale4b10_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2b\"\n bottom: \"res4b10_branch2b\"\n name: \"res4b10_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2c\"\n name: \"res4b10_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res4b10_branch2c\"\n top: \"res4b10_branch2c\"\n name: \"scale4b10_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9\"\n bottom: \"res4b10_branch2c\"\n top: \"res4b10\"\n name: \"res4b10\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b10\"\n name: \"res4b10_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b11_branch2a\"\n name: \"res4b11_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2a\"\n name: \"scale4b11_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2a\"\n bottom: \"res4b11_branch2a\"\n name: \"res4b11_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2b\"\n name: \"res4b11_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2b\"\n name: \"scale4b11_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2b\"\n bottom: \"res4b11_branch2b\"\n name: \"res4b11_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2c\"\n name: \"res4b11_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2c\"\n top: \"res4b11_branch2c\"\n name: \"scale4b11_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10\"\n bottom: \"res4b11_branch2c\"\n top: \"res4b11\"\n name: \"res4b11\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b11\"\n name: \"res4b11_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b12_branch2a\"\n name: \"res4b12_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2a\"\n name: \"scale4b12_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2a\"\n bottom: \"res4b12_branch2a\"\n name: \"res4b12_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2b\"\n name: \"res4b12_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2b\"\n name: \"scale4b12_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2b\"\n bottom: \"res4b12_branch2b\"\n name: \"res4b12_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2c\"\n name: \"res4b12_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2c\"\n top: \"res4b12_branch2c\"\n name: \"scale4b12_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11\"\n bottom: \"res4b12_branch2c\"\n top: \"res4b12\"\n name: \"res4b12\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b12\"\n name: \"res4b12_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b13_branch2a\"\n name: \"res4b13_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2a\"\n name: \"scale4b13_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2a\"\n bottom: \"res4b13_branch2a\"\n name: \"res4b13_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2b\"\n name: \"res4b13_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2b\"\n name: \"scale4b13_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2b\"\n bottom: \"res4b13_branch2b\"\n name: \"res4b13_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2c\"\n name: \"res4b13_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2c\"\n top: \"res4b13_branch2c\"\n name: \"scale4b13_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12\"\n bottom: \"res4b13_branch2c\"\n top: \"res4b13\"\n name: \"res4b13\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b13\"\n name: \"res4b13_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b14_branch2a\"\n name: \"res4b14_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2a\"\n name: \"scale4b14_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2a\"\n bottom: \"res4b14_branch2a\"\n name: \"res4b14_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2b\"\n name: \"res4b14_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2b\"\n name: \"scale4b14_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2b\"\n bottom: \"res4b14_branch2b\"\n name: \"res4b14_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2c\"\n name: \"res4b14_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2c\"\n top: \"res4b14_branch2c\"\n name: \"scale4b14_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13\"\n bottom: \"res4b14_branch2c\"\n top: \"res4b14\"\n name: \"res4b14\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b14\"\n name: \"res4b14_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b15_branch2a\"\n name: \"res4b15_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2a\"\n name: \"scale4b15_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2a\"\n bottom: \"res4b15_branch2a\"\n name: \"res4b15_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2b\"\n name: \"res4b15_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2b\"\n name: \"scale4b15_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2b\"\n bottom: \"res4b15_branch2b\"\n name: \"res4b15_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2c\"\n name: \"res4b15_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2c\"\n top: \"res4b15_branch2c\"\n name: \"scale4b15_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14\"\n bottom: \"res4b15_branch2c\"\n top: \"res4b15\"\n name: \"res4b15\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b15\"\n name: \"res4b15_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b16_branch2a\"\n name: \"res4b16_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2a\"\n name: \"scale4b16_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2a\"\n bottom: \"res4b16_branch2a\"\n name: \"res4b16_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2b\"\n name: \"res4b16_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2b\"\n name: \"scale4b16_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2b\"\n bottom: \"res4b16_branch2b\"\n name: \"res4b16_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2c\"\n name: \"res4b16_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2c\"\n top: \"res4b16_branch2c\"\n name: \"scale4b16_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15\"\n bottom: \"res4b16_branch2c\"\n top: \"res4b16\"\n name: \"res4b16\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b16\"\n name: \"res4b16_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b17_branch2a\"\n name: \"res4b17_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2a\"\n name: \"scale4b17_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2a\"\n bottom: \"res4b17_branch2a\"\n name: \"res4b17_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2b\"\n name: \"res4b17_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2b\"\n name: \"scale4b17_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2b\"\n bottom: \"res4b17_branch2b\"\n name: \"res4b17_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2c\"\n name: \"res4b17_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2c\"\n top: \"res4b17_branch2c\"\n name: \"scale4b17_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16\"\n bottom: \"res4b17_branch2c\"\n top: \"res4b17\"\n name: \"res4b17\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b17\"\n name: \"res4b17_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b18_branch2a\"\n name: \"res4b18_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2a\"\n name: \"scale4b18_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2a\"\n bottom: \"res4b18_branch2a\"\n name: \"res4b18_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2b\"\n name: \"res4b18_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2b\"\n name: \"scale4b18_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2b\"\n bottom: \"res4b18_branch2b\"\n name: \"res4b18_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2c\"\n name: \"res4b18_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res4b18_branch2c\"\n top: \"res4b18_branch2c\"\n name: \"scale4b18_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17\"\n bottom: \"res4b18_branch2c\"\n top: \"res4b18\"\n name: \"res4b18\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b18\"\n name: \"res4b18_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b19_branch2a\"\n name: \"res4b19_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2a\"\n name: \"scale4b19_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2a\"\n bottom: \"res4b19_branch2a\"\n name: \"res4b19_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2b\"\n name: \"res4b19_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2b\"\n name: \"scale4b19_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2b\"\n bottom: \"res4b19_branch2b\"\n name: \"res4b19_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2c\"\n name: \"res4b19_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res4b19_branch2c\"\n top: \"res4b19_branch2c\"\n name: \"scale4b19_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18\"\n bottom: \"res4b19_branch2c\"\n top: \"res4b19\"\n name: \"res4b19\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b19\"\n name: \"res4b19_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b20_branch2a\"\n name: \"res4b20_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2a\"\n name: \"scale4b20_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2a\"\n bottom: \"res4b20_branch2a\"\n name: \"res4b20_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2b\"\n name: \"res4b20_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2b\"\n name: \"scale4b20_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2b\"\n bottom: \"res4b20_branch2b\"\n name: \"res4b20_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2c\"\n name: \"res4b20_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2c\"\n top: \"res4b20_branch2c\"\n name: \"scale4b20_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19\"\n bottom: \"res4b20_branch2c\"\n top: \"res4b20\"\n name: \"res4b20\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b20\"\n name: \"res4b20_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b21_branch2a\"\n name: \"res4b21_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2a\"\n name: \"scale4b21_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2a\"\n bottom: \"res4b21_branch2a\"\n name: \"res4b21_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2b\"\n name: \"res4b21_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2b\"\n name: \"scale4b21_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2b\"\n bottom: \"res4b21_branch2b\"\n name: \"res4b21_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2c\"\n name: \"res4b21_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2c\"\n top: \"res4b21_branch2c\"\n name: \"scale4b21_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20\"\n bottom: \"res4b21_branch2c\"\n top: \"res4b21\"\n name: \"res4b21\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b21\"\n name: \"res4b21_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b22_branch2a\"\n name: \"res4b22_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2a\"\n name: \"scale4b22_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2a\"\n bottom: \"res4b22_branch2a\"\n name: \"res4b22_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2b\"\n name: \"res4b22_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2b\"\n name: \"scale4b22_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2b\"\n bottom: \"res4b22_branch2b\"\n name: \"res4b22_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2c\"\n name: \"res4b22_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res4b22_branch2c\"\n top: \"res4b22_branch2c\"\n name: \"scale4b22_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21\"\n bottom: \"res4b22_branch2c\"\n top: \"res4b22\"\n name: \"res4b22\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b22\"\n top: \"res4b22\"\n name: \"res4b22_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"res4b22\"\n bottom: \"rois\"\n top: \"roi_pool5\"\n roi_pooling_param {\n pooled_w: 14\n pooled_h: 14\n spatial_scale: 0.0625 # 1/16\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\n\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"loss_bbox\"\n loss_weight: 1\n}\n\n\n#========= RPN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4b22\"\n top: \"rpn/output\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"silence_rpn_cls_score\"\n type: \"Silence\"\n bottom: \"rpn_cls_score\"\n}\nlayer {\n name: \"silence_rpn_bbox_pred\"\n type: \"Silence\"\n bottom: \"rpn_bbox_pred\"\n}\n" }, { "path": "models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_alt_opt/stage2_rpn_solver60k80k.pt", "content": "train_net: \"models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_alt_opt/stage2_rpn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 60000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet101_bn_scale_merged_rpn\"\n" }, { "path": "models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_alt_opt/stage2_rpn_train.pt", "content": "name: \"ResNet101_BN_SCALE_Merged\"\n\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"conv1\"\n bottom: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2a\"\n bottom: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2b\"\n bottom: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2a\"\n bottom: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2b\"\n bottom: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2a\"\n bottom: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2b\"\n bottom: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2a\"\n bottom: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2b\"\n bottom: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b1_branch2a\"\n name: \"res3b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2a\"\n name: \"scale3b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2a\"\n bottom: \"res3b1_branch2a\"\n name: \"res3b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2b\"\n name: \"res3b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2b\"\n name: \"scale3b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2b\"\n bottom: \"res3b1_branch2b\"\n name: \"res3b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2c\"\n name: \"res3b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2c\"\n top: \"res3b1_branch2c\"\n name: \"scale3b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b1_branch2c\"\n top: \"res3b1\"\n name: \"res3b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b1\"\n name: \"res3b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b2_branch2a\"\n name: \"res3b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2a\"\n name: \"scale3b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2a\"\n bottom: \"res3b2_branch2a\"\n name: \"res3b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2b\"\n name: \"res3b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2b\"\n name: \"scale3b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2b\"\n bottom: \"res3b2_branch2b\"\n name: \"res3b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2c\"\n name: \"res3b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2c\"\n top: \"res3b2_branch2c\"\n name: \"scale3b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1\"\n bottom: \"res3b2_branch2c\"\n top: \"res3b2\"\n name: \"res3b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b2\"\n name: \"res3b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b3_branch2a\"\n name: \"res3b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2a\"\n name: \"scale3b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2a\"\n bottom: \"res3b3_branch2a\"\n name: \"res3b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2b\"\n name: \"res3b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2b\"\n name: \"scale3b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2b\"\n bottom: \"res3b3_branch2b\"\n name: \"res3b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2c\"\n name: \"res3b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2c\"\n top: \"res3b3_branch2c\"\n name: \"scale3b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2\"\n bottom: \"res3b3_branch2c\"\n top: \"res3b3\"\n name: \"res3b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res3b3\"\n name: \"res3b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2a\"\n bottom: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2b\"\n bottom: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b1_branch2a\"\n name: \"res4b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2a\"\n name: \"scale4b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2a\"\n bottom: \"res4b1_branch2a\"\n name: \"res4b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2b\"\n name: \"res4b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2b\"\n name: \"scale4b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2b\"\n bottom: \"res4b1_branch2b\"\n name: \"res4b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2c\"\n name: \"res4b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2c\"\n top: \"res4b1_branch2c\"\n name: \"scale4b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b1_branch2c\"\n top: \"res4b1\"\n name: \"res4b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b1\"\n name: \"res4b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b2_branch2a\"\n name: \"res4b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2a\"\n name: \"scale4b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2a\"\n bottom: \"res4b2_branch2a\"\n name: \"res4b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2b\"\n name: \"res4b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2b\"\n name: \"scale4b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2b\"\n bottom: \"res4b2_branch2b\"\n name: \"res4b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2c\"\n name: \"res4b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2c\"\n top: \"res4b2_branch2c\"\n name: \"scale4b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1\"\n bottom: \"res4b2_branch2c\"\n top: \"res4b2\"\n name: \"res4b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b2\"\n name: \"res4b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b3_branch2a\"\n name: \"res4b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2a\"\n name: \"scale4b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2a\"\n bottom: \"res4b3_branch2a\"\n name: \"res4b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2b\"\n name: \"res4b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2b\"\n name: \"scale4b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2b\"\n bottom: \"res4b3_branch2b\"\n name: \"res4b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2c\"\n name: \"res4b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2c\"\n top: \"res4b3_branch2c\"\n name: \"scale4b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2\"\n bottom: \"res4b3_branch2c\"\n top: \"res4b3\"\n name: \"res4b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b3\"\n name: \"res4b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b4_branch2a\"\n name: \"res4b4_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2a\"\n name: \"scale4b4_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2a\"\n bottom: \"res4b4_branch2a\"\n name: \"res4b4_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2b\"\n name: \"res4b4_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2b\"\n name: \"scale4b4_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2b\"\n bottom: \"res4b4_branch2b\"\n name: \"res4b4_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2c\"\n name: \"res4b4_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2c\"\n top: \"res4b4_branch2c\"\n name: \"scale4b4_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3\"\n bottom: \"res4b4_branch2c\"\n top: \"res4b4\"\n name: \"res4b4\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b4\"\n name: \"res4b4_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b5_branch2a\"\n name: \"res4b5_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2a\"\n name: \"scale4b5_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2a\"\n bottom: \"res4b5_branch2a\"\n name: \"res4b5_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2b\"\n name: \"res4b5_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2b\"\n name: \"scale4b5_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2b\"\n bottom: \"res4b5_branch2b\"\n name: \"res4b5_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2c\"\n name: \"res4b5_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2c\"\n top: \"res4b5_branch2c\"\n name: \"scale4b5_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4\"\n bottom: \"res4b5_branch2c\"\n top: \"res4b5\"\n name: \"res4b5\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b5\"\n name: \"res4b5_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b6_branch2a\"\n name: \"res4b6_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2a\"\n name: \"scale4b6_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2a\"\n bottom: \"res4b6_branch2a\"\n name: \"res4b6_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2b\"\n name: \"res4b6_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2b\"\n name: \"scale4b6_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2b\"\n bottom: \"res4b6_branch2b\"\n name: \"res4b6_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2c\"\n name: \"res4b6_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2c\"\n top: \"res4b6_branch2c\"\n name: \"scale4b6_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5\"\n bottom: \"res4b6_branch2c\"\n top: \"res4b6\"\n name: \"res4b6\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b6\"\n name: \"res4b6_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b7_branch2a\"\n name: \"res4b7_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2a\"\n name: \"scale4b7_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2a\"\n bottom: \"res4b7_branch2a\"\n name: \"res4b7_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2b\"\n name: \"res4b7_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2b\"\n name: \"scale4b7_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2b\"\n bottom: \"res4b7_branch2b\"\n name: \"res4b7_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2c\"\n name: \"res4b7_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2c\"\n top: \"res4b7_branch2c\"\n name: \"scale4b7_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6\"\n bottom: \"res4b7_branch2c\"\n top: \"res4b7\"\n name: \"res4b7\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b7\"\n name: \"res4b7_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b8_branch2a\"\n name: \"res4b8_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2a\"\n name: \"scale4b8_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2a\"\n bottom: \"res4b8_branch2a\"\n name: \"res4b8_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2b\"\n name: \"res4b8_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2b\"\n name: \"scale4b8_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2b\"\n bottom: \"res4b8_branch2b\"\n name: \"res4b8_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2c\"\n name: \"res4b8_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2c\"\n top: \"res4b8_branch2c\"\n name: \"scale4b8_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7\"\n bottom: \"res4b8_branch2c\"\n top: \"res4b8\"\n name: \"res4b8\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b8\"\n name: \"res4b8_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b9_branch2a\"\n name: \"res4b9_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2a\"\n name: \"scale4b9_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2a\"\n bottom: \"res4b9_branch2a\"\n name: \"res4b9_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2b\"\n name: \"res4b9_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2b\"\n name: \"scale4b9_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2b\"\n bottom: \"res4b9_branch2b\"\n name: \"res4b9_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2c\"\n name: \"res4b9_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2c\"\n top: \"res4b9_branch2c\"\n name: \"scale4b9_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8\"\n bottom: \"res4b9_branch2c\"\n top: \"res4b9\"\n name: \"res4b9\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b9\"\n name: \"res4b9_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b10_branch2a\"\n name: \"res4b10_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2a\"\n name: \"scale4b10_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2a\"\n bottom: \"res4b10_branch2a\"\n name: \"res4b10_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2b\"\n name: \"res4b10_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2b\"\n name: \"scale4b10_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2b\"\n bottom: \"res4b10_branch2b\"\n name: \"res4b10_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2c\"\n name: \"res4b10_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res4b10_branch2c\"\n top: \"res4b10_branch2c\"\n name: \"scale4b10_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9\"\n bottom: \"res4b10_branch2c\"\n top: \"res4b10\"\n name: \"res4b10\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b10\"\n name: \"res4b10_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b11_branch2a\"\n name: \"res4b11_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2a\"\n name: \"scale4b11_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2a\"\n bottom: \"res4b11_branch2a\"\n name: \"res4b11_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2b\"\n name: \"res4b11_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2b\"\n name: \"scale4b11_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2b\"\n bottom: \"res4b11_branch2b\"\n name: \"res4b11_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2c\"\n name: \"res4b11_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2c\"\n top: \"res4b11_branch2c\"\n name: \"scale4b11_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10\"\n bottom: \"res4b11_branch2c\"\n top: \"res4b11\"\n name: \"res4b11\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b11\"\n name: \"res4b11_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b12_branch2a\"\n name: \"res4b12_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2a\"\n name: \"scale4b12_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2a\"\n bottom: \"res4b12_branch2a\"\n name: \"res4b12_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2b\"\n name: \"res4b12_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2b\"\n name: \"scale4b12_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2b\"\n bottom: \"res4b12_branch2b\"\n name: \"res4b12_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2c\"\n name: \"res4b12_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2c\"\n top: \"res4b12_branch2c\"\n name: \"scale4b12_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11\"\n bottom: \"res4b12_branch2c\"\n top: \"res4b12\"\n name: \"res4b12\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b12\"\n name: \"res4b12_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b13_branch2a\"\n name: \"res4b13_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2a\"\n name: \"scale4b13_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2a\"\n bottom: \"res4b13_branch2a\"\n name: \"res4b13_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2b\"\n name: \"res4b13_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2b\"\n name: \"scale4b13_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2b\"\n bottom: \"res4b13_branch2b\"\n name: \"res4b13_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2c\"\n name: \"res4b13_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2c\"\n top: \"res4b13_branch2c\"\n name: \"scale4b13_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12\"\n bottom: \"res4b13_branch2c\"\n top: \"res4b13\"\n name: \"res4b13\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b13\"\n name: \"res4b13_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b14_branch2a\"\n name: \"res4b14_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2a\"\n name: \"scale4b14_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2a\"\n bottom: \"res4b14_branch2a\"\n name: \"res4b14_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2b\"\n name: \"res4b14_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2b\"\n name: \"scale4b14_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2b\"\n bottom: \"res4b14_branch2b\"\n name: \"res4b14_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2c\"\n name: \"res4b14_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2c\"\n top: \"res4b14_branch2c\"\n name: \"scale4b14_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13\"\n bottom: \"res4b14_branch2c\"\n top: \"res4b14\"\n name: \"res4b14\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b14\"\n name: \"res4b14_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b15_branch2a\"\n name: \"res4b15_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2a\"\n name: \"scale4b15_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2a\"\n bottom: \"res4b15_branch2a\"\n name: \"res4b15_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2b\"\n name: \"res4b15_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2b\"\n name: \"scale4b15_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2b\"\n bottom: \"res4b15_branch2b\"\n name: \"res4b15_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2c\"\n name: \"res4b15_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2c\"\n top: \"res4b15_branch2c\"\n name: \"scale4b15_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14\"\n bottom: \"res4b15_branch2c\"\n top: \"res4b15\"\n name: \"res4b15\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b15\"\n name: \"res4b15_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b16_branch2a\"\n name: \"res4b16_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2a\"\n name: \"scale4b16_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2a\"\n bottom: \"res4b16_branch2a\"\n name: \"res4b16_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2b\"\n name: \"res4b16_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2b\"\n name: \"scale4b16_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2b\"\n bottom: \"res4b16_branch2b\"\n name: \"res4b16_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2c\"\n name: \"res4b16_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2c\"\n top: \"res4b16_branch2c\"\n name: \"scale4b16_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15\"\n bottom: \"res4b16_branch2c\"\n top: \"res4b16\"\n name: \"res4b16\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b16\"\n name: \"res4b16_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b17_branch2a\"\n name: \"res4b17_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2a\"\n name: \"scale4b17_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2a\"\n bottom: \"res4b17_branch2a\"\n name: \"res4b17_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2b\"\n name: \"res4b17_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2b\"\n name: \"scale4b17_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2b\"\n bottom: \"res4b17_branch2b\"\n name: \"res4b17_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2c\"\n name: \"res4b17_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2c\"\n top: \"res4b17_branch2c\"\n name: \"scale4b17_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16\"\n bottom: \"res4b17_branch2c\"\n top: \"res4b17\"\n name: \"res4b17\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b17\"\n name: \"res4b17_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b18_branch2a\"\n name: \"res4b18_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2a\"\n name: \"scale4b18_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2a\"\n bottom: \"res4b18_branch2a\"\n name: \"res4b18_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2b\"\n name: \"res4b18_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2b\"\n name: \"scale4b18_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2b\"\n bottom: \"res4b18_branch2b\"\n name: \"res4b18_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2c\"\n name: \"res4b18_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res4b18_branch2c\"\n top: \"res4b18_branch2c\"\n name: \"scale4b18_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17\"\n bottom: \"res4b18_branch2c\"\n top: \"res4b18\"\n name: \"res4b18\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b18\"\n name: \"res4b18_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b19_branch2a\"\n name: \"res4b19_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2a\"\n name: \"scale4b19_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2a\"\n bottom: \"res4b19_branch2a\"\n name: \"res4b19_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2b\"\n name: \"res4b19_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2b\"\n name: \"scale4b19_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2b\"\n bottom: \"res4b19_branch2b\"\n name: \"res4b19_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2c\"\n name: \"res4b19_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res4b19_branch2c\"\n top: \"res4b19_branch2c\"\n name: \"scale4b19_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18\"\n bottom: \"res4b19_branch2c\"\n top: \"res4b19\"\n name: \"res4b19\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b19\"\n name: \"res4b19_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b20_branch2a\"\n name: \"res4b20_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2a\"\n name: \"scale4b20_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2a\"\n bottom: \"res4b20_branch2a\"\n name: \"res4b20_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2b\"\n name: \"res4b20_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2b\"\n name: \"scale4b20_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2b\"\n bottom: \"res4b20_branch2b\"\n name: \"res4b20_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2c\"\n name: \"res4b20_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2c\"\n top: \"res4b20_branch2c\"\n name: \"scale4b20_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19\"\n bottom: \"res4b20_branch2c\"\n top: \"res4b20\"\n name: \"res4b20\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b20\"\n name: \"res4b20_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b21_branch2a\"\n name: \"res4b21_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2a\"\n name: \"scale4b21_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2a\"\n bottom: \"res4b21_branch2a\"\n name: \"res4b21_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2b\"\n name: \"res4b21_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2b\"\n name: \"scale4b21_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2b\"\n bottom: \"res4b21_branch2b\"\n name: \"res4b21_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2c\"\n name: \"res4b21_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2c\"\n top: \"res4b21_branch2c\"\n name: \"scale4b21_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20\"\n bottom: \"res4b21_branch2c\"\n top: \"res4b21\"\n name: \"res4b21\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b21\"\n name: \"res4b21_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b22_branch2a\"\n name: \"res4b22_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2a\"\n name: \"scale4b22_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2a\"\n bottom: \"res4b22_branch2a\"\n name: \"res4b22_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2b\"\n name: \"res4b22_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2b\"\n name: \"scale4b22_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2b\"\n bottom: \"res4b22_branch2b\"\n name: \"res4b22_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2c\"\n name: \"res4b22_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res4b22_branch2c\"\n top: \"res4b22_branch2c\"\n name: \"scale4b22_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21\"\n bottom: \"res4b22_branch2c\"\n top: \"res4b22\"\n name: \"res4b22\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b22\"\n top: \"res4b22\"\n name: \"res4b22_relu\"\n type: \"ReLU\"\n}\n\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4b22\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RCNN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"dummy_roi_pool_res4b22\"\n type: \"DummyData\"\n top: \"dummy_roi_pool_res4b22\"\n dummy_data_param {\n shape { dim: 1 dim: 1024 dim: 14 dim: 14 }\n data_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"dummy_roi_pool_res4b22\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"dummy_roi_pool_res4b22\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\nlayer {\n name: \"silence_pool5\"\n type: \"Silence\"\n bottom: \"pool5\"\n}\n" }, { "path": "models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_end2end/solver.prototxt", "content": "train_net: \"models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_end2end/train.prototxt\"\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 50000\ndisplay: 20\naverage_loss: 100\n# iter_size: 1\nmomentum: 0.9\nweight_decay: 0.0005\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet101_faster_rcnn_bn_scale_merged_end2end\"\niter_size: 2\n" }, { "path": "models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_end2end/test.prototxt", "content": "name: \"ResNet101_BN_SCALE_Merged\"\n\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\n\ninput: \"im_info\"\ninput_shape {\n dim: 1\n dim: 3\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"conv1\"\n bottom: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2a\"\n bottom: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2b\"\n bottom: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2a\"\n bottom: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2b\"\n bottom: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2a\"\n bottom: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2b\"\n bottom: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2a\"\n bottom: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2b\"\n bottom: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b1_branch2a\"\n name: \"res3b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2a\"\n name: \"scale3b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2a\"\n bottom: \"res3b1_branch2a\"\n name: \"res3b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2b\"\n name: \"res3b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2b\"\n name: \"scale3b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2b\"\n bottom: \"res3b1_branch2b\"\n name: \"res3b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2c\"\n name: \"res3b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2c\"\n top: \"res3b1_branch2c\"\n name: \"scale3b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b1_branch2c\"\n top: \"res3b1\"\n name: \"res3b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b1\"\n name: \"res3b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b2_branch2a\"\n name: \"res3b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2a\"\n name: \"scale3b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2a\"\n bottom: \"res3b2_branch2a\"\n name: \"res3b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2b\"\n name: \"res3b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2b\"\n name: \"scale3b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2b\"\n bottom: \"res3b2_branch2b\"\n name: \"res3b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2c\"\n name: \"res3b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2c\"\n top: \"res3b2_branch2c\"\n name: \"scale3b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1\"\n bottom: \"res3b2_branch2c\"\n top: \"res3b2\"\n name: \"res3b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b2\"\n name: \"res3b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b3_branch2a\"\n name: \"res3b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2a\"\n name: \"scale3b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2a\"\n bottom: \"res3b3_branch2a\"\n name: \"res3b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2b\"\n name: \"res3b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2b\"\n name: \"scale3b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2b\"\n bottom: \"res3b3_branch2b\"\n name: \"res3b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2c\"\n name: \"res3b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2c\"\n top: \"res3b3_branch2c\"\n name: \"scale3b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2\"\n bottom: \"res3b3_branch2c\"\n top: \"res3b3\"\n name: \"res3b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res3b3\"\n name: \"res3b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2a\"\n bottom: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2b\"\n bottom: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b1_branch2a\"\n name: \"res4b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2a\"\n name: \"scale4b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2a\"\n bottom: \"res4b1_branch2a\"\n name: \"res4b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2b\"\n name: \"res4b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2b\"\n name: \"scale4b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2b\"\n bottom: \"res4b1_branch2b\"\n name: \"res4b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2c\"\n name: \"res4b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2c\"\n top: \"res4b1_branch2c\"\n name: \"scale4b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b1_branch2c\"\n top: \"res4b1\"\n name: \"res4b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b1\"\n name: \"res4b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b2_branch2a\"\n name: \"res4b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2a\"\n name: \"scale4b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2a\"\n bottom: \"res4b2_branch2a\"\n name: \"res4b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2b\"\n name: \"res4b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2b\"\n name: \"scale4b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2b\"\n bottom: \"res4b2_branch2b\"\n name: \"res4b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2c\"\n name: \"res4b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2c\"\n top: \"res4b2_branch2c\"\n name: \"scale4b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1\"\n bottom: \"res4b2_branch2c\"\n top: \"res4b2\"\n name: \"res4b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b2\"\n name: \"res4b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b3_branch2a\"\n name: \"res4b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2a\"\n name: \"scale4b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2a\"\n bottom: \"res4b3_branch2a\"\n name: \"res4b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2b\"\n name: \"res4b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2b\"\n name: \"scale4b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2b\"\n bottom: \"res4b3_branch2b\"\n name: \"res4b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2c\"\n name: \"res4b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2c\"\n top: \"res4b3_branch2c\"\n name: \"scale4b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2\"\n bottom: \"res4b3_branch2c\"\n top: \"res4b3\"\n name: \"res4b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b3\"\n name: \"res4b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b4_branch2a\"\n name: \"res4b4_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2a\"\n name: \"scale4b4_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2a\"\n bottom: \"res4b4_branch2a\"\n name: \"res4b4_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2b\"\n name: \"res4b4_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2b\"\n name: \"scale4b4_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2b\"\n bottom: \"res4b4_branch2b\"\n name: \"res4b4_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2c\"\n name: \"res4b4_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2c\"\n top: \"res4b4_branch2c\"\n name: \"scale4b4_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3\"\n bottom: \"res4b4_branch2c\"\n top: \"res4b4\"\n name: \"res4b4\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b4\"\n name: \"res4b4_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b5_branch2a\"\n name: \"res4b5_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2a\"\n name: \"scale4b5_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2a\"\n bottom: \"res4b5_branch2a\"\n name: \"res4b5_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2b\"\n name: \"res4b5_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2b\"\n name: \"scale4b5_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2b\"\n bottom: \"res4b5_branch2b\"\n name: \"res4b5_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2c\"\n name: \"res4b5_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2c\"\n top: \"res4b5_branch2c\"\n name: \"scale4b5_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4\"\n bottom: \"res4b5_branch2c\"\n top: \"res4b5\"\n name: \"res4b5\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b5\"\n name: \"res4b5_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b6_branch2a\"\n name: \"res4b6_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2a\"\n name: \"scale4b6_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2a\"\n bottom: \"res4b6_branch2a\"\n name: \"res4b6_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2b\"\n name: \"res4b6_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2b\"\n name: \"scale4b6_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2b\"\n bottom: \"res4b6_branch2b\"\n name: \"res4b6_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2c\"\n name: \"res4b6_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2c\"\n top: \"res4b6_branch2c\"\n name: \"scale4b6_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5\"\n bottom: \"res4b6_branch2c\"\n top: \"res4b6\"\n name: \"res4b6\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b6\"\n name: \"res4b6_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b7_branch2a\"\n name: \"res4b7_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2a\"\n name: \"scale4b7_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2a\"\n bottom: \"res4b7_branch2a\"\n name: \"res4b7_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2b\"\n name: \"res4b7_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2b\"\n name: \"scale4b7_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2b\"\n bottom: \"res4b7_branch2b\"\n name: \"res4b7_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2c\"\n name: \"res4b7_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2c\"\n top: \"res4b7_branch2c\"\n name: \"scale4b7_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6\"\n bottom: \"res4b7_branch2c\"\n top: \"res4b7\"\n name: \"res4b7\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b7\"\n name: \"res4b7_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b8_branch2a\"\n name: \"res4b8_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2a\"\n name: \"scale4b8_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2a\"\n bottom: \"res4b8_branch2a\"\n name: \"res4b8_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2b\"\n name: \"res4b8_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2b\"\n name: \"scale4b8_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2b\"\n bottom: \"res4b8_branch2b\"\n name: \"res4b8_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2c\"\n name: \"res4b8_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2c\"\n top: \"res4b8_branch2c\"\n name: \"scale4b8_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7\"\n bottom: \"res4b8_branch2c\"\n top: \"res4b8\"\n name: \"res4b8\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b8\"\n name: \"res4b8_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b9_branch2a\"\n name: \"res4b9_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2a\"\n name: \"scale4b9_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2a\"\n bottom: \"res4b9_branch2a\"\n name: \"res4b9_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2b\"\n name: \"res4b9_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2b\"\n name: \"scale4b9_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2b\"\n bottom: \"res4b9_branch2b\"\n name: \"res4b9_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2c\"\n name: \"res4b9_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2c\"\n top: \"res4b9_branch2c\"\n name: \"scale4b9_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8\"\n bottom: \"res4b9_branch2c\"\n top: \"res4b9\"\n name: \"res4b9\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b9\"\n name: \"res4b9_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b10_branch2a\"\n name: \"res4b10_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2a\"\n name: \"scale4b10_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2a\"\n bottom: \"res4b10_branch2a\"\n name: \"res4b10_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2b\"\n name: \"res4b10_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2b\"\n name: \"scale4b10_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2b\"\n bottom: \"res4b10_branch2b\"\n name: \"res4b10_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2c\"\n name: \"res4b10_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b10_branch2c\"\n top: \"res4b10_branch2c\"\n name: \"scale4b10_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9\"\n bottom: \"res4b10_branch2c\"\n top: \"res4b10\"\n name: \"res4b10\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b10\"\n name: \"res4b10_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b11_branch2a\"\n name: \"res4b11_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2a\"\n name: \"scale4b11_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2a\"\n bottom: \"res4b11_branch2a\"\n name: \"res4b11_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2b\"\n name: \"res4b11_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2b\"\n name: \"scale4b11_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2b\"\n bottom: \"res4b11_branch2b\"\n name: \"res4b11_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2c\"\n name: \"res4b11_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2c\"\n top: \"res4b11_branch2c\"\n name: \"scale4b11_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10\"\n bottom: \"res4b11_branch2c\"\n top: \"res4b11\"\n name: \"res4b11\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b11\"\n name: \"res4b11_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b12_branch2a\"\n name: \"res4b12_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2a\"\n name: \"scale4b12_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2a\"\n bottom: \"res4b12_branch2a\"\n name: \"res4b12_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2b\"\n name: \"res4b12_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2b\"\n name: \"scale4b12_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2b\"\n bottom: \"res4b12_branch2b\"\n name: \"res4b12_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2c\"\n name: \"res4b12_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2c\"\n top: \"res4b12_branch2c\"\n name: \"scale4b12_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11\"\n bottom: \"res4b12_branch2c\"\n top: \"res4b12\"\n name: \"res4b12\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b12\"\n name: \"res4b12_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b13_branch2a\"\n name: \"res4b13_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2a\"\n name: \"scale4b13_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2a\"\n bottom: \"res4b13_branch2a\"\n name: \"res4b13_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2b\"\n name: \"res4b13_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2b\"\n name: \"scale4b13_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2b\"\n bottom: \"res4b13_branch2b\"\n name: \"res4b13_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2c\"\n name: \"res4b13_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2c\"\n top: \"res4b13_branch2c\"\n name: \"scale4b13_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12\"\n bottom: \"res4b13_branch2c\"\n top: \"res4b13\"\n name: \"res4b13\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b13\"\n name: \"res4b13_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b14_branch2a\"\n name: \"res4b14_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2a\"\n name: \"scale4b14_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2a\"\n bottom: \"res4b14_branch2a\"\n name: \"res4b14_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2b\"\n name: \"res4b14_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2b\"\n name: \"scale4b14_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2b\"\n bottom: \"res4b14_branch2b\"\n name: \"res4b14_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2c\"\n name: \"res4b14_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2c\"\n top: \"res4b14_branch2c\"\n name: \"scale4b14_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13\"\n bottom: \"res4b14_branch2c\"\n top: \"res4b14\"\n name: \"res4b14\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b14\"\n name: \"res4b14_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b15_branch2a\"\n name: \"res4b15_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2a\"\n name: \"scale4b15_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2a\"\n bottom: \"res4b15_branch2a\"\n name: \"res4b15_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2b\"\n name: \"res4b15_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2b\"\n name: \"scale4b15_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2b\"\n bottom: \"res4b15_branch2b\"\n name: \"res4b15_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2c\"\n name: \"res4b15_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2c\"\n top: \"res4b15_branch2c\"\n name: \"scale4b15_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14\"\n bottom: \"res4b15_branch2c\"\n top: \"res4b15\"\n name: \"res4b15\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b15\"\n name: \"res4b15_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b16_branch2a\"\n name: \"res4b16_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2a\"\n name: \"scale4b16_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2a\"\n bottom: \"res4b16_branch2a\"\n name: \"res4b16_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2b\"\n name: \"res4b16_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2b\"\n name: \"scale4b16_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2b\"\n bottom: \"res4b16_branch2b\"\n name: \"res4b16_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2c\"\n name: \"res4b16_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2c\"\n top: \"res4b16_branch2c\"\n name: \"scale4b16_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15\"\n bottom: \"res4b16_branch2c\"\n top: \"res4b16\"\n name: \"res4b16\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b16\"\n name: \"res4b16_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b17_branch2a\"\n name: \"res4b17_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2a\"\n name: \"scale4b17_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2a\"\n bottom: \"res4b17_branch2a\"\n name: \"res4b17_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2b\"\n name: \"res4b17_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2b\"\n name: \"scale4b17_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2b\"\n bottom: \"res4b17_branch2b\"\n name: \"res4b17_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2c\"\n name: \"res4b17_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2c\"\n top: \"res4b17_branch2c\"\n name: \"scale4b17_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16\"\n bottom: \"res4b17_branch2c\"\n top: \"res4b17\"\n name: \"res4b17\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b17\"\n name: \"res4b17_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b18_branch2a\"\n name: \"res4b18_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2a\"\n name: \"scale4b18_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2a\"\n bottom: \"res4b18_branch2a\"\n name: \"res4b18_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2b\"\n name: \"res4b18_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2b\"\n name: \"scale4b18_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2b\"\n bottom: \"res4b18_branch2b\"\n name: \"res4b18_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2c\"\n name: \"res4b18_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b18_branch2c\"\n top: \"res4b18_branch2c\"\n name: \"scale4b18_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17\"\n bottom: \"res4b18_branch2c\"\n top: \"res4b18\"\n name: \"res4b18\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b18\"\n name: \"res4b18_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b19_branch2a\"\n name: \"res4b19_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2a\"\n name: \"scale4b19_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2a\"\n bottom: \"res4b19_branch2a\"\n name: \"res4b19_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2b\"\n name: \"res4b19_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2b\"\n name: \"scale4b19_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2b\"\n bottom: \"res4b19_branch2b\"\n name: \"res4b19_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2c\"\n name: \"res4b19_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b19_branch2c\"\n top: \"res4b19_branch2c\"\n name: \"scale4b19_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18\"\n bottom: \"res4b19_branch2c\"\n top: \"res4b19\"\n name: \"res4b19\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b19\"\n name: \"res4b19_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b20_branch2a\"\n name: \"res4b20_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2a\"\n name: \"scale4b20_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2a\"\n bottom: \"res4b20_branch2a\"\n name: \"res4b20_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2b\"\n name: \"res4b20_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2b\"\n name: \"scale4b20_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2b\"\n bottom: \"res4b20_branch2b\"\n name: \"res4b20_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2c\"\n name: \"res4b20_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2c\"\n top: \"res4b20_branch2c\"\n name: \"scale4b20_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19\"\n bottom: \"res4b20_branch2c\"\n top: \"res4b20\"\n name: \"res4b20\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b20\"\n name: \"res4b20_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b21_branch2a\"\n name: \"res4b21_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2a\"\n name: \"scale4b21_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2a\"\n bottom: \"res4b21_branch2a\"\n name: \"res4b21_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2b\"\n name: \"res4b21_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2b\"\n name: \"scale4b21_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2b\"\n bottom: \"res4b21_branch2b\"\n name: \"res4b21_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2c\"\n name: \"res4b21_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2c\"\n top: \"res4b21_branch2c\"\n name: \"scale4b21_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20\"\n bottom: \"res4b21_branch2c\"\n top: \"res4b21\"\n name: \"res4b21\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b21\"\n name: \"res4b21_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b22_branch2a\"\n name: \"res4b22_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2a\"\n name: \"scale4b22_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2a\"\n bottom: \"res4b22_branch2a\"\n name: \"res4b22_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2b\"\n name: \"res4b22_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2b\"\n name: \"scale4b22_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2b\"\n bottom: \"res4b22_branch2b\"\n name: \"res4b22_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2c\"\n name: \"res4b22_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b22_branch2c\"\n top: \"res4b22_branch2c\"\n name: \"scale4b22_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21\"\n bottom: \"res4b22_branch2c\"\n top: \"res4b22\"\n name: \"res4b22\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b22\"\n top: \"res4b22\"\n name: \"res4b22_relu\"\n type: \"ReLU\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4b22\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rois'\n top: 'scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n\n#========= RCNN ============\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"res4b22\"\n bottom: \"rois\"\n top: \"roi_pool5\"\n roi_pooling_param {\n pooled_w: 14\n pooled_h: 14\n spatial_scale: 0.0625 # 1/16\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\n\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\n\nlayer {\n name: \"cls_prob\"\n type: \"Softmax\"\n bottom: \"cls_score\"\n top: \"cls_prob\"\n}\n" }, { "path": "models/pascal_voc/ResNet101_BN_SCALE_Merged/faster_rcnn_end2end/train.prototxt", "content": "name: \"ResNet101\"\n\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"conv1\"\n bottom: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2a\"\n bottom: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2b\"\n bottom: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2a\"\n bottom: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2b\"\n bottom: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2a\"\n bottom: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2b\"\n bottom: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2a\"\n bottom: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2b\"\n bottom: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b1_branch2a\"\n name: \"res3b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2a\"\n name: \"scale3b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2a\"\n bottom: \"res3b1_branch2a\"\n name: \"res3b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2b\"\n name: \"res3b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2b\"\n name: \"scale3b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2b\"\n bottom: \"res3b1_branch2b\"\n name: \"res3b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2c\"\n name: \"res3b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2c\"\n top: \"res3b1_branch2c\"\n name: \"scale3b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b1_branch2c\"\n top: \"res3b1\"\n name: \"res3b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b1\"\n name: \"res3b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b2_branch2a\"\n name: \"res3b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2a\"\n name: \"scale3b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2a\"\n bottom: \"res3b2_branch2a\"\n name: \"res3b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2b\"\n name: \"res3b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2b\"\n name: \"scale3b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2b\"\n bottom: \"res3b2_branch2b\"\n name: \"res3b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2c\"\n name: \"res3b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2c\"\n top: \"res3b2_branch2c\"\n name: \"scale3b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1\"\n bottom: \"res3b2_branch2c\"\n top: \"res3b2\"\n name: \"res3b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b2\"\n name: \"res3b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b3_branch2a\"\n name: \"res3b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2a\"\n name: \"scale3b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2a\"\n bottom: \"res3b3_branch2a\"\n name: \"res3b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2b\"\n name: \"res3b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2b\"\n name: \"scale3b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2b\"\n bottom: \"res3b3_branch2b\"\n name: \"res3b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2c\"\n name: \"res3b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2c\"\n top: \"res3b3_branch2c\"\n name: \"scale3b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2\"\n bottom: \"res3b3_branch2c\"\n top: \"res3b3\"\n name: \"res3b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res3b3\"\n name: \"res3b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2a\"\n bottom: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2b\"\n bottom: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b1_branch2a\"\n name: \"res4b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2a\"\n name: \"scale4b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2a\"\n bottom: \"res4b1_branch2a\"\n name: \"res4b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2b\"\n name: \"res4b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2b\"\n name: \"scale4b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2b\"\n bottom: \"res4b1_branch2b\"\n name: \"res4b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2c\"\n name: \"res4b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2c\"\n top: \"res4b1_branch2c\"\n name: \"scale4b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b1_branch2c\"\n top: \"res4b1\"\n name: \"res4b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b1\"\n name: \"res4b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b2_branch2a\"\n name: \"res4b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2a\"\n name: \"scale4b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2a\"\n bottom: \"res4b2_branch2a\"\n name: \"res4b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2b\"\n name: \"res4b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2b\"\n name: \"scale4b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2b\"\n bottom: \"res4b2_branch2b\"\n name: \"res4b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2c\"\n name: \"res4b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2c\"\n top: \"res4b2_branch2c\"\n name: \"scale4b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1\"\n bottom: \"res4b2_branch2c\"\n top: \"res4b2\"\n name: \"res4b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b2\"\n name: \"res4b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b3_branch2a\"\n name: \"res4b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2a\"\n name: \"scale4b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2a\"\n bottom: \"res4b3_branch2a\"\n name: \"res4b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2b\"\n name: \"res4b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2b\"\n name: \"scale4b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2b\"\n bottom: \"res4b3_branch2b\"\n name: \"res4b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2c\"\n name: \"res4b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2c\"\n top: \"res4b3_branch2c\"\n name: \"scale4b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2\"\n bottom: \"res4b3_branch2c\"\n top: \"res4b3\"\n name: \"res4b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b3\"\n name: \"res4b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b4_branch2a\"\n name: \"res4b4_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2a\"\n name: \"scale4b4_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2a\"\n bottom: \"res4b4_branch2a\"\n name: \"res4b4_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2b\"\n name: \"res4b4_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2b\"\n name: \"scale4b4_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2b\"\n bottom: \"res4b4_branch2b\"\n name: \"res4b4_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2c\"\n name: \"res4b4_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2c\"\n top: \"res4b4_branch2c\"\n name: \"scale4b4_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3\"\n bottom: \"res4b4_branch2c\"\n top: \"res4b4\"\n name: \"res4b4\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b4\"\n name: \"res4b4_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b5_branch2a\"\n name: \"res4b5_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2a\"\n name: \"scale4b5_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2a\"\n bottom: \"res4b5_branch2a\"\n name: \"res4b5_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2b\"\n name: \"res4b5_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2b\"\n name: \"scale4b5_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2b\"\n bottom: \"res4b5_branch2b\"\n name: \"res4b5_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2c\"\n name: \"res4b5_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2c\"\n top: \"res4b5_branch2c\"\n name: \"scale4b5_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4\"\n bottom: \"res4b5_branch2c\"\n top: \"res4b5\"\n name: \"res4b5\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b5\"\n name: \"res4b5_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b6_branch2a\"\n name: \"res4b6_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2a\"\n name: \"scale4b6_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2a\"\n bottom: \"res4b6_branch2a\"\n name: \"res4b6_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2b\"\n name: \"res4b6_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2b\"\n name: \"scale4b6_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2b\"\n bottom: \"res4b6_branch2b\"\n name: \"res4b6_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2c\"\n name: \"res4b6_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2c\"\n top: \"res4b6_branch2c\"\n name: \"scale4b6_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5\"\n bottom: \"res4b6_branch2c\"\n top: \"res4b6\"\n name: \"res4b6\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b6\"\n name: \"res4b6_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b7_branch2a\"\n name: \"res4b7_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2a\"\n name: \"scale4b7_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2a\"\n bottom: \"res4b7_branch2a\"\n name: \"res4b7_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2b\"\n name: \"res4b7_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2b\"\n name: \"scale4b7_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2b\"\n bottom: \"res4b7_branch2b\"\n name: \"res4b7_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2c\"\n name: \"res4b7_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2c\"\n top: \"res4b7_branch2c\"\n name: \"scale4b7_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6\"\n bottom: \"res4b7_branch2c\"\n top: \"res4b7\"\n name: \"res4b7\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b7\"\n name: \"res4b7_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b8_branch2a\"\n name: \"res4b8_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2a\"\n name: \"scale4b8_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2a\"\n bottom: \"res4b8_branch2a\"\n name: \"res4b8_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2b\"\n name: \"res4b8_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2b\"\n name: \"scale4b8_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2b\"\n bottom: \"res4b8_branch2b\"\n name: \"res4b8_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2c\"\n name: \"res4b8_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2c\"\n top: \"res4b8_branch2c\"\n name: \"scale4b8_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7\"\n bottom: \"res4b8_branch2c\"\n top: \"res4b8\"\n name: \"res4b8\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b8\"\n name: \"res4b8_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b9_branch2a\"\n name: \"res4b9_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2a\"\n name: \"scale4b9_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2a\"\n bottom: \"res4b9_branch2a\"\n name: \"res4b9_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2b\"\n name: \"res4b9_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2b\"\n name: \"scale4b9_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2b\"\n bottom: \"res4b9_branch2b\"\n name: \"res4b9_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2c\"\n name: \"res4b9_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2c\"\n top: \"res4b9_branch2c\"\n name: \"scale4b9_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8\"\n bottom: \"res4b9_branch2c\"\n top: \"res4b9\"\n name: \"res4b9\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b9\"\n name: \"res4b9_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b10_branch2a\"\n name: \"res4b10_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2a\"\n name: \"scale4b10_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2a\"\n bottom: \"res4b10_branch2a\"\n name: \"res4b10_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2b\"\n name: \"res4b10_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2b\"\n name: \"scale4b10_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2b\"\n bottom: \"res4b10_branch2b\"\n name: \"res4b10_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2c\"\n name: \"res4b10_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b10_branch2c\"\n top: \"res4b10_branch2c\"\n name: \"scale4b10_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9\"\n bottom: \"res4b10_branch2c\"\n top: \"res4b10\"\n name: \"res4b10\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b10\"\n name: \"res4b10_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b11_branch2a\"\n name: \"res4b11_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2a\"\n name: \"scale4b11_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2a\"\n bottom: \"res4b11_branch2a\"\n name: \"res4b11_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2b\"\n name: \"res4b11_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2b\"\n name: \"scale4b11_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2b\"\n bottom: \"res4b11_branch2b\"\n name: \"res4b11_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2c\"\n name: \"res4b11_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2c\"\n top: \"res4b11_branch2c\"\n name: \"scale4b11_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10\"\n bottom: \"res4b11_branch2c\"\n top: \"res4b11\"\n name: \"res4b11\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b11\"\n name: \"res4b11_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b12_branch2a\"\n name: \"res4b12_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2a\"\n name: \"scale4b12_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2a\"\n bottom: \"res4b12_branch2a\"\n name: \"res4b12_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2b\"\n name: \"res4b12_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2b\"\n name: \"scale4b12_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2b\"\n bottom: \"res4b12_branch2b\"\n name: \"res4b12_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2c\"\n name: \"res4b12_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2c\"\n top: \"res4b12_branch2c\"\n name: \"scale4b12_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11\"\n bottom: \"res4b12_branch2c\"\n top: \"res4b12\"\n name: \"res4b12\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b12\"\n name: \"res4b12_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b13_branch2a\"\n name: \"res4b13_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2a\"\n name: \"scale4b13_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2a\"\n bottom: \"res4b13_branch2a\"\n name: \"res4b13_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2b\"\n name: \"res4b13_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2b\"\n name: \"scale4b13_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2b\"\n bottom: \"res4b13_branch2b\"\n name: \"res4b13_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2c\"\n name: \"res4b13_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2c\"\n top: \"res4b13_branch2c\"\n name: \"scale4b13_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12\"\n bottom: \"res4b13_branch2c\"\n top: \"res4b13\"\n name: \"res4b13\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b13\"\n name: \"res4b13_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b14_branch2a\"\n name: \"res4b14_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2a\"\n name: \"scale4b14_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2a\"\n bottom: \"res4b14_branch2a\"\n name: \"res4b14_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2b\"\n name: \"res4b14_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2b\"\n name: \"scale4b14_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2b\"\n bottom: \"res4b14_branch2b\"\n name: \"res4b14_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2c\"\n name: \"res4b14_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2c\"\n top: \"res4b14_branch2c\"\n name: \"scale4b14_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13\"\n bottom: \"res4b14_branch2c\"\n top: \"res4b14\"\n name: \"res4b14\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b14\"\n name: \"res4b14_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b15_branch2a\"\n name: \"res4b15_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2a\"\n name: \"scale4b15_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2a\"\n bottom: \"res4b15_branch2a\"\n name: \"res4b15_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2b\"\n name: \"res4b15_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2b\"\n name: \"scale4b15_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2b\"\n bottom: \"res4b15_branch2b\"\n name: \"res4b15_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2c\"\n name: \"res4b15_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2c\"\n top: \"res4b15_branch2c\"\n name: \"scale4b15_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14\"\n bottom: \"res4b15_branch2c\"\n top: \"res4b15\"\n name: \"res4b15\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b15\"\n name: \"res4b15_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b16_branch2a\"\n name: \"res4b16_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2a\"\n name: \"scale4b16_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2a\"\n bottom: \"res4b16_branch2a\"\n name: \"res4b16_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2b\"\n name: \"res4b16_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2b\"\n name: \"scale4b16_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2b\"\n bottom: \"res4b16_branch2b\"\n name: \"res4b16_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2c\"\n name: \"res4b16_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2c\"\n top: \"res4b16_branch2c\"\n name: \"scale4b16_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15\"\n bottom: \"res4b16_branch2c\"\n top: \"res4b16\"\n name: \"res4b16\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b16\"\n name: \"res4b16_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b17_branch2a\"\n name: \"res4b17_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2a\"\n name: \"scale4b17_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2a\"\n bottom: \"res4b17_branch2a\"\n name: \"res4b17_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2b\"\n name: \"res4b17_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2b\"\n name: \"scale4b17_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2b\"\n bottom: \"res4b17_branch2b\"\n name: \"res4b17_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2c\"\n name: \"res4b17_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2c\"\n top: \"res4b17_branch2c\"\n name: \"scale4b17_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16\"\n bottom: \"res4b17_branch2c\"\n top: \"res4b17\"\n name: \"res4b17\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b17\"\n name: \"res4b17_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b18_branch2a\"\n name: \"res4b18_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2a\"\n name: \"scale4b18_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2a\"\n bottom: \"res4b18_branch2a\"\n name: \"res4b18_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2b\"\n name: \"res4b18_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2b\"\n name: \"scale4b18_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2b\"\n bottom: \"res4b18_branch2b\"\n name: \"res4b18_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2c\"\n name: \"res4b18_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b18_branch2c\"\n top: \"res4b18_branch2c\"\n name: \"scale4b18_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17\"\n bottom: \"res4b18_branch2c\"\n top: \"res4b18\"\n name: \"res4b18\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b18\"\n name: \"res4b18_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b19_branch2a\"\n name: \"res4b19_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2a\"\n name: \"scale4b19_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2a\"\n bottom: \"res4b19_branch2a\"\n name: \"res4b19_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2b\"\n name: \"res4b19_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2b\"\n name: \"scale4b19_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2b\"\n bottom: \"res4b19_branch2b\"\n name: \"res4b19_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2c\"\n name: \"res4b19_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b19_branch2c\"\n top: \"res4b19_branch2c\"\n name: \"scale4b19_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18\"\n bottom: \"res4b19_branch2c\"\n top: \"res4b19\"\n name: \"res4b19\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b19\"\n name: \"res4b19_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b20_branch2a\"\n name: \"res4b20_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2a\"\n name: \"scale4b20_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2a\"\n bottom: \"res4b20_branch2a\"\n name: \"res4b20_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2b\"\n name: \"res4b20_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2b\"\n name: \"scale4b20_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2b\"\n bottom: \"res4b20_branch2b\"\n name: \"res4b20_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2c\"\n name: \"res4b20_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2c\"\n top: \"res4b20_branch2c\"\n name: \"scale4b20_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19\"\n bottom: \"res4b20_branch2c\"\n top: \"res4b20\"\n name: \"res4b20\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b20\"\n name: \"res4b20_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b21_branch2a\"\n name: \"res4b21_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2a\"\n name: \"scale4b21_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2a\"\n bottom: \"res4b21_branch2a\"\n name: \"res4b21_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2b\"\n name: \"res4b21_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2b\"\n name: \"scale4b21_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2b\"\n bottom: \"res4b21_branch2b\"\n name: \"res4b21_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2c\"\n name: \"res4b21_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2c\"\n top: \"res4b21_branch2c\"\n name: \"scale4b21_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20\"\n bottom: \"res4b21_branch2c\"\n top: \"res4b21\"\n name: \"res4b21\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b21\"\n name: \"res4b21_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b22_branch2a\"\n name: \"res4b22_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2a\"\n name: \"scale4b22_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2a\"\n bottom: \"res4b22_branch2a\"\n name: \"res4b22_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2b\"\n name: \"res4b22_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2b\"\n name: \"scale4b22_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2b\"\n bottom: \"res4b22_branch2b\"\n name: \"res4b22_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2c\"\n name: \"res4b22_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b22_branch2c\"\n top: \"res4b22_branch2c\"\n name: \"scale4b22_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21\"\n bottom: \"res4b22_branch2c\"\n top: \"res4b22\"\n name: \"res4b22\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b22\"\n top: \"res4b22\"\n name: \"res4b22_relu\"\n type: \"ReLU\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4b22\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\n\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rpn_rois'\n# top: 'rpn_scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n#layer {\n# name: 'debug-data'\n# type: 'Python'\n# bottom: 'data'\n# bottom: 'rpn_rois'\n# bottom: 'rpn_scores'\n# python_param {\n# module: 'rpn.debug_layer'\n# layer: 'RPNDebugLayer'\n# }\n#}\n\nlayer {\n name: 'roi-data'\n type: 'Python'\n bottom: 'rpn_rois'\n bottom: 'gt_boxes'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'rpn.proposal_target_layer'\n layer: 'ProposalTargetLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n#========= RCNN ============\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"res4b22\"\n bottom: \"rois\"\n top: \"roi_pool5\"\n roi_pooling_param {\n pooled_w: 14\n pooled_h: 14\n spatial_scale: 0.0625 # 1/16\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\n\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"loss_bbox\"\n loss_weight: 1\n}" }, { "path": "models/pascal_voc/ResNet101_BN_SCALE_Merged_OHEM/faster_rcnn_end2end_ohem/solver.prototxt", "content": "train_net: \"models/pascal_voc/ResNet101_BN_SCALE_Merged_OHEM/faster_rcnn_end2end_ohem/train.prototxt\"\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 50000\ndisplay: 20\naverage_loss: 100\niter_size: 2\nmomentum: 0.9\nweight_decay: 0.0005\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"resnet101_faster_rcnn_bn_scale_merged_end2end_ohem\"\n#debug_info: true\n" }, { "path": "models/pascal_voc/ResNet101_BN_SCALE_Merged_OHEM/faster_rcnn_end2end_ohem/train.prototxt", "content": "name: \"ResNet101\"\n\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n# ------------------------ conv1 -----------------------------\nlayer {\n bottom: \"data\"\n top: \"conv1\"\n name: \"conv1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 7\n pad: 3\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"conv1\"\n name: \"scale_conv1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"conv1\"\n bottom: \"conv1\"\n name: \"conv1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"conv1\"\n top: \"pool1\"\n name: \"pool1\"\n type: \"Pooling\"\n pooling_param {\n kernel_size: 3\n stride: 2\n pool: MAX\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch1\"\n name: \"res2a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n top: \"res2a_branch1\"\n name: \"scale2a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"pool1\"\n top: \"res2a_branch2a\"\n name: \"res2a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2a\"\n name: \"scale2a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2a\"\n bottom: \"res2a_branch2a\"\n name: \"res2a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2a\"\n top: \"res2a_branch2b\"\n name: \"res2a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2b\"\n name: \"scale2a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2a_branch2b\"\n bottom: \"res2a_branch2b\"\n name: \"res2a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a_branch2b\"\n top: \"res2a_branch2c\"\n name: \"res2a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch2c\"\n top: \"res2a_branch2c\"\n name: \"scale2a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a_branch1\"\n bottom: \"res2a_branch2c\"\n top: \"res2a\"\n name: \"res2a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2a\"\n name: \"res2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2a\"\n top: \"res2b_branch2a\"\n name: \"res2b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2a\"\n name: \"scale2b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2a\"\n bottom: \"res2b_branch2a\"\n name: \"res2b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2a\"\n top: \"res2b_branch2b\"\n name: \"res2b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2b\"\n name: \"scale2b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2b_branch2b\"\n bottom: \"res2b_branch2b\"\n name: \"res2b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b_branch2b\"\n top: \"res2b_branch2c\"\n name: \"res2b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b_branch2c\"\n top: \"res2b_branch2c\"\n name: \"scale2b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2a\"\n bottom: \"res2b_branch2c\"\n top: \"res2b\"\n name: \"res2b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2b\"\n name: \"res2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2b\"\n top: \"res2c_branch2a\"\n name: \"res2c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2a\"\n name: \"scale2c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2a\"\n bottom: \"res2c_branch2a\"\n name: \"res2c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2a\"\n top: \"res2c_branch2b\"\n name: \"res2c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 64\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2b\"\n name: \"scale2c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res2c_branch2b\"\n bottom: \"res2c_branch2b\"\n name: \"res2c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c_branch2b\"\n top: \"res2c_branch2c\"\n name: \"res2c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c_branch2c\"\n top: \"res2c_branch2c\"\n name: \"scale2c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2b\"\n bottom: \"res2c_branch2c\"\n top: \"res2c\"\n name: \"res2c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res2c\"\n name: \"res2c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch1\"\n name: \"res3a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n top: \"res3a_branch1\"\n name: \"scale3a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res2c\"\n top: \"res3a_branch2a\"\n name: \"res3a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2a\"\n name: \"scale3a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2a\"\n bottom: \"res3a_branch2a\"\n name: \"res3a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2a\"\n top: \"res3a_branch2b\"\n name: \"res3a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2b\"\n name: \"scale3a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3a_branch2b\"\n bottom: \"res3a_branch2b\"\n name: \"res3a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a_branch2b\"\n top: \"res3a_branch2c\"\n name: \"res3a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch2c\"\n top: \"res3a_branch2c\"\n name: \"scale3a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a_branch1\"\n bottom: \"res3a_branch2c\"\n top: \"res3a\"\n name: \"res3a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3a\"\n name: \"res3a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3a\"\n top: \"res3b1_branch2a\"\n name: \"res3b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2a\"\n name: \"scale3b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2a\"\n bottom: \"res3b1_branch2a\"\n name: \"res3b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2a\"\n top: \"res3b1_branch2b\"\n name: \"res3b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2b\"\n name: \"scale3b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b1_branch2b\"\n bottom: \"res3b1_branch2b\"\n name: \"res3b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1_branch2b\"\n top: \"res3b1_branch2c\"\n name: \"res3b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b1_branch2c\"\n top: \"res3b1_branch2c\"\n name: \"scale3b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3a\"\n bottom: \"res3b1_branch2c\"\n top: \"res3b1\"\n name: \"res3b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b1\"\n name: \"res3b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b1\"\n top: \"res3b2_branch2a\"\n name: \"res3b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2a\"\n name: \"scale3b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2a\"\n bottom: \"res3b2_branch2a\"\n name: \"res3b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2a\"\n top: \"res3b2_branch2b\"\n name: \"res3b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2b\"\n name: \"scale3b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b2_branch2b\"\n bottom: \"res3b2_branch2b\"\n name: \"res3b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2_branch2b\"\n top: \"res3b2_branch2c\"\n name: \"res3b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b2_branch2c\"\n top: \"res3b2_branch2c\"\n name: \"scale3b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b1\"\n bottom: \"res3b2_branch2c\"\n top: \"res3b2\"\n name: \"res3b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b2\"\n name: \"res3b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b2\"\n top: \"res3b3_branch2a\"\n name: \"res3b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2a\"\n name: \"scale3b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2a\"\n bottom: \"res3b3_branch2a\"\n name: \"res3b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2a\"\n top: \"res3b3_branch2b\"\n name: \"res3b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 128\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2b\"\n name: \"scale3b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res3b3_branch2b\"\n bottom: \"res3b3_branch2b\"\n name: \"res3b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3_branch2b\"\n top: \"res3b3_branch2c\"\n name: \"res3b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res3b3_branch2c\"\n top: \"res3b3_branch2c\"\n name: \"scale3b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b2\"\n bottom: \"res3b3_branch2c\"\n top: \"res3b3\"\n name: \"res3b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res3b3\"\n name: \"res3b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch1\"\n name: \"res4a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n top: \"res4a_branch1\"\n name: \"scale4a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res3b3\"\n top: \"res4a_branch2a\"\n name: \"res4a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2a\"\n name: \"scale4a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2a\"\n bottom: \"res4a_branch2a\"\n name: \"res4a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2a\"\n top: \"res4a_branch2b\"\n name: \"res4a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2b\"\n name: \"scale4a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4a_branch2b\"\n bottom: \"res4a_branch2b\"\n name: \"res4a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a_branch2b\"\n top: \"res4a_branch2c\"\n name: \"res4a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch2c\"\n top: \"res4a_branch2c\"\n name: \"scale4a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a_branch1\"\n bottom: \"res4a_branch2c\"\n top: \"res4a\"\n name: \"res4a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4a\"\n name: \"res4a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4a\"\n top: \"res4b1_branch2a\"\n name: \"res4b1_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2a\"\n name: \"scale4b1_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2a\"\n bottom: \"res4b1_branch2a\"\n name: \"res4b1_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2a\"\n top: \"res4b1_branch2b\"\n name: \"res4b1_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2b\"\n name: \"scale4b1_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b1_branch2b\"\n bottom: \"res4b1_branch2b\"\n name: \"res4b1_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1_branch2b\"\n top: \"res4b1_branch2c\"\n name: \"res4b1_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b1_branch2c\"\n top: \"res4b1_branch2c\"\n name: \"scale4b1_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4a\"\n bottom: \"res4b1_branch2c\"\n top: \"res4b1\"\n name: \"res4b1\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b1\"\n name: \"res4b1_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b1\"\n top: \"res4b2_branch2a\"\n name: \"res4b2_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2a\"\n name: \"scale4b2_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2a\"\n bottom: \"res4b2_branch2a\"\n name: \"res4b2_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2a\"\n top: \"res4b2_branch2b\"\n name: \"res4b2_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2b\"\n name: \"scale4b2_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b2_branch2b\"\n bottom: \"res4b2_branch2b\"\n name: \"res4b2_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2_branch2b\"\n top: \"res4b2_branch2c\"\n name: \"res4b2_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b2_branch2c\"\n top: \"res4b2_branch2c\"\n name: \"scale4b2_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b1\"\n bottom: \"res4b2_branch2c\"\n top: \"res4b2\"\n name: \"res4b2\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b2\"\n name: \"res4b2_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b2\"\n top: \"res4b3_branch2a\"\n name: \"res4b3_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2a\"\n name: \"scale4b3_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2a\"\n bottom: \"res4b3_branch2a\"\n name: \"res4b3_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2a\"\n top: \"res4b3_branch2b\"\n name: \"res4b3_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2b\"\n name: \"scale4b3_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b3_branch2b\"\n bottom: \"res4b3_branch2b\"\n name: \"res4b3_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3_branch2b\"\n top: \"res4b3_branch2c\"\n name: \"res4b3_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b3_branch2c\"\n top: \"res4b3_branch2c\"\n name: \"scale4b3_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b2\"\n bottom: \"res4b3_branch2c\"\n top: \"res4b3\"\n name: \"res4b3\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b3\"\n name: \"res4b3_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b3\"\n top: \"res4b4_branch2a\"\n name: \"res4b4_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2a\"\n name: \"scale4b4_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2a\"\n bottom: \"res4b4_branch2a\"\n name: \"res4b4_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2a\"\n top: \"res4b4_branch2b\"\n name: \"res4b4_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2b\"\n name: \"scale4b4_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b4_branch2b\"\n bottom: \"res4b4_branch2b\"\n name: \"res4b4_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4_branch2b\"\n top: \"res4b4_branch2c\"\n name: \"res4b4_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b4_branch2c\"\n top: \"res4b4_branch2c\"\n name: \"scale4b4_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b3\"\n bottom: \"res4b4_branch2c\"\n top: \"res4b4\"\n name: \"res4b4\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b4\"\n name: \"res4b4_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b4\"\n top: \"res4b5_branch2a\"\n name: \"res4b5_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2a\"\n name: \"scale4b5_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2a\"\n bottom: \"res4b5_branch2a\"\n name: \"res4b5_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2a\"\n top: \"res4b5_branch2b\"\n name: \"res4b5_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2b\"\n name: \"scale4b5_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b5_branch2b\"\n bottom: \"res4b5_branch2b\"\n name: \"res4b5_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5_branch2b\"\n top: \"res4b5_branch2c\"\n name: \"res4b5_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b5_branch2c\"\n top: \"res4b5_branch2c\"\n name: \"scale4b5_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b4\"\n bottom: \"res4b5_branch2c\"\n top: \"res4b5\"\n name: \"res4b5\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b5\"\n name: \"res4b5_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b5\"\n top: \"res4b6_branch2a\"\n name: \"res4b6_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2a\"\n name: \"scale4b6_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2a\"\n bottom: \"res4b6_branch2a\"\n name: \"res4b6_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2a\"\n top: \"res4b6_branch2b\"\n name: \"res4b6_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2b\"\n name: \"scale4b6_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b6_branch2b\"\n bottom: \"res4b6_branch2b\"\n name: \"res4b6_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6_branch2b\"\n top: \"res4b6_branch2c\"\n name: \"res4b6_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b6_branch2c\"\n top: \"res4b6_branch2c\"\n name: \"scale4b6_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b5\"\n bottom: \"res4b6_branch2c\"\n top: \"res4b6\"\n name: \"res4b6\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b6\"\n name: \"res4b6_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b6\"\n top: \"res4b7_branch2a\"\n name: \"res4b7_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2a\"\n name: \"scale4b7_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2a\"\n bottom: \"res4b7_branch2a\"\n name: \"res4b7_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2a\"\n top: \"res4b7_branch2b\"\n name: \"res4b7_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2b\"\n name: \"scale4b7_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b7_branch2b\"\n bottom: \"res4b7_branch2b\"\n name: \"res4b7_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7_branch2b\"\n top: \"res4b7_branch2c\"\n name: \"res4b7_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b7_branch2c\"\n top: \"res4b7_branch2c\"\n name: \"scale4b7_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b6\"\n bottom: \"res4b7_branch2c\"\n top: \"res4b7\"\n name: \"res4b7\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b7\"\n name: \"res4b7_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b7\"\n top: \"res4b8_branch2a\"\n name: \"res4b8_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2a\"\n name: \"scale4b8_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2a\"\n bottom: \"res4b8_branch2a\"\n name: \"res4b8_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2a\"\n top: \"res4b8_branch2b\"\n name: \"res4b8_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2b\"\n name: \"scale4b8_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b8_branch2b\"\n bottom: \"res4b8_branch2b\"\n name: \"res4b8_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8_branch2b\"\n top: \"res4b8_branch2c\"\n name: \"res4b8_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b8_branch2c\"\n top: \"res4b8_branch2c\"\n name: \"scale4b8_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b7\"\n bottom: \"res4b8_branch2c\"\n top: \"res4b8\"\n name: \"res4b8\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b8\"\n name: \"res4b8_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b8\"\n top: \"res4b9_branch2a\"\n name: \"res4b9_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2a\"\n name: \"scale4b9_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2a\"\n bottom: \"res4b9_branch2a\"\n name: \"res4b9_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2a\"\n top: \"res4b9_branch2b\"\n name: \"res4b9_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2b\"\n name: \"scale4b9_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b9_branch2b\"\n bottom: \"res4b9_branch2b\"\n name: \"res4b9_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9_branch2b\"\n top: \"res4b9_branch2c\"\n name: \"res4b9_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b9_branch2c\"\n top: \"res4b9_branch2c\"\n name: \"scale4b9_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b8\"\n bottom: \"res4b9_branch2c\"\n top: \"res4b9\"\n name: \"res4b9\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b9\"\n name: \"res4b9_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b9\"\n top: \"res4b10_branch2a\"\n name: \"res4b10_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2a\"\n name: \"scale4b10_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2a\"\n bottom: \"res4b10_branch2a\"\n name: \"res4b10_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2a\"\n top: \"res4b10_branch2b\"\n name: \"res4b10_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2b\"\n name: \"scale4b10_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b10_branch2b\"\n bottom: \"res4b10_branch2b\"\n name: \"res4b10_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10_branch2b\"\n top: \"res4b10_branch2c\"\n name: \"res4b10_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b10_branch2c\"\n top: \"res4b10_branch2c\"\n name: \"scale4b10_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b9\"\n bottom: \"res4b10_branch2c\"\n top: \"res4b10\"\n name: \"res4b10\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b10\"\n name: \"res4b10_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b10\"\n top: \"res4b11_branch2a\"\n name: \"res4b11_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2a\"\n name: \"scale4b11_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2a\"\n bottom: \"res4b11_branch2a\"\n name: \"res4b11_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2a\"\n top: \"res4b11_branch2b\"\n name: \"res4b11_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2b\"\n name: \"scale4b11_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b11_branch2b\"\n bottom: \"res4b11_branch2b\"\n name: \"res4b11_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11_branch2b\"\n top: \"res4b11_branch2c\"\n name: \"res4b11_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b11_branch2c\"\n top: \"res4b11_branch2c\"\n name: \"scale4b11_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b10\"\n bottom: \"res4b11_branch2c\"\n top: \"res4b11\"\n name: \"res4b11\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b11\"\n name: \"res4b11_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b11\"\n top: \"res4b12_branch2a\"\n name: \"res4b12_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2a\"\n name: \"scale4b12_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2a\"\n bottom: \"res4b12_branch2a\"\n name: \"res4b12_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2a\"\n top: \"res4b12_branch2b\"\n name: \"res4b12_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2b\"\n name: \"scale4b12_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b12_branch2b\"\n bottom: \"res4b12_branch2b\"\n name: \"res4b12_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12_branch2b\"\n top: \"res4b12_branch2c\"\n name: \"res4b12_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b12_branch2c\"\n top: \"res4b12_branch2c\"\n name: \"scale4b12_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b11\"\n bottom: \"res4b12_branch2c\"\n top: \"res4b12\"\n name: \"res4b12\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b12\"\n name: \"res4b12_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b12\"\n top: \"res4b13_branch2a\"\n name: \"res4b13_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2a\"\n name: \"scale4b13_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2a\"\n bottom: \"res4b13_branch2a\"\n name: \"res4b13_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2a\"\n top: \"res4b13_branch2b\"\n name: \"res4b13_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2b\"\n name: \"scale4b13_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b13_branch2b\"\n bottom: \"res4b13_branch2b\"\n name: \"res4b13_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13_branch2b\"\n top: \"res4b13_branch2c\"\n name: \"res4b13_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b13_branch2c\"\n top: \"res4b13_branch2c\"\n name: \"scale4b13_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b12\"\n bottom: \"res4b13_branch2c\"\n top: \"res4b13\"\n name: \"res4b13\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b13\"\n name: \"res4b13_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b13\"\n top: \"res4b14_branch2a\"\n name: \"res4b14_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2a\"\n name: \"scale4b14_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2a\"\n bottom: \"res4b14_branch2a\"\n name: \"res4b14_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2a\"\n top: \"res4b14_branch2b\"\n name: \"res4b14_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2b\"\n name: \"scale4b14_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b14_branch2b\"\n bottom: \"res4b14_branch2b\"\n name: \"res4b14_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14_branch2b\"\n top: \"res4b14_branch2c\"\n name: \"res4b14_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b14_branch2c\"\n top: \"res4b14_branch2c\"\n name: \"scale4b14_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b13\"\n bottom: \"res4b14_branch2c\"\n top: \"res4b14\"\n name: \"res4b14\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b14\"\n name: \"res4b14_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b14\"\n top: \"res4b15_branch2a\"\n name: \"res4b15_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2a\"\n name: \"scale4b15_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2a\"\n bottom: \"res4b15_branch2a\"\n name: \"res4b15_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2a\"\n top: \"res4b15_branch2b\"\n name: \"res4b15_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2b\"\n name: \"scale4b15_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b15_branch2b\"\n bottom: \"res4b15_branch2b\"\n name: \"res4b15_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15_branch2b\"\n top: \"res4b15_branch2c\"\n name: \"res4b15_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b15_branch2c\"\n top: \"res4b15_branch2c\"\n name: \"scale4b15_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b14\"\n bottom: \"res4b15_branch2c\"\n top: \"res4b15\"\n name: \"res4b15\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b15\"\n name: \"res4b15_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b15\"\n top: \"res4b16_branch2a\"\n name: \"res4b16_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2a\"\n name: \"scale4b16_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2a\"\n bottom: \"res4b16_branch2a\"\n name: \"res4b16_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2a\"\n top: \"res4b16_branch2b\"\n name: \"res4b16_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2b\"\n name: \"scale4b16_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b16_branch2b\"\n bottom: \"res4b16_branch2b\"\n name: \"res4b16_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16_branch2b\"\n top: \"res4b16_branch2c\"\n name: \"res4b16_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b16_branch2c\"\n top: \"res4b16_branch2c\"\n name: \"scale4b16_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b15\"\n bottom: \"res4b16_branch2c\"\n top: \"res4b16\"\n name: \"res4b16\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b16\"\n name: \"res4b16_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b16\"\n top: \"res4b17_branch2a\"\n name: \"res4b17_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2a\"\n name: \"scale4b17_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2a\"\n bottom: \"res4b17_branch2a\"\n name: \"res4b17_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2a\"\n top: \"res4b17_branch2b\"\n name: \"res4b17_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2b\"\n name: \"scale4b17_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b17_branch2b\"\n bottom: \"res4b17_branch2b\"\n name: \"res4b17_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17_branch2b\"\n top: \"res4b17_branch2c\"\n name: \"res4b17_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b17_branch2c\"\n top: \"res4b17_branch2c\"\n name: \"scale4b17_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b16\"\n bottom: \"res4b17_branch2c\"\n top: \"res4b17\"\n name: \"res4b17\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b17\"\n name: \"res4b17_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b17\"\n top: \"res4b18_branch2a\"\n name: \"res4b18_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2a\"\n name: \"scale4b18_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2a\"\n bottom: \"res4b18_branch2a\"\n name: \"res4b18_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2a\"\n top: \"res4b18_branch2b\"\n name: \"res4b18_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2b\"\n name: \"scale4b18_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b18_branch2b\"\n bottom: \"res4b18_branch2b\"\n name: \"res4b18_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18_branch2b\"\n top: \"res4b18_branch2c\"\n name: \"res4b18_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b18_branch2c\"\n top: \"res4b18_branch2c\"\n name: \"scale4b18_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b17\"\n bottom: \"res4b18_branch2c\"\n top: \"res4b18\"\n name: \"res4b18\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b18\"\n name: \"res4b18_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b18\"\n top: \"res4b19_branch2a\"\n name: \"res4b19_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2a\"\n name: \"scale4b19_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2a\"\n bottom: \"res4b19_branch2a\"\n name: \"res4b19_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2a\"\n top: \"res4b19_branch2b\"\n name: \"res4b19_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2b\"\n name: \"scale4b19_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b19_branch2b\"\n bottom: \"res4b19_branch2b\"\n name: \"res4b19_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19_branch2b\"\n top: \"res4b19_branch2c\"\n name: \"res4b19_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b19_branch2c\"\n top: \"res4b19_branch2c\"\n name: \"scale4b19_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b18\"\n bottom: \"res4b19_branch2c\"\n top: \"res4b19\"\n name: \"res4b19\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b19\"\n name: \"res4b19_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b19\"\n top: \"res4b20_branch2a\"\n name: \"res4b20_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2a\"\n name: \"scale4b20_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2a\"\n bottom: \"res4b20_branch2a\"\n name: \"res4b20_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2a\"\n top: \"res4b20_branch2b\"\n name: \"res4b20_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2b\"\n name: \"scale4b20_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b20_branch2b\"\n bottom: \"res4b20_branch2b\"\n name: \"res4b20_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20_branch2b\"\n top: \"res4b20_branch2c\"\n name: \"res4b20_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b20_branch2c\"\n top: \"res4b20_branch2c\"\n name: \"scale4b20_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b19\"\n bottom: \"res4b20_branch2c\"\n top: \"res4b20\"\n name: \"res4b20\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b20\"\n name: \"res4b20_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b20\"\n top: \"res4b21_branch2a\"\n name: \"res4b21_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2a\"\n name: \"scale4b21_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2a\"\n bottom: \"res4b21_branch2a\"\n name: \"res4b21_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2a\"\n top: \"res4b21_branch2b\"\n name: \"res4b21_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2b\"\n name: \"scale4b21_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b21_branch2b\"\n bottom: \"res4b21_branch2b\"\n name: \"res4b21_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21_branch2b\"\n top: \"res4b21_branch2c\"\n name: \"res4b21_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b21_branch2c\"\n top: \"res4b21_branch2c\"\n name: \"scale4b21_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b20\"\n bottom: \"res4b21_branch2c\"\n top: \"res4b21\"\n name: \"res4b21\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b21\"\n name: \"res4b21_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b21\"\n top: \"res4b22_branch2a\"\n name: \"res4b22_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2a\"\n name: \"scale4b22_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2a\"\n bottom: \"res4b22_branch2a\"\n name: \"res4b22_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2a\"\n top: \"res4b22_branch2b\"\n name: \"res4b22_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 256\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2b\"\n name: \"scale4b22_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res4b22_branch2b\"\n bottom: \"res4b22_branch2b\"\n name: \"res4b22_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res4b22_branch2b\"\n top: \"res4b22_branch2c\"\n name: \"res4b22_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 1024\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res4b22_branch2c\"\n top: \"res4b22_branch2c\"\n name: \"scale4b22_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res4b21\"\n bottom: \"res4b22_branch2c\"\n top: \"res4b22\"\n name: \"res4b22\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res4b22\"\n top: \"res4b22\"\n name: \"res4b22_relu\"\n type: \"ReLU\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"res4b22\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\n\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rpn_rois'\n# top: 'rpn_scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n#layer {\n# name: 'debug-data'\n# type: 'Python'\n# bottom: 'data'\n# bottom: 'rpn_rois'\n# bottom: 'rpn_scores'\n# python_param {\n# module: 'rpn.debug_layer'\n# layer: 'RPNDebugLayer'\n# }\n#}\n\nlayer {\n name: 'roi-data'\n type: 'Python'\n bottom: 'rpn_rois'\n bottom: 'gt_boxes'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'rpn.proposal_target_layer'\n layer: 'ProposalTargetLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n\n\n##########################\n## Readonly RoI Network ##\n######### Start ##########\nlayer {\n name: \"roi_pool5_readonly\"\n type: \"ROIPooling\"\n bottom: \"res4b22\"\n bottom: \"rois\"\n top: \"roi_pool5_readonly\"\n propagate_down: false\n propagate_down: false\n roi_pooling_param {\n pooled_w: 14\n pooled_h: 14\n spatial_scale: 0.0625 # 1/16\n }\n}\n\nlayer {\n bottom: \"roi_pool5_readonly\"\n top: \"res5a_branch1_readonly\"\n name: \"res5a_branch1_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n name: \"res5a_branch1_w\"\n }\n}\n\nlayer {\n bottom: \"res5a_branch1_readonly\"\n top: \"res5a_branch1_readonly\"\n name: \"scale5a_branch1_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch1_w\"\n }\n param {\n name: \"scale5a_branch1_b\"\n }\n}\n\nlayer {\n bottom: \"roi_pool5_readonly\"\n top: \"res5a_branch2a_readonly\"\n name: \"res5a_branch2a_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n name: \"res5a_branch2a_w\"\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a_readonly\"\n top: \"res5a_branch2a_readonly\"\n name: \"scale5a_branch2a_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch2a_w\"\n }\n param {\n name: \"scale5a_branch2a_b\"\n }\n}\n\nlayer {\n top: \"res5a_branch2a_readonly\"\n bottom: \"res5a_branch2a_readonly\"\n name: \"res5a_branch2a_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a_readonly\"\n top: \"res5a_branch2b_readonly\"\n name: \"res5a_branch2b_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5a_branch2b_w\"\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2b_readonly\"\n top: \"res5a_branch2b_readonly\"\n name: \"scale5a_branch2b_readonly\"\n type: \"Scale\"\n propagate_down: false\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch2b_w\"\n }\n param {\n name: \"scale5a_branch2b_b\"\n }\n}\n\nlayer {\n top: \"res5a_branch2b_readonly\"\n bottom: \"res5a_branch2b_readonly\"\n name: \"res5a_branch2b_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b_readonly\"\n top: \"res5a_branch2c_readonly\"\n name: \"res5a_branch2c_readonly\"\n type: \"Convolution\"\n propagate_down: false\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5a_branch2c_w\"\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2c_readonly\"\n top: \"res5a_branch2c_readonly\"\n name: \"scale5a_branch2c_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch2c_w\"\n }\n param {\n name: \"scale5a_branch2c_b\"\n }\n}\n\nlayer {\n bottom: \"res5a_branch1_readonly\"\n bottom: \"res5a_branch2c_readonly\"\n top: \"res5a_readonly\"\n name: \"res5a_readonly\"\n propagate_down: false\n propagate_down: false\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a_readonly\"\n top: \"res5a_readonly\"\n name: \"res5a_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_readonly\"\n top: \"res5b_branch2a_readonly\"\n name: \"res5b_branch2a_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5b_branch2a_w\"\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2a_readonly\"\n top: \"res5b_branch2a_readonly\"\n name: \"scale5b_branch2a_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5b_branch2a_w\"\n }\n param {\n name: \"scale5b_branch2a_b\"\n }\n}\n\nlayer {\n top: \"res5b_branch2a_readonly\"\n bottom: \"res5b_branch2a_readonly\"\n name: \"res5b_branch2a_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a_readonly\"\n top: \"res5b_branch2b_readonly\"\n name: \"res5b_branch2b_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5b_branch2b_w\"\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2b_readonly\"\n top: \"res5b_branch2b_readonly\"\n name: \"scale5b_branch2b_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5b_branch2b_w\"\n }\n param {\n name: \"scale5b_branch2b_b\"\n }\n}\n\nlayer {\n top: \"res5b_branch2b_readonly\"\n bottom: \"res5b_branch2b_readonly\"\n name: \"res5b_branch2b_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b_readonly\"\n top: \"res5b_branch2c_readonly\"\n name: \"res5b_branch2c_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5b_branch2c_w\"\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c_readonly\"\n top: \"res5b_branch2c_readonly\"\n name: \"scale5b_branch2c_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5b_branch2c_w\"\n }\n param {\n name: \"scale5b_branch2c_b\"\n }\n}\n\nlayer {\n bottom: \"res5a_readonly\"\n bottom: \"res5b_branch2c_readonly\"\n top: \"res5b_readonly\"\n name: \"res5b_readonly\"\n propagate_down: false\n propagate_down: false\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b_readonly\"\n top: \"res5b_readonly\"\n name: \"res5b_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_readonly\"\n top: \"res5c_branch2a_readonly\"\n name: \"res5c_branch2a_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5c_branch2a_w\"\n }\n}\n\n\nlayer {\n bottom: \"res5c_branch2a_readonly\"\n top: \"res5c_branch2a_readonly\"\n name: \"scale5c_branch2a_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5c_branch2a_w\"\n }\n param {\n name: \"scale5c_branch2a_b\"\n }\n}\n\nlayer {\n top: \"res5c_branch2a_readonly\"\n bottom: \"res5c_branch2a_readonly\"\n name: \"res5c_branch2a_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a_readonly\"\n top: \"res5c_branch2b_readonly\"\n name: \"res5c_branch2b_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5c_branch2b_w\"\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b_readonly\"\n top: \"res5c_branch2b_readonly\"\n name: \"scale5c_branch2b_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5c_branch2b_w\"\n }\n param {\n name: \"scale5c_branch2b_b\"\n }\n}\n\nlayer {\n top: \"res5c_branch2b_readonly\"\n bottom: \"res5c_branch2b_readonly\"\n name: \"res5c_branch2b_relu_readonly\"\n propagate_down: false\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b_readonly\"\n top: \"res5c_branch2c_readonly\"\n name: \"res5c_branch2c_readonly\"\n propagate_down: false\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5c_branch2c_w\"\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c_readonly\"\n top: \"res5c_branch2c_readonly\"\n name: \"scale5c_branch2c_readonly\"\n propagate_down: false\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5c_branch2c_w\"\n }\n param {\n name: \"scale5c_branch2c_b\"\n }\n}\n\nlayer {\n bottom: \"res5b_readonly\"\n bottom: \"res5c_branch2c_readonly\"\n propagate_down: false\n propagate_down: false\n top: \"res5c_readonly\"\n name: \"res5c_readonly\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c_readonly\"\n top: \"res5c_readonly\"\n propagate_down: false\n name: \"res5c_relu_readonly\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c_readonly\"\n\ttop: \"pool5_readonly\"\n\tname: \"pool5_readonly\"\n\ttype: \"Pooling\"\n\tpropagate_down: false\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\n\nlayer {\n name: \"cls_score_readonly\"\n type: \"InnerProduct\"\n bottom: \"pool5_readonly\"\n top: \"cls_score_readonly\"\n propagate_down: false\n param {\n name: \"cls_score_w\"\n }\n param {\n name: \"cls_score_b\"\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred_readonly\"\n type: \"InnerProduct\"\n bottom: \"pool5_readonly\"\n top: \"bbox_pred_readonly\"\n propagate_down: false\n param {\n name: \"bbox_pred_w\"\n }\n param {\n name: \"bbox_pred_b\"\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"cls_prob_readonly\"\n type: \"Softmax\"\n bottom: \"cls_score_readonly\"\n top: \"cls_prob_readonly\"\n propagate_down: false\n}\nlayer {\n name: \"hard_roi_mining\"\n type: \"Python\"\n bottom: \"cls_prob_readonly\"\n bottom: \"bbox_pred_readonly\"\n bottom: \"rois\"\n bottom: \"labels\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"rois_hard\"\n top: \"labels_hard\"\n top: \"bbox_targets_hard\"\n top: \"bbox_inside_weights_hard\"\n top: \"bbox_outside_weights_hard\"\n propagate_down: false\n propagate_down: false\n propagate_down: false\n propagate_down: false\n propagate_down: false\n propagate_down: false\n propagate_down: false\n python_param {\n module: \"roi_data_layer.layer\"\n layer: \"OHEMDataLayer\"\n param_str: \"'num_classes': 21\"\n }\n}\n########## End ###########\n## Readonly RoI Network ##\n##########################\n\n\n#========= RCNN ============\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"res4b22\"\n bottom: \"rois_hard\"\n top: \"roi_pool5\"\n propagate_down: true\n propagate_down: false\n roi_pooling_param {\n pooled_w: 14\n pooled_h: 14\n spatial_scale: 0.0625 # 1/16\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch1\"\n name: \"res5a_branch1\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n name: \"res5a_branch1_w\"\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n top: \"res5a_branch1\"\n name: \"scale5a_branch1\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch1_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5a_branch1_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"roi_pool5\"\n top: \"res5a_branch2a\"\n name: \"res5a_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 2\n bias_term: false\n }\n param {\n name: \"res5a_branch2a_w\"\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2a\"\n name: \"scale5a_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch2a_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5a_branch2a_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2a\"\n bottom: \"res5a_branch2a\"\n name: \"res5a_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2a\"\n top: \"res5a_branch2b\"\n name: \"res5a_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5a_branch2b_w\"\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2b\"\n name: \"scale5a_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch2b_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5a_branch2b_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5a_branch2b\"\n bottom: \"res5a_branch2b\"\n name: \"res5a_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a_branch2b\"\n top: \"res5a_branch2c\"\n name: \"res5a_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5a_branch2c_w\"\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5a_branch2c\"\n top: \"res5a_branch2c\"\n name: \"scale5a_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5a_branch2c_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5a_branch2c_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a_branch1\"\n bottom: \"res5a_branch2c\"\n top: \"res5a\"\n name: \"res5a\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5a\"\n name: \"res5a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5a\"\n top: \"res5b_branch2a\"\n name: \"res5b_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5b_branch2a_w\"\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2a\"\n name: \"scale5b_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5b_branch2a_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5b_branch2a_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2a\"\n bottom: \"res5b_branch2a\"\n name: \"res5b_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2a\"\n top: \"res5b_branch2b\"\n name: \"res5b_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5b_branch2b_w\"\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2b\"\n name: \"scale5b_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5b_branch2b_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5b_branch2b_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5b_branch2b\"\n bottom: \"res5b_branch2b\"\n name: \"res5b_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b_branch2b\"\n top: \"res5b_branch2c\"\n name: \"res5b_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5b_branch2c_w\"\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5b_branch2c\"\n top: \"res5b_branch2c\"\n name: \"scale5b_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5b_branch2c_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5b_branch2c_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5a\"\n bottom: \"res5b_branch2c\"\n top: \"res5b\"\n name: \"res5b\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5b\"\n name: \"res5b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5b\"\n top: \"res5c_branch2a\"\n name: \"res5c_branch2a\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5c_branch2a_w\"\n lr_mult: 1.0\n }\n}\n\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2a\"\n name: \"scale5c_branch2a\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5c_branch2a_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5c_branch2a_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2a\"\n bottom: \"res5c_branch2a\"\n name: \"res5c_branch2a_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2a\"\n top: \"res5c_branch2b\"\n name: \"res5c_branch2b\"\n type: \"Convolution\"\n convolution_param {\n num_output: 512\n kernel_size: 3\n pad: 1\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5c_branch2b_w\"\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2b\"\n name: \"scale5c_branch2b\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5c_branch2b_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5c_branch2b_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n top: \"res5c_branch2b\"\n bottom: \"res5c_branch2b\"\n name: \"res5c_branch2b_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n bottom: \"res5c_branch2b\"\n top: \"res5c_branch2c\"\n name: \"res5c_branch2c\"\n type: \"Convolution\"\n convolution_param {\n num_output: 2048\n kernel_size: 1\n pad: 0\n stride: 1\n bias_term: false\n }\n param {\n name: \"res5c_branch2c_w\"\n lr_mult: 1.0\n }\n}\n\nlayer {\n bottom: \"res5c_branch2c\"\n top: \"res5c_branch2c\"\n name: \"scale5c_branch2c\"\n type: \"Scale\"\n scale_param {\n bias_term: true\n }\n param {\n name: \"scale5c_branch2c_w\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n param {\n name: \"scale5c_branch2c_b\"\n lr_mult: 0.0\n decay_mult: 0.0\n }\n}\n\nlayer {\n bottom: \"res5b\"\n bottom: \"res5c_branch2c\"\n top: \"res5c\"\n name: \"res5c\"\n type: \"Eltwise\"\n}\n\nlayer {\n bottom: \"res5c\"\n top: \"res5c\"\n name: \"res5c_relu\"\n type: \"ReLU\"\n}\n\nlayer {\n\tbottom: \"res5c\"\n\ttop: \"pool5\"\n\tname: \"pool5\"\n\ttype: \"Pooling\"\n\tpooling_param {\n\t\tkernel_size: 7\n\t\tstride: 1\n\t\tpool: AVE\n\t}\n}\n\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"cls_score\"\n param {\n name: \"cls_score_w\"\n lr_mult: 1\n }\n param {\n name: \"cls_score_b\"\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"bbox_pred\"\n param {\n name: \"bbox_pred_w\"\n lr_mult: 1\n }\n param {\n name: \"bbox_pred_b\"\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\n\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels_hard\"\n propagate_down: 1\n propagate_down: 0\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets_hard\"\n bottom: \"bbox_inside_weights_hard\"\n bottom: \"bbox_outside_weights_hard\"\n top: \"loss_bbox\"\n propagate_down: true\n propagate_down: false\n propagate_down: false\n propagate_down: false\n loss_weight: 1\n}\n" }, { "path": "models/pascal_voc/VGG16/fast_rcnn/solver.prototxt", "content": "train_net: \"models/pascal_voc/VGG16/fast_rcnn/train.prototxt\"\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 30000\ndisplay: 20\naverage_loss: 100\n# iter_size: 1\nmomentum: 0.9\nweight_decay: 0.0005\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"vgg16_fast_rcnn\"\n#debug_info: true\n" }, { "path": "models/pascal_voc/VGG16/fast_rcnn/test.prototxt", "content": "name: \"VGG_ILSVRC_16_layers\"\n\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\n\ninput: \"rois\"\ninput_shape {\n dim: 1 # to be changed on-the-fly to num ROIs\n dim: 5 # [batch ind, x1, y1, x2, y2] zero-based indexing\n}\n\nlayer {\n name: \"conv1_1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1_1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_1\"\n type: \"ReLU\"\n bottom: \"conv1_1\"\n top: \"conv1_1\"\n}\nlayer {\n name: \"conv1_2\"\n type: \"Convolution\"\n bottom: \"conv1_1\"\n top: \"conv1_2\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_2\"\n type: \"ReLU\"\n bottom: \"conv1_2\"\n top: \"conv1_2\"\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"conv1_2\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv2_1\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2_1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_1\"\n type: \"ReLU\"\n bottom: \"conv2_1\"\n top: \"conv2_1\"\n}\nlayer {\n name: \"conv2_2\"\n type: \"Convolution\"\n bottom: \"conv2_1\"\n top: \"conv2_2\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_2\"\n type: \"ReLU\"\n bottom: \"conv2_2\"\n top: \"conv2_2\"\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"conv2_2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv3_1\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3_1\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_1\"\n type: \"ReLU\"\n bottom: \"conv3_1\"\n top: \"conv3_1\"\n}\nlayer {\n name: \"conv3_2\"\n type: \"Convolution\"\n bottom: \"conv3_1\"\n top: \"conv3_2\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_2\"\n type: \"ReLU\"\n bottom: \"conv3_2\"\n top: \"conv3_2\"\n}\nlayer {\n name: \"conv3_3\"\n type: \"Convolution\"\n bottom: \"conv3_2\"\n top: \"conv3_3\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_3\"\n type: \"ReLU\"\n bottom: \"conv3_3\"\n top: \"conv3_3\"\n}\nlayer {\n name: \"pool3\"\n type: \"Pooling\"\n bottom: \"conv3_3\"\n top: \"pool3\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv4_1\"\n type: \"Convolution\"\n bottom: \"pool3\"\n top: \"conv4_1\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_1\"\n type: \"ReLU\"\n bottom: \"conv4_1\"\n top: \"conv4_1\"\n}\nlayer {\n name: \"conv4_2\"\n type: \"Convolution\"\n bottom: \"conv4_1\"\n top: \"conv4_2\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_2\"\n type: \"ReLU\"\n bottom: \"conv4_2\"\n top: \"conv4_2\"\n}\nlayer {\n name: \"conv4_3\"\n type: \"Convolution\"\n bottom: \"conv4_2\"\n top: \"conv4_3\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_3\"\n type: \"ReLU\"\n bottom: \"conv4_3\"\n top: \"conv4_3\"\n}\nlayer {\n name: \"pool4\"\n type: \"Pooling\"\n bottom: \"conv4_3\"\n top: \"pool4\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv5_1\"\n type: \"Convolution\"\n bottom: \"pool4\"\n top: \"conv5_1\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_1\"\n type: \"ReLU\"\n bottom: \"conv5_1\"\n top: \"conv5_1\"\n}\nlayer {\n name: \"conv5_2\"\n type: \"Convolution\"\n bottom: \"conv5_1\"\n top: \"conv5_2\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_2\"\n type: \"ReLU\"\n bottom: \"conv5_2\"\n top: \"conv5_2\"\n}\nlayer {\n name: \"conv5_3\"\n type: \"Convolution\"\n bottom: \"conv5_2\"\n top: \"conv5_3\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_3\"\n type: \"ReLU\"\n bottom: \"conv5_3\"\n top: \"conv5_3\"\n}\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"conv5_3\"\n bottom: \"rois\"\n top: \"pool5\"\n roi_pooling_param {\n pooled_w: 7\n pooled_h: 7\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"fc6\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"drop6\"\n type: \"Dropout\"\n bottom: \"fc6\"\n top: \"fc6\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"drop7\"\n type: \"Dropout\"\n bottom: \"fc7\"\n top: \"fc7\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"cls_prob\"\n type: \"Softmax\"\n bottom: \"cls_score\"\n top: \"cls_prob\"\n}\n" }, { "path": "models/pascal_voc/VGG16/fast_rcnn/train.prototxt", "content": "name: \"VGG_ILSVRC_16_layers\"\nlayer {\n name: 'data'\n type: 'Python'\n top: 'data'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\nlayer {\n name: \"conv1_1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1_1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_1\"\n type: \"ReLU\"\n bottom: \"conv1_1\"\n top: \"conv1_1\"\n}\nlayer {\n name: \"conv1_2\"\n type: \"Convolution\"\n bottom: \"conv1_1\"\n top: \"conv1_2\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_2\"\n type: \"ReLU\"\n bottom: \"conv1_2\"\n top: \"conv1_2\"\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"conv1_2\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv2_1\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2_1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_1\"\n type: \"ReLU\"\n bottom: \"conv2_1\"\n top: \"conv2_1\"\n}\nlayer {\n name: \"conv2_2\"\n type: \"Convolution\"\n bottom: \"conv2_1\"\n top: \"conv2_2\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_2\"\n type: \"ReLU\"\n bottom: \"conv2_2\"\n top: \"conv2_2\"\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"conv2_2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv3_1\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3_1\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_1\"\n type: \"ReLU\"\n bottom: \"conv3_1\"\n top: \"conv3_1\"\n}\nlayer {\n name: \"conv3_2\"\n type: \"Convolution\"\n bottom: \"conv3_1\"\n top: \"conv3_2\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_2\"\n type: \"ReLU\"\n bottom: \"conv3_2\"\n top: \"conv3_2\"\n}\nlayer {\n name: \"conv3_3\"\n type: \"Convolution\"\n bottom: \"conv3_2\"\n top: \"conv3_3\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_3\"\n type: \"ReLU\"\n bottom: \"conv3_3\"\n top: \"conv3_3\"\n}\nlayer {\n name: \"pool3\"\n type: \"Pooling\"\n bottom: \"conv3_3\"\n top: \"pool3\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv4_1\"\n type: \"Convolution\"\n bottom: \"pool3\"\n top: \"conv4_1\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_1\"\n type: \"ReLU\"\n bottom: \"conv4_1\"\n top: \"conv4_1\"\n}\nlayer {\n name: \"conv4_2\"\n type: \"Convolution\"\n bottom: \"conv4_1\"\n top: \"conv4_2\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_2\"\n type: \"ReLU\"\n bottom: \"conv4_2\"\n top: \"conv4_2\"\n}\nlayer {\n name: \"conv4_3\"\n type: \"Convolution\"\n bottom: \"conv4_2\"\n top: \"conv4_3\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_3\"\n type: \"ReLU\"\n bottom: \"conv4_3\"\n top: \"conv4_3\"\n}\nlayer {\n name: \"pool4\"\n type: \"Pooling\"\n bottom: \"conv4_3\"\n top: \"pool4\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv5_1\"\n type: \"Convolution\"\n bottom: \"pool4\"\n top: \"conv5_1\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_1\"\n type: \"ReLU\"\n bottom: \"conv5_1\"\n top: \"conv5_1\"\n}\nlayer {\n name: \"conv5_2\"\n type: \"Convolution\"\n bottom: \"conv5_1\"\n top: \"conv5_2\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_2\"\n type: \"ReLU\"\n bottom: \"conv5_2\"\n top: \"conv5_2\"\n}\nlayer {\n name: \"conv5_3\"\n type: \"Convolution\"\n bottom: \"conv5_2\"\n top: \"conv5_3\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_3\"\n type: \"ReLU\"\n bottom: \"conv5_3\"\n top: \"conv5_3\"\n}\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"conv5_3\"\n bottom: \"rois\"\n top: \"pool5\"\n roi_pooling_param {\n pooled_w: 7\n pooled_h: 7\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"fc6\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"drop6\"\n type: \"Dropout\"\n bottom: \"fc6\"\n top: \"fc6\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"drop7\"\n type: \"Dropout\"\n bottom: \"fc7\"\n top: \"fc7\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"loss_bbox\"\n loss_weight: 1\n}\n" }, { "path": "models/pascal_voc/VGG16/faster_rcnn_alt_opt/faster_rcnn_test.pt", "content": "name: \"VGG_ILSVRC_16_layers\"\n\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\n\ninput: \"im_info\"\ninput_shape {\n dim: 1\n dim: 3\n}\n\nlayer {\n name: \"conv1_1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1_1\"\n convolution_param {\n num_output: 64\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_1\"\n type: \"ReLU\"\n bottom: \"conv1_1\"\n top: \"conv1_1\"\n}\nlayer {\n name: \"conv1_2\"\n type: \"Convolution\"\n bottom: \"conv1_1\"\n top: \"conv1_2\"\n convolution_param {\n num_output: 64\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_2\"\n type: \"ReLU\"\n bottom: \"conv1_2\"\n top: \"conv1_2\"\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"conv1_2\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 2 stride: 2\n }\n}\nlayer {\n name: \"conv2_1\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2_1\"\n convolution_param {\n num_output: 128\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_1\"\n type: \"ReLU\"\n bottom: \"conv2_1\"\n top: \"conv2_1\"\n}\nlayer {\n name: \"conv2_2\"\n type: \"Convolution\"\n bottom: \"conv2_1\"\n top: \"conv2_2\"\n convolution_param {\n num_output: 128\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_2\"\n type: \"ReLU\"\n bottom: \"conv2_2\"\n top: \"conv2_2\"\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"conv2_2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 2 stride: 2\n }\n}\nlayer {\n name: \"conv3_1\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3_1\"\n convolution_param {\n num_output: 256\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_1\"\n type: \"ReLU\"\n bottom: \"conv3_1\"\n top: \"conv3_1\"\n}\nlayer {\n name: \"conv3_2\"\n type: \"Convolution\"\n bottom: \"conv3_1\"\n top: \"conv3_2\"\n convolution_param {\n num_output: 256\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_2\"\n type: \"ReLU\"\n bottom: \"conv3_2\"\n top: \"conv3_2\"\n}\nlayer {\n name: \"conv3_3\"\n type: \"Convolution\"\n bottom: \"conv3_2\"\n top: \"conv3_3\"\n convolution_param {\n num_output: 256\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_3\"\n type: \"ReLU\"\n bottom: \"conv3_3\"\n top: \"conv3_3\"\n}\nlayer {\n name: \"pool3\"\n type: \"Pooling\"\n bottom: \"conv3_3\"\n top: \"pool3\"\n pooling_param {\n pool: MAX\n kernel_size: 2 stride: 2\n }\n}\nlayer {\n name: \"conv4_1\"\n type: \"Convolution\"\n bottom: \"pool3\"\n top: \"conv4_1\"\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_1\"\n type: \"ReLU\"\n bottom: \"conv4_1\"\n top: \"conv4_1\"\n}\nlayer {\n name: \"conv4_2\"\n type: \"Convolution\"\n bottom: \"conv4_1\"\n top: \"conv4_2\"\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_2\"\n type: \"ReLU\"\n bottom: \"conv4_2\"\n top: \"conv4_2\"\n}\nlayer {\n name: \"conv4_3\"\n type: \"Convolution\"\n bottom: \"conv4_2\"\n top: \"conv4_3\"\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_3\"\n type: \"ReLU\"\n bottom: \"conv4_3\"\n top: \"conv4_3\"\n}\nlayer {\n name: \"pool4\"\n type: \"Pooling\"\n bottom: \"conv4_3\"\n top: \"pool4\"\n pooling_param {\n pool: MAX\n kernel_size: 2 stride: 2\n }\n}\nlayer {\n name: \"conv5_1\"\n type: \"Convolution\"\n bottom: \"pool4\"\n top: \"conv5_1\"\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_1\"\n type: \"ReLU\"\n bottom: \"conv5_1\"\n top: \"conv5_1\"\n}\nlayer {\n name: \"conv5_2\"\n type: \"Convolution\"\n bottom: \"conv5_1\"\n top: \"conv5_2\"\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_2\"\n type: \"ReLU\"\n bottom: \"conv5_2\"\n top: \"conv5_2\"\n}\nlayer {\n name: \"conv5_3\"\n type: \"Convolution\"\n bottom: \"conv5_2\"\n top: \"conv5_3\"\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_3\"\n type: \"ReLU\"\n bottom: \"conv5_3\"\n top: \"conv5_3\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"conv5_3\"\n top: \"rpn/output\"\n convolution_param {\n num_output: 512\n kernel_size: 3 pad: 1 stride: 1\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n }\n}\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rois'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n#========= RCNN ============\n\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"conv5_3\"\n bottom: \"rois\"\n top: \"pool5\"\n roi_pooling_param {\n pooled_w: 7\n pooled_h: 7\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"fc6\"\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n inner_product_param {\n num_output: 21\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n inner_product_param {\n num_output: 84\n }\n}\nlayer {\n name: \"cls_prob\"\n type: \"Softmax\"\n bottom: \"cls_score\"\n top: \"cls_prob\"\n}\n" }, { "path": "models/pascal_voc/VGG16/faster_rcnn_alt_opt/rpn_test.pt", "content": "name: \"VGG_ILSVRC_16_layers\"\n\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\n\ninput: \"im_info\"\ninput_shape {\n dim: 1\n dim: 3\n}\n\nlayer {\n name: \"conv1_1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1_1\"\n convolution_param {\n num_output: 64\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_1\"\n type: \"ReLU\"\n bottom: \"conv1_1\"\n top: \"conv1_1\"\n}\nlayer {\n name: \"conv1_2\"\n type: \"Convolution\"\n bottom: \"conv1_1\"\n top: \"conv1_2\"\n convolution_param {\n num_output: 64\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_2\"\n type: \"ReLU\"\n bottom: \"conv1_2\"\n top: \"conv1_2\"\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"conv1_2\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 2 stride: 2\n }\n}\nlayer {\n name: \"conv2_1\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2_1\"\n convolution_param {\n num_output: 128\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_1\"\n type: \"ReLU\"\n bottom: \"conv2_1\"\n top: \"conv2_1\"\n}\nlayer {\n name: \"conv2_2\"\n type: \"Convolution\"\n bottom: \"conv2_1\"\n top: \"conv2_2\"\n convolution_param {\n num_output: 128\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_2\"\n type: \"ReLU\"\n bottom: \"conv2_2\"\n top: \"conv2_2\"\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"conv2_2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 2 stride: 2\n }\n}\nlayer {\n name: \"conv3_1\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3_1\"\n convolution_param {\n num_output: 256\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_1\"\n type: \"ReLU\"\n bottom: \"conv3_1\"\n top: \"conv3_1\"\n}\nlayer {\n name: \"conv3_2\"\n type: \"Convolution\"\n bottom: \"conv3_1\"\n top: \"conv3_2\"\n convolution_param {\n num_output: 256\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_2\"\n type: \"ReLU\"\n bottom: \"conv3_2\"\n top: \"conv3_2\"\n}\nlayer {\n name: \"conv3_3\"\n type: \"Convolution\"\n bottom: \"conv3_2\"\n top: \"conv3_3\"\n convolution_param {\n num_output: 256\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_3\"\n type: \"ReLU\"\n bottom: \"conv3_3\"\n top: \"conv3_3\"\n}\nlayer {\n name: \"pool3\"\n type: \"Pooling\"\n bottom: \"conv3_3\"\n top: \"pool3\"\n pooling_param {\n pool: MAX\n kernel_size: 2 stride: 2\n }\n}\nlayer {\n name: \"conv4_1\"\n type: \"Convolution\"\n bottom: \"pool3\"\n top: \"conv4_1\"\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_1\"\n type: \"ReLU\"\n bottom: \"conv4_1\"\n top: \"conv4_1\"\n}\nlayer {\n name: \"conv4_2\"\n type: \"Convolution\"\n bottom: \"conv4_1\"\n top: \"conv4_2\"\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_2\"\n type: \"ReLU\"\n bottom: \"conv4_2\"\n top: \"conv4_2\"\n}\nlayer {\n name: \"conv4_3\"\n type: \"Convolution\"\n bottom: \"conv4_2\"\n top: \"conv4_3\"\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_3\"\n type: \"ReLU\"\n bottom: \"conv4_3\"\n top: \"conv4_3\"\n}\nlayer {\n name: \"pool4\"\n type: \"Pooling\"\n bottom: \"conv4_3\"\n top: \"pool4\"\n pooling_param {\n pool: MAX\n kernel_size: 2 stride: 2\n }\n}\nlayer {\n name: \"conv5_1\"\n type: \"Convolution\"\n bottom: \"pool4\"\n top: \"conv5_1\"\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_1\"\n type: \"ReLU\"\n bottom: \"conv5_1\"\n top: \"conv5_1\"\n}\nlayer {\n name: \"conv5_2\"\n type: \"Convolution\"\n bottom: \"conv5_1\"\n top: \"conv5_2\"\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_2\"\n type: \"ReLU\"\n bottom: \"conv5_2\"\n top: \"conv5_2\"\n}\nlayer {\n name: \"conv5_3\"\n type: \"Convolution\"\n bottom: \"conv5_2\"\n top: \"conv5_3\"\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_3\"\n type: \"ReLU\"\n bottom: \"conv5_3\"\n top: \"conv5_3\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"conv5_3\"\n top: \"rpn/output\"\n convolution_param {\n num_output: 512\n kernel_size: 3 pad: 1 stride: 1\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n }\n}\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rois'\n top: 'scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n" }, { "path": "models/pascal_voc/VGG16/faster_rcnn_alt_opt/stage1_fast_rcnn_solver30k40k.pt", "content": "train_net: \"models/pascal_voc/VGG16/faster_rcnn_alt_opt/stage1_fast_rcnn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 30000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"vgg16_fast_rcnn\"\n" }, { "path": "models/pascal_voc/VGG16/faster_rcnn_alt_opt/stage1_fast_rcnn_train.pt", "content": "name: \"VGG_ILSVRC_16_layers\"\nlayer {\n name: 'data'\n type: 'Python'\n top: 'data'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\nlayer {\n name: \"conv1_1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1_1\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_1\"\n type: \"ReLU\"\n bottom: \"conv1_1\"\n top: \"conv1_1\"\n}\nlayer {\n name: \"conv1_2\"\n type: \"Convolution\"\n bottom: \"conv1_1\"\n top: \"conv1_2\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_2\"\n type: \"ReLU\"\n bottom: \"conv1_2\"\n top: \"conv1_2\"\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"conv1_2\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv2_1\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2_1\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_1\"\n type: \"ReLU\"\n bottom: \"conv2_1\"\n top: \"conv2_1\"\n}\nlayer {\n name: \"conv2_2\"\n type: \"Convolution\"\n bottom: \"conv2_1\"\n top: \"conv2_2\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_2\"\n type: \"ReLU\"\n bottom: \"conv2_2\"\n top: \"conv2_2\"\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"conv2_2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv3_1\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3_1\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_1\"\n type: \"ReLU\"\n bottom: \"conv3_1\"\n top: \"conv3_1\"\n}\nlayer {\n name: \"conv3_2\"\n type: \"Convolution\"\n bottom: \"conv3_1\"\n top: \"conv3_2\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_2\"\n type: \"ReLU\"\n bottom: \"conv3_2\"\n top: \"conv3_2\"\n}\nlayer {\n name: \"conv3_3\"\n type: \"Convolution\"\n bottom: \"conv3_2\"\n top: \"conv3_3\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_3\"\n type: \"ReLU\"\n bottom: \"conv3_3\"\n top: \"conv3_3\"\n}\nlayer {\n name: \"pool3\"\n type: \"Pooling\"\n bottom: \"conv3_3\"\n top: \"pool3\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv4_1\"\n type: \"Convolution\"\n bottom: \"pool3\"\n top: \"conv4_1\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_1\"\n type: \"ReLU\"\n bottom: \"conv4_1\"\n top: \"conv4_1\"\n}\nlayer {\n name: \"conv4_2\"\n type: \"Convolution\"\n bottom: \"conv4_1\"\n top: \"conv4_2\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_2\"\n type: \"ReLU\"\n bottom: \"conv4_2\"\n top: \"conv4_2\"\n}\nlayer {\n name: \"conv4_3\"\n type: \"Convolution\"\n bottom: \"conv4_2\"\n top: \"conv4_3\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_3\"\n type: \"ReLU\"\n bottom: \"conv4_3\"\n top: \"conv4_3\"\n}\nlayer {\n name: \"pool4\"\n type: \"Pooling\"\n bottom: \"conv4_3\"\n top: \"pool4\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv5_1\"\n type: \"Convolution\"\n bottom: \"pool4\"\n top: \"conv5_1\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_1\"\n type: \"ReLU\"\n bottom: \"conv5_1\"\n top: \"conv5_1\"\n}\nlayer {\n name: \"conv5_2\"\n type: \"Convolution\"\n bottom: \"conv5_1\"\n top: \"conv5_2\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_2\"\n type: \"ReLU\"\n bottom: \"conv5_2\"\n top: \"conv5_2\"\n}\nlayer {\n name: \"conv5_3\"\n type: \"Convolution\"\n bottom: \"conv5_2\"\n top: \"conv5_3\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_3\"\n type: \"ReLU\"\n bottom: \"conv5_3\"\n top: \"conv5_3\"\n}\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"conv5_3\"\n bottom: \"rois\"\n top: \"pool5\"\n roi_pooling_param {\n pooled_w: 7\n pooled_h: 7\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"fc6\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"drop6\"\n type: \"Dropout\"\n bottom: \"fc6\"\n top: \"fc6\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"drop7\"\n type: \"Dropout\"\n bottom: \"fc7\"\n top: \"fc7\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"loss_bbox\"\n loss_weight: 1\n}\n\n#========= RPN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"conv5_3\"\n top: \"rpn/output\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"silence_rpn_cls_score\"\n type: \"Silence\"\n bottom: \"rpn_cls_score\"\n}\nlayer {\n name: \"silence_rpn_bbox_pred\"\n type: \"Silence\"\n bottom: \"rpn_bbox_pred\"\n}\n" }, { "path": "models/pascal_voc/VGG16/faster_rcnn_alt_opt/stage1_rpn_solver60k80k.pt", "content": "train_net: \"models/pascal_voc/VGG16/faster_rcnn_alt_opt/stage1_rpn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 60000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"vgg16_rpn\"\n" }, { "path": "models/pascal_voc/VGG16/faster_rcnn_alt_opt/stage1_rpn_train.pt", "content": "name: \"VGG_ILSVRC_16_layers\"\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\nlayer {\n name: \"conv1_1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1_1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_1\"\n type: \"ReLU\"\n bottom: \"conv1_1\"\n top: \"conv1_1\"\n}\nlayer {\n name: \"conv1_2\"\n type: \"Convolution\"\n bottom: \"conv1_1\"\n top: \"conv1_2\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_2\"\n type: \"ReLU\"\n bottom: \"conv1_2\"\n top: \"conv1_2\"\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"conv1_2\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv2_1\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2_1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_1\"\n type: \"ReLU\"\n bottom: \"conv2_1\"\n top: \"conv2_1\"\n}\nlayer {\n name: \"conv2_2\"\n type: \"Convolution\"\n bottom: \"conv2_1\"\n top: \"conv2_2\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_2\"\n type: \"ReLU\"\n bottom: \"conv2_2\"\n top: \"conv2_2\"\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"conv2_2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv3_1\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3_1\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_1\"\n type: \"ReLU\"\n bottom: \"conv3_1\"\n top: \"conv3_1\"\n}\nlayer {\n name: \"conv3_2\"\n type: \"Convolution\"\n bottom: \"conv3_1\"\n top: \"conv3_2\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_2\"\n type: \"ReLU\"\n bottom: \"conv3_2\"\n top: \"conv3_2\"\n}\nlayer {\n name: \"conv3_3\"\n type: \"Convolution\"\n bottom: \"conv3_2\"\n top: \"conv3_3\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_3\"\n type: \"ReLU\"\n bottom: \"conv3_3\"\n top: \"conv3_3\"\n}\nlayer {\n name: \"pool3\"\n type: \"Pooling\"\n bottom: \"conv3_3\"\n top: \"pool3\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv4_1\"\n type: \"Convolution\"\n bottom: \"pool3\"\n top: \"conv4_1\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_1\"\n type: \"ReLU\"\n bottom: \"conv4_1\"\n top: \"conv4_1\"\n}\nlayer {\n name: \"conv4_2\"\n type: \"Convolution\"\n bottom: \"conv4_1\"\n top: \"conv4_2\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_2\"\n type: \"ReLU\"\n bottom: \"conv4_2\"\n top: \"conv4_2\"\n}\nlayer {\n name: \"conv4_3\"\n type: \"Convolution\"\n bottom: \"conv4_2\"\n top: \"conv4_3\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_3\"\n type: \"ReLU\"\n bottom: \"conv4_3\"\n top: \"conv4_3\"\n}\nlayer {\n name: \"pool4\"\n type: \"Pooling\"\n bottom: \"conv4_3\"\n top: \"pool4\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv5_1\"\n type: \"Convolution\"\n bottom: \"pool4\"\n top: \"conv5_1\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_1\"\n type: \"ReLU\"\n bottom: \"conv5_1\"\n top: \"conv5_1\"\n}\nlayer {\n name: \"conv5_2\"\n type: \"Convolution\"\n bottom: \"conv5_1\"\n top: \"conv5_2\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_2\"\n type: \"ReLU\"\n bottom: \"conv5_2\"\n top: \"conv5_2\"\n}\nlayer {\n name: \"conv5_3\"\n type: \"Convolution\"\n bottom: \"conv5_2\"\n top: \"conv5_3\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_3\"\n type: \"ReLU\"\n bottom: \"conv5_3\"\n top: \"conv5_3\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"conv5_3\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 512\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RCNN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"dummy_roi_pool_conv5\"\n type: \"DummyData\"\n top: \"dummy_roi_pool_conv5\"\n dummy_data_param {\n shape { dim: 1 dim: 25088 }\n data_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"dummy_roi_pool_conv5\"\n top: \"fc6\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"drop6\"\n type: \"Dropout\"\n bottom: \"fc6\"\n top: \"fc6\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"silence_fc7\"\n type: \"Silence\"\n bottom: \"fc7\"\n}\n" }, { "path": "models/pascal_voc/VGG16/faster_rcnn_alt_opt/stage2_fast_rcnn_solver30k40k.pt", "content": "train_net: \"models/pascal_voc/VGG16/faster_rcnn_alt_opt/stage2_fast_rcnn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 30000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"vgg16_fast_rcnn\"\n" }, { "path": "models/pascal_voc/VGG16/faster_rcnn_alt_opt/stage2_fast_rcnn_train.pt", "content": "name: \"VGG_ILSVRC_16_layers\"\nlayer {\n name: 'data'\n type: 'Python'\n top: 'data'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\nlayer {\n name: \"conv1_1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1_1\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_1\"\n type: \"ReLU\"\n bottom: \"conv1_1\"\n top: \"conv1_1\"\n}\nlayer {\n name: \"conv1_2\"\n type: \"Convolution\"\n bottom: \"conv1_1\"\n top: \"conv1_2\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_2\"\n type: \"ReLU\"\n bottom: \"conv1_2\"\n top: \"conv1_2\"\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"conv1_2\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv2_1\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2_1\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_1\"\n type: \"ReLU\"\n bottom: \"conv2_1\"\n top: \"conv2_1\"\n}\nlayer {\n name: \"conv2_2\"\n type: \"Convolution\"\n bottom: \"conv2_1\"\n top: \"conv2_2\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_2\"\n type: \"ReLU\"\n bottom: \"conv2_2\"\n top: \"conv2_2\"\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"conv2_2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv3_1\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3_1\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_1\"\n type: \"ReLU\"\n bottom: \"conv3_1\"\n top: \"conv3_1\"\n}\nlayer {\n name: \"conv3_2\"\n type: \"Convolution\"\n bottom: \"conv3_1\"\n top: \"conv3_2\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_2\"\n type: \"ReLU\"\n bottom: \"conv3_2\"\n top: \"conv3_2\"\n}\nlayer {\n name: \"conv3_3\"\n type: \"Convolution\"\n bottom: \"conv3_2\"\n top: \"conv3_3\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_3\"\n type: \"ReLU\"\n bottom: \"conv3_3\"\n top: \"conv3_3\"\n}\nlayer {\n name: \"pool3\"\n type: \"Pooling\"\n bottom: \"conv3_3\"\n top: \"pool3\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv4_1\"\n type: \"Convolution\"\n bottom: \"pool3\"\n top: \"conv4_1\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_1\"\n type: \"ReLU\"\n bottom: \"conv4_1\"\n top: \"conv4_1\"\n}\nlayer {\n name: \"conv4_2\"\n type: \"Convolution\"\n bottom: \"conv4_1\"\n top: \"conv4_2\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_2\"\n type: \"ReLU\"\n bottom: \"conv4_2\"\n top: \"conv4_2\"\n}\nlayer {\n name: \"conv4_3\"\n type: \"Convolution\"\n bottom: \"conv4_2\"\n top: \"conv4_3\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_3\"\n type: \"ReLU\"\n bottom: \"conv4_3\"\n top: \"conv4_3\"\n}\nlayer {\n name: \"pool4\"\n type: \"Pooling\"\n bottom: \"conv4_3\"\n top: \"pool4\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv5_1\"\n type: \"Convolution\"\n bottom: \"pool4\"\n top: \"conv5_1\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_1\"\n type: \"ReLU\"\n bottom: \"conv5_1\"\n top: \"conv5_1\"\n}\nlayer {\n name: \"conv5_2\"\n type: \"Convolution\"\n bottom: \"conv5_1\"\n top: \"conv5_2\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_2\"\n type: \"ReLU\"\n bottom: \"conv5_2\"\n top: \"conv5_2\"\n}\nlayer {\n name: \"conv5_3\"\n type: \"Convolution\"\n bottom: \"conv5_2\"\n top: \"conv5_3\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_3\"\n type: \"ReLU\"\n bottom: \"conv5_3\"\n top: \"conv5_3\"\n}\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"conv5_3\"\n bottom: \"rois\"\n top: \"pool5\"\n roi_pooling_param {\n pooled_w: 7\n pooled_h: 7\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"fc6\"\n param { lr_mult: 1 }\n param { lr_mult: 2 }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"drop6\"\n type: \"Dropout\"\n bottom: \"fc6\"\n top: \"fc6\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param { lr_mult: 1 }\n param { lr_mult: 2 }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"drop7\"\n type: \"Dropout\"\n bottom: \"fc7\"\n top: \"fc7\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param { lr_mult: 1 }\n param { lr_mult: 2 }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param { lr_mult: 1 }\n param { lr_mult: 2 }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"loss_bbox\"\n loss_weight: 1\n}\n\n#========= RPN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"conv5_3\"\n top: \"rpn/output\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"silence_rpn_cls_score\"\n type: \"Silence\"\n bottom: \"rpn_cls_score\"\n}\nlayer {\n name: \"silence_rpn_bbox_pred\"\n type: \"Silence\"\n bottom: \"rpn_bbox_pred\"\n}\n" }, { "path": "models/pascal_voc/VGG16/faster_rcnn_alt_opt/stage2_rpn_solver60k80k.pt", "content": "train_net: \"models/pascal_voc/VGG16/faster_rcnn_alt_opt/stage2_rpn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 60000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"vgg16_rpn\"\n" }, { "path": "models/pascal_voc/VGG16/faster_rcnn_alt_opt/stage2_rpn_train.pt", "content": "name: \"VGG_ILSVRC_16_layers\"\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\nlayer {\n name: \"conv1_1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1_1\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_1\"\n type: \"ReLU\"\n bottom: \"conv1_1\"\n top: \"conv1_1\"\n}\nlayer {\n name: \"conv1_2\"\n type: \"Convolution\"\n bottom: \"conv1_1\"\n top: \"conv1_2\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_2\"\n type: \"ReLU\"\n bottom: \"conv1_2\"\n top: \"conv1_2\"\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"conv1_2\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv2_1\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2_1\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_1\"\n type: \"ReLU\"\n bottom: \"conv2_1\"\n top: \"conv2_1\"\n}\nlayer {\n name: \"conv2_2\"\n type: \"Convolution\"\n bottom: \"conv2_1\"\n top: \"conv2_2\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_2\"\n type: \"ReLU\"\n bottom: \"conv2_2\"\n top: \"conv2_2\"\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"conv2_2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv3_1\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3_1\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_1\"\n type: \"ReLU\"\n bottom: \"conv3_1\"\n top: \"conv3_1\"\n}\nlayer {\n name: \"conv3_2\"\n type: \"Convolution\"\n bottom: \"conv3_1\"\n top: \"conv3_2\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_2\"\n type: \"ReLU\"\n bottom: \"conv3_2\"\n top: \"conv3_2\"\n}\nlayer {\n name: \"conv3_3\"\n type: \"Convolution\"\n bottom: \"conv3_2\"\n top: \"conv3_3\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_3\"\n type: \"ReLU\"\n bottom: \"conv3_3\"\n top: \"conv3_3\"\n}\nlayer {\n name: \"pool3\"\n type: \"Pooling\"\n bottom: \"conv3_3\"\n top: \"pool3\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv4_1\"\n type: \"Convolution\"\n bottom: \"pool3\"\n top: \"conv4_1\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_1\"\n type: \"ReLU\"\n bottom: \"conv4_1\"\n top: \"conv4_1\"\n}\nlayer {\n name: \"conv4_2\"\n type: \"Convolution\"\n bottom: \"conv4_1\"\n top: \"conv4_2\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_2\"\n type: \"ReLU\"\n bottom: \"conv4_2\"\n top: \"conv4_2\"\n}\nlayer {\n name: \"conv4_3\"\n type: \"Convolution\"\n bottom: \"conv4_2\"\n top: \"conv4_3\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_3\"\n type: \"ReLU\"\n bottom: \"conv4_3\"\n top: \"conv4_3\"\n}\nlayer {\n name: \"pool4\"\n type: \"Pooling\"\n bottom: \"conv4_3\"\n top: \"pool4\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv5_1\"\n type: \"Convolution\"\n bottom: \"pool4\"\n top: \"conv5_1\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_1\"\n type: \"ReLU\"\n bottom: \"conv5_1\"\n top: \"conv5_1\"\n}\nlayer {\n name: \"conv5_2\"\n type: \"Convolution\"\n bottom: \"conv5_1\"\n top: \"conv5_2\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_2\"\n type: \"ReLU\"\n bottom: \"conv5_2\"\n top: \"conv5_2\"\n}\nlayer {\n name: \"conv5_3\"\n type: \"Convolution\"\n bottom: \"conv5_2\"\n top: \"conv5_3\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_3\"\n type: \"ReLU\"\n bottom: \"conv5_3\"\n top: \"conv5_3\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"conv5_3\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 512\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RCNN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"dummy_roi_pool_conv5\"\n type: \"DummyData\"\n top: \"dummy_roi_pool_conv5\"\n dummy_data_param {\n shape { dim: 1 dim: 25088 }\n data_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"dummy_roi_pool_conv5\"\n top: \"fc6\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"drop6\"\n type: \"Dropout\"\n bottom: \"fc6\"\n top: \"fc6\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"silence_fc7\"\n type: \"Silence\"\n bottom: \"fc7\"\n}\n" }, { "path": "models/pascal_voc/VGG16/faster_rcnn_end2end/solver.prototxt", "content": "train_net: \"models/pascal_voc/VGG16/faster_rcnn_end2end/train.prototxt\"\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 50000\ndisplay: 20\naverage_loss: 100\n# iter_size: 1\nmomentum: 0.9\nweight_decay: 0.0005\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"vgg16_faster_rcnn\"\niter_size: 2\n" }, { "path": "models/pascal_voc/VGG16/faster_rcnn_end2end/test.prototxt", "content": "name: \"VGG_ILSVRC_16_layers\"\n\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\n\ninput: \"im_info\"\ninput_shape {\n dim: 1\n dim: 3\n}\n\nlayer {\n name: \"conv1_1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1_1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_1\"\n type: \"ReLU\"\n bottom: \"conv1_1\"\n top: \"conv1_1\"\n}\nlayer {\n name: \"conv1_2\"\n type: \"Convolution\"\n bottom: \"conv1_1\"\n top: \"conv1_2\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_2\"\n type: \"ReLU\"\n bottom: \"conv1_2\"\n top: \"conv1_2\"\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"conv1_2\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv2_1\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2_1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_1\"\n type: \"ReLU\"\n bottom: \"conv2_1\"\n top: \"conv2_1\"\n}\nlayer {\n name: \"conv2_2\"\n type: \"Convolution\"\n bottom: \"conv2_1\"\n top: \"conv2_2\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_2\"\n type: \"ReLU\"\n bottom: \"conv2_2\"\n top: \"conv2_2\"\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"conv2_2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv3_1\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3_1\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_1\"\n type: \"ReLU\"\n bottom: \"conv3_1\"\n top: \"conv3_1\"\n}\nlayer {\n name: \"conv3_2\"\n type: \"Convolution\"\n bottom: \"conv3_1\"\n top: \"conv3_2\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_2\"\n type: \"ReLU\"\n bottom: \"conv3_2\"\n top: \"conv3_2\"\n}\nlayer {\n name: \"conv3_3\"\n type: \"Convolution\"\n bottom: \"conv3_2\"\n top: \"conv3_3\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_3\"\n type: \"ReLU\"\n bottom: \"conv3_3\"\n top: \"conv3_3\"\n}\nlayer {\n name: \"pool3\"\n type: \"Pooling\"\n bottom: \"conv3_3\"\n top: \"pool3\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv4_1\"\n type: \"Convolution\"\n bottom: \"pool3\"\n top: \"conv4_1\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_1\"\n type: \"ReLU\"\n bottom: \"conv4_1\"\n top: \"conv4_1\"\n}\nlayer {\n name: \"conv4_2\"\n type: \"Convolution\"\n bottom: \"conv4_1\"\n top: \"conv4_2\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_2\"\n type: \"ReLU\"\n bottom: \"conv4_2\"\n top: \"conv4_2\"\n}\nlayer {\n name: \"conv4_3\"\n type: \"Convolution\"\n bottom: \"conv4_2\"\n top: \"conv4_3\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_3\"\n type: \"ReLU\"\n bottom: \"conv4_3\"\n top: \"conv4_3\"\n}\nlayer {\n name: \"pool4\"\n type: \"Pooling\"\n bottom: \"conv4_3\"\n top: \"pool4\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv5_1\"\n type: \"Convolution\"\n bottom: \"pool4\"\n top: \"conv5_1\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_1\"\n type: \"ReLU\"\n bottom: \"conv5_1\"\n top: \"conv5_1\"\n}\nlayer {\n name: \"conv5_2\"\n type: \"Convolution\"\n bottom: \"conv5_1\"\n top: \"conv5_2\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_2\"\n type: \"ReLU\"\n bottom: \"conv5_2\"\n top: \"conv5_2\"\n}\nlayer {\n name: \"conv5_3\"\n type: \"Convolution\"\n bottom: \"conv5_2\"\n top: \"conv5_3\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_3\"\n type: \"ReLU\"\n bottom: \"conv5_3\"\n top: \"conv5_3\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"conv5_3\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 decay_mult: 1.0 }\n param { lr_mult: 2.0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 decay_mult: 1.0 }\n param { lr_mult: 2.0 decay_mult: 0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 decay_mult: 1.0 }\n param { lr_mult: 2.0 decay_mult: 0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rois'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n#========= RCNN ============\n\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"conv5_3\"\n bottom: \"rois\"\n top: \"pool5\"\n roi_pooling_param {\n pooled_w: 7\n pooled_h: 7\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"fc6\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"drop6\"\n type: \"Dropout\"\n bottom: \"fc6\"\n top: \"fc6\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"drop7\"\n type: \"Dropout\"\n bottom: \"fc7\"\n top: \"fc7\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"cls_prob\"\n type: \"Softmax\"\n bottom: \"cls_score\"\n top: \"cls_prob\"\n}\n" }, { "path": "models/pascal_voc/VGG16/faster_rcnn_end2end/train.prototxt", "content": "name: \"VGG_ILSVRC_16_layers\"\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\nlayer {\n name: \"conv1_1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1_1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_1\"\n type: \"ReLU\"\n bottom: \"conv1_1\"\n top: \"conv1_1\"\n}\nlayer {\n name: \"conv1_2\"\n type: \"Convolution\"\n bottom: \"conv1_1\"\n top: \"conv1_2\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 64\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu1_2\"\n type: \"ReLU\"\n bottom: \"conv1_2\"\n top: \"conv1_2\"\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"conv1_2\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv2_1\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2_1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_1\"\n type: \"ReLU\"\n bottom: \"conv2_1\"\n top: \"conv2_1\"\n}\nlayer {\n name: \"conv2_2\"\n type: \"Convolution\"\n bottom: \"conv2_1\"\n top: \"conv2_2\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 128\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu2_2\"\n type: \"ReLU\"\n bottom: \"conv2_2\"\n top: \"conv2_2\"\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"conv2_2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv3_1\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3_1\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_1\"\n type: \"ReLU\"\n bottom: \"conv3_1\"\n top: \"conv3_1\"\n}\nlayer {\n name: \"conv3_2\"\n type: \"Convolution\"\n bottom: \"conv3_1\"\n top: \"conv3_2\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_2\"\n type: \"ReLU\"\n bottom: \"conv3_2\"\n top: \"conv3_2\"\n}\nlayer {\n name: \"conv3_3\"\n type: \"Convolution\"\n bottom: \"conv3_2\"\n top: \"conv3_3\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3_3\"\n type: \"ReLU\"\n bottom: \"conv3_3\"\n top: \"conv3_3\"\n}\nlayer {\n name: \"pool3\"\n type: \"Pooling\"\n bottom: \"conv3_3\"\n top: \"pool3\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv4_1\"\n type: \"Convolution\"\n bottom: \"pool3\"\n top: \"conv4_1\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_1\"\n type: \"ReLU\"\n bottom: \"conv4_1\"\n top: \"conv4_1\"\n}\nlayer {\n name: \"conv4_2\"\n type: \"Convolution\"\n bottom: \"conv4_1\"\n top: \"conv4_2\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_2\"\n type: \"ReLU\"\n bottom: \"conv4_2\"\n top: \"conv4_2\"\n}\nlayer {\n name: \"conv4_3\"\n type: \"Convolution\"\n bottom: \"conv4_2\"\n top: \"conv4_3\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4_3\"\n type: \"ReLU\"\n bottom: \"conv4_3\"\n top: \"conv4_3\"\n}\nlayer {\n name: \"pool4\"\n type: \"Pooling\"\n bottom: \"conv4_3\"\n top: \"pool4\"\n pooling_param {\n pool: MAX\n kernel_size: 2\n stride: 2\n }\n}\nlayer {\n name: \"conv5_1\"\n type: \"Convolution\"\n bottom: \"pool4\"\n top: \"conv5_1\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_1\"\n type: \"ReLU\"\n bottom: \"conv5_1\"\n top: \"conv5_1\"\n}\nlayer {\n name: \"conv5_2\"\n type: \"Convolution\"\n bottom: \"conv5_1\"\n top: \"conv5_2\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_2\"\n type: \"ReLU\"\n bottom: \"conv5_2\"\n top: \"conv5_2\"\n}\nlayer {\n name: \"conv5_3\"\n type: \"Convolution\"\n bottom: \"conv5_2\"\n top: \"conv5_3\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5_3\"\n type: \"ReLU\"\n bottom: \"conv5_3\"\n top: \"conv5_3\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"conv5_3\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 512\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\n\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rpn_rois'\n# top: 'rpn_scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n#layer {\n# name: 'debug-data'\n# type: 'Python'\n# bottom: 'data'\n# bottom: 'rpn_rois'\n# bottom: 'rpn_scores'\n# python_param {\n# module: 'rpn.debug_layer'\n# layer: 'RPNDebugLayer'\n# }\n#}\n\nlayer {\n name: 'roi-data'\n type: 'Python'\n bottom: 'rpn_rois'\n bottom: 'gt_boxes'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'rpn.proposal_target_layer'\n layer: 'ProposalTargetLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n#========= RCNN ============\n\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"conv5_3\"\n bottom: \"rois\"\n top: \"pool5\"\n roi_pooling_param {\n pooled_w: 7\n pooled_h: 7\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"fc6\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"drop6\"\n type: \"Dropout\"\n bottom: \"fc6\"\n top: \"fc6\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"drop7\"\n type: \"Dropout\"\n bottom: \"fc7\"\n top: \"fc7\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"loss_bbox\"\n loss_weight: 1\n}\n" }, { "path": "models/pascal_voc/VGG_CNN_M_1024/fast_rcnn/solver.prototxt", "content": "train_net: \"models/pascal_voc/VGG_CNN_M_1024/fast_rcnn/train.prototxt\"\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 30000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"vgg_cnn_m_1024_fast_rcnn\"\n#debug_info: true\n" }, { "path": "models/pascal_voc/VGG_CNN_M_1024/fast_rcnn/test.prototxt", "content": "name: \"VGG_CNN_M_1024\"\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\ninput: \"rois\"\ninput_shape {\n dim: 1 # to be changed on-the-fly to num ROIs\n dim: 5 # [batch ind, x1, y1, x2, y2] zero-based indexing\n}\nlayer {\n name: \"conv1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 96\n kernel_size: 7\n stride: 2\n }\n}\nlayer {\n name: \"relu1\"\n type: \"ReLU\"\n bottom: \"conv1\"\n top: \"conv1\"\n}\nlayer {\n name: \"norm1\"\n type: \"LRN\"\n bottom: \"conv1\"\n top: \"norm1\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"norm1\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 3\n stride: 2\n }\n}\nlayer {\n name: \"conv2\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 5\n stride: 2\n }\n}\nlayer {\n name: \"relu2\"\n type: \"ReLU\"\n bottom: \"conv2\"\n top: \"conv2\"\n}\nlayer {\n name: \"norm2\"\n type: \"LRN\"\n bottom: \"conv2\"\n top: \"norm2\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"norm2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 3\n stride: 2\n }\n}\nlayer {\n name: \"conv3\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3\"\n type: \"ReLU\"\n bottom: \"conv3\"\n top: \"conv3\"\n}\nlayer {\n name: \"conv4\"\n type: \"Convolution\"\n bottom: \"conv3\"\n top: \"conv4\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4\"\n type: \"ReLU\"\n bottom: \"conv4\"\n top: \"conv4\"\n}\nlayer {\n name: \"conv5\"\n type: \"Convolution\"\n bottom: \"conv4\"\n top: \"conv5\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5\"\n type: \"ReLU\"\n bottom: \"conv5\"\n top: \"conv5\"\n}\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"conv5\"\n bottom: \"rois\"\n top: \"pool5\"\n roi_pooling_param {\n pooled_w: 6\n pooled_h: 6\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"fc6\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"drop6\"\n type: \"Dropout\"\n bottom: \"fc6\"\n top: \"fc6\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 1024\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"drop7\"\n type: \"Dropout\"\n bottom: \"fc7\"\n top: \"fc7\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"cls_prob\"\n type: \"Softmax\"\n bottom: \"cls_score\"\n top: \"cls_prob\"\n}\n" }, { "path": "models/pascal_voc/VGG_CNN_M_1024/fast_rcnn/train.prototxt", "content": "name: \"VGG_CNN_M_1024\"\nlayer {\n name: 'data'\n type: 'Python'\n top: 'data'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\nlayer {\n name: \"conv1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 96\n kernel_size: 7\n stride: 2\n }\n}\nlayer {\n name: \"relu1\"\n type: \"ReLU\"\n bottom: \"conv1\"\n top: \"conv1\"\n}\nlayer {\n name: \"norm1\"\n type: \"LRN\"\n bottom: \"conv1\"\n top: \"norm1\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"norm1\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 3\n stride: 2\n }\n}\nlayer {\n name: \"conv2\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 5\n stride: 2\n }\n}\nlayer {\n name: \"relu2\"\n type: \"ReLU\"\n bottom: \"conv2\"\n top: \"conv2\"\n}\nlayer {\n name: \"norm2\"\n type: \"LRN\"\n bottom: \"conv2\"\n top: \"norm2\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"norm2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 3\n stride: 2\n }\n}\nlayer {\n name: \"conv3\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3\"\n type: \"ReLU\"\n bottom: \"conv3\"\n top: \"conv3\"\n}\nlayer {\n name: \"conv4\"\n type: \"Convolution\"\n bottom: \"conv3\"\n top: \"conv4\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4\"\n type: \"ReLU\"\n bottom: \"conv4\"\n top: \"conv4\"\n}\nlayer {\n name: \"conv5\"\n type: \"Convolution\"\n bottom: \"conv4\"\n top: \"conv5\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5\"\n type: \"ReLU\"\n bottom: \"conv5\"\n top: \"conv5\"\n}\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"conv5\"\n bottom: \"rois\"\n top: \"pool5\"\n roi_pooling_param {\n pooled_w: 6\n pooled_h: 6\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"fc6\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"drop6\"\n type: \"Dropout\"\n bottom: \"fc6\"\n top: \"fc6\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 1024\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"drop7\"\n type: \"Dropout\"\n bottom: \"fc7\"\n top: \"fc7\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"loss_bbox\"\n loss_weight: 1\n}\n" }, { "path": "models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_alt_opt/faster_rcnn_test.pt", "content": "name: \"VGG_CNN_M_1024\"\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\ninput: \"im_info\"\ninput_shape {\n dim: 1\n dim: 3\n}\nlayer {\n name: \"conv1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1\"\n convolution_param {\n num_output: 96\n kernel_size: 7\n stride: 2\n }\n}\nlayer {\n name: \"relu1\"\n type: \"ReLU\"\n bottom: \"conv1\"\n top: \"conv1\"\n}\nlayer {\n name: \"norm1\"\n type: \"LRN\"\n bottom: \"conv1\"\n top: \"norm1\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"norm1\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 3\n stride: 2\n }\n}\nlayer {\n name: \"conv2\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2\"\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 5\n stride: 2\n }\n}\nlayer {\n name: \"relu2\"\n type: \"ReLU\"\n bottom: \"conv2\"\n top: \"conv2\"\n}\nlayer {\n name: \"norm2\"\n type: \"LRN\"\n bottom: \"conv2\"\n top: \"norm2\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"norm2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 3\n stride: 2\n }\n}\nlayer {\n name: \"conv3\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3\"\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3\"\n type: \"ReLU\"\n bottom: \"conv3\"\n top: \"conv3\"\n}\nlayer {\n name: \"conv4\"\n type: \"Convolution\"\n bottom: \"conv3\"\n top: \"conv4\"\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4\"\n type: \"ReLU\"\n bottom: \"conv4\"\n top: \"conv4\"\n}\nlayer {\n name: \"conv5\"\n type: \"Convolution\"\n bottom: \"conv4\"\n top: \"conv5\"\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5\"\n type: \"ReLU\"\n bottom: \"conv5\"\n top: \"conv5\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"conv5\"\n top: \"rpn/output\"\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n }\n}\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rois'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n#========= RCNN ============\n\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"conv5\"\n bottom: \"rois\"\n top: \"pool5\"\n roi_pooling_param {\n pooled_w: 6\n pooled_h: 6\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"fc6\"\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n inner_product_param {\n num_output: 1024\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n inner_product_param {\n num_output: 21\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n inner_product_param {\n num_output: 84\n }\n}\nlayer {\n name: \"cls_prob\"\n type: \"Softmax\"\n bottom: \"cls_score\"\n top: \"cls_prob\"\n}\n" }, { "path": "models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_alt_opt/rpn_test.pt", "content": "name: \"VGG_CNN_M_1024\"\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\ninput: \"im_info\"\ninput_shape {\n dim: 1\n dim: 3\n}\nlayer {\n name: \"conv1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1\"\n convolution_param {\n num_output: 96\n kernel_size: 7\n stride: 2\n }\n}\nlayer {\n name: \"relu1\"\n type: \"ReLU\"\n bottom: \"conv1\"\n top: \"conv1\"\n}\nlayer {\n name: \"norm1\"\n type: \"LRN\"\n bottom: \"conv1\"\n top: \"norm1\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"norm1\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 3\n stride: 2\n }\n}\nlayer {\n name: \"conv2\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2\"\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 5\n stride: 2\n }\n}\nlayer {\n name: \"relu2\"\n type: \"ReLU\"\n bottom: \"conv2\"\n top: \"conv2\"\n}\nlayer {\n name: \"norm2\"\n type: \"LRN\"\n bottom: \"conv2\"\n top: \"norm2\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"norm2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 3\n stride: 2\n }\n}\nlayer {\n name: \"conv3\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3\"\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3\"\n type: \"ReLU\"\n bottom: \"conv3\"\n top: \"conv3\"\n}\nlayer {\n name: \"conv4\"\n type: \"Convolution\"\n bottom: \"conv3\"\n top: \"conv4\"\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4\"\n type: \"ReLU\"\n bottom: \"conv4\"\n top: \"conv4\"\n}\nlayer {\n name: \"conv5\"\n type: \"Convolution\"\n bottom: \"conv4\"\n top: \"conv5\"\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5\"\n type: \"ReLU\"\n bottom: \"conv5\"\n top: \"conv5\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"conv5\"\n top: \"rpn/output\"\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n }\n}\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rois'\n top: 'scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n" }, { "path": "models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_alt_opt/stage1_fast_rcnn_solver30k40k.pt", "content": "train_net: \"models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_alt_opt/stage1_fast_rcnn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 30000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"vgg_cnn_m_1024_fast_rcnn\"\n" }, { "path": "models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_alt_opt/stage1_fast_rcnn_train.pt", "content": "name: \"VGG_CNN_M_1024\"\nlayer {\n name: 'data'\n type: 'Python'\n top: 'data'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\nlayer {\n name: \"conv1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 96\n kernel_size: 7 stride: 2\n }\n}\nlayer {\n name: \"relu1\"\n type: \"ReLU\"\n bottom: \"conv1\"\n top: \"conv1\"\n}\nlayer {\n name: \"norm1\"\n type: \"LRN\"\n bottom: \"conv1\"\n top: \"norm1\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"norm1\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 3 stride: 2\n }\n}\nlayer {\n name: \"conv2\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2\"\n param { lr_mult: 1 }\n param { lr_mult: 2 }\n convolution_param {\n num_output: 256\n pad: 1 kernel_size: 5 stride: 2\n }\n}\nlayer {\n name: \"relu2\"\n type: \"ReLU\"\n bottom: \"conv2\"\n top: \"conv2\"\n}\nlayer {\n name: \"norm2\"\n type: \"LRN\"\n bottom: \"conv2\"\n top: \"norm2\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"norm2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 3 stride: 2\n }\n}\nlayer {\n name: \"conv3\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3\"\n param { lr_mult: 1 }\n param { lr_mult: 2 }\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu3\"\n type: \"ReLU\"\n bottom: \"conv3\"\n top: \"conv3\"\n}\nlayer {\n name: \"conv4\"\n type: \"Convolution\"\n bottom: \"conv3\"\n top: \"conv4\"\n param { lr_mult: 1 }\n param { lr_mult: 2 }\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu4\"\n type: \"ReLU\"\n bottom: \"conv4\"\n top: \"conv4\"\n}\nlayer {\n name: \"conv5\"\n type: \"Convolution\"\n bottom: \"conv4\"\n top: \"conv5\"\n param { lr_mult: 1 }\n param { lr_mult: 2 }\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu5\"\n type: \"ReLU\"\n bottom: \"conv5\"\n top: \"conv5\"\n}\n\n#========= RCNN ============\n\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"conv5\"\n bottom: \"rois\"\n top: \"pool5\"\n roi_pooling_param {\n pooled_w: 6\n pooled_h: 6\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"fc6\"\n param { lr_mult: 1 }\n param { lr_mult: 2 }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"drop6\"\n type: \"Dropout\"\n bottom: \"fc6\"\n top: \"fc6\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param { lr_mult: 1 }\n param { lr_mult: 2 }\n inner_product_param {\n num_output: 1024\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"drop7\"\n type: \"Dropout\"\n bottom: \"fc7\"\n top: \"fc7\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param { lr_mult: 1 }\n param { lr_mult: 2 }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param { lr_mult: 1 }\n param { lr_mult: 2 }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"loss_bbox\"\n loss_weight: 1\n}\n\n#========= RPN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"conv5\"\n top: \"rpn/output\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"silence_rpn_cls_score\"\n type: \"Silence\"\n bottom: \"rpn_cls_score\"\n}\nlayer {\n name: \"silence_rpn_bbox_pred\"\n type: \"Silence\"\n bottom: \"rpn_bbox_pred\"\n}\n" }, { "path": "models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_alt_opt/stage1_rpn_solver60k80k.pt", "content": "train_net: \"models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_alt_opt/stage1_rpn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 60000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"vgg_cnn_m_1024_rpn\"\n" }, { "path": "models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_alt_opt/stage1_rpn_train.pt", "content": "name: \"VGG_CNN_M_1024\"\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\nlayer {\n name: \"conv1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 96\n kernel_size: 7 stride: 2\n }\n}\nlayer {\n name: \"relu1\"\n type: \"ReLU\"\n bottom: \"conv1\"\n top: \"conv1\"\n}\nlayer {\n name: \"norm1\"\n type: \"LRN\"\n bottom: \"conv1\"\n top: \"norm1\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"norm1\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 3 stride: 2\n }\n}\nlayer {\n name: \"conv2\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2\"\n param { lr_mult: 1 }\n param { lr_mult: 2 }\n convolution_param {\n num_output: 256\n pad: 1 kernel_size: 5 stride: 2\n }\n}\nlayer {\n name: \"relu2\"\n type: \"ReLU\"\n bottom: \"conv2\"\n top: \"conv2\"\n}\nlayer {\n name: \"norm2\"\n type: \"LRN\"\n bottom: \"conv2\"\n top: \"norm2\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"norm2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 3 stride: 2\n }\n}\nlayer {\n name: \"conv3\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3\"\n param { lr_mult: 1 }\n param { lr_mult: 2 }\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu3\"\n type: \"ReLU\"\n bottom: \"conv3\"\n top: \"conv3\"\n}\nlayer {\n name: \"conv4\"\n type: \"Convolution\"\n bottom: \"conv3\"\n top: \"conv4\"\n param { lr_mult: 1 }\n param { lr_mult: 2 }\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu4\"\n type: \"ReLU\"\n bottom: \"conv4\"\n top: \"conv4\"\n}\nlayer {\n name: \"conv5\"\n type: \"Convolution\"\n bottom: \"conv4\"\n top: \"conv5\"\n param { lr_mult: 1 }\n param { lr_mult: 2 }\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu5\"\n type: \"ReLU\"\n bottom: \"conv5\"\n top: \"conv5\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"conv5\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RCNN ============\n\nlayer {\n name: \"dummy_roi_pool_conv5\"\n type: \"DummyData\"\n top: \"dummy_roi_pool_conv5\"\n dummy_data_param {\n shape { dim: 1 dim: 18432 }\n data_filler { type: \"gaussian\" std: 0.01 }\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"dummy_roi_pool_conv5\"\n top: \"fc6\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n inner_product_param {\n num_output: 1024\n }\n}\nlayer {\n name: \"silence_fc7\"\n type: \"Silence\"\n bottom: \"fc7\"\n}\n" }, { "path": "models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_alt_opt/stage2_fast_rcnn_solver30k40k.pt", "content": "train_net: \"models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_alt_opt/stage2_fast_rcnn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 30000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"vgg_cnn_m_1024_fast_rcnn\"\n" }, { "path": "models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_alt_opt/stage2_fast_rcnn_train.pt", "content": "name: \"VGG_CNN_M_1024\"\nlayer {\n name: 'data'\n type: 'Python'\n top: 'data'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\nlayer {\n name: \"conv1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 96\n kernel_size: 7 stride: 2\n }\n}\nlayer {\n name: \"relu1\"\n type: \"ReLU\"\n bottom: \"conv1\"\n top: \"conv1\"\n}\nlayer {\n name: \"norm1\"\n type: \"LRN\"\n bottom: \"conv1\"\n top: \"norm1\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"norm1\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 3 stride: 2\n }\n}\nlayer {\n name: \"conv2\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 256\n pad: 1 kernel_size: 5 stride: 2\n }\n}\nlayer {\n name: \"relu2\"\n type: \"ReLU\"\n bottom: \"conv2\"\n top: \"conv2\"\n}\nlayer {\n name: \"norm2\"\n type: \"LRN\"\n bottom: \"conv2\"\n top: \"norm2\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"norm2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 3 stride: 2\n }\n}\nlayer {\n name: \"conv3\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu3\"\n type: \"ReLU\"\n bottom: \"conv3\"\n top: \"conv3\"\n}\nlayer {\n name: \"conv4\"\n type: \"Convolution\"\n bottom: \"conv3\"\n top: \"conv4\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu4\"\n type: \"ReLU\"\n bottom: \"conv4\"\n top: \"conv4\"\n}\nlayer {\n name: \"conv5\"\n type: \"Convolution\"\n bottom: \"conv4\"\n top: \"conv5\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu5\"\n type: \"ReLU\"\n bottom: \"conv5\"\n top: \"conv5\"\n}\n\n#========= RCNN ============\n\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"conv5\"\n bottom: \"rois\"\n top: \"pool5\"\n roi_pooling_param {\n pooled_w: 6\n pooled_h: 6\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"fc6\"\n param { lr_mult: 1 }\n param { lr_mult: 2 }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"drop6\"\n type: \"Dropout\"\n bottom: \"fc6\"\n top: \"fc6\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param { lr_mult: 1 }\n param { lr_mult: 2 }\n inner_product_param {\n num_output: 1024\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"drop7\"\n type: \"Dropout\"\n bottom: \"fc7\"\n top: \"fc7\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param { lr_mult: 1 }\n param { lr_mult: 2 }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param { lr_mult: 1 }\n param { lr_mult: 2 }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"loss_bbox\"\n loss_weight: 1\n}\n\n#========= RPN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"conv5\"\n top: \"rpn/output\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"silence_rpn_cls_score\"\n type: \"Silence\"\n bottom: \"rpn_cls_score\"\n}\nlayer {\n name: \"silence_rpn_bbox_pred\"\n type: \"Silence\"\n bottom: \"rpn_bbox_pred\"\n}\n" }, { "path": "models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_alt_opt/stage2_rpn_solver60k80k.pt", "content": "train_net: \"models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_alt_opt/stage2_rpn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 60000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"vgg_cnn_m_1024_rpn\"\n" }, { "path": "models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_alt_opt/stage2_rpn_train.pt", "content": "name: \"VGG_CNN_M_1024\"\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\nlayer {\n name: \"conv1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 96\n kernel_size: 7 stride: 2\n }\n}\nlayer {\n name: \"relu1\"\n type: \"ReLU\"\n bottom: \"conv1\"\n top: \"conv1\"\n}\nlayer {\n name: \"norm1\"\n type: \"LRN\"\n bottom: \"conv1\"\n top: \"norm1\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"norm1\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 3 stride: 2\n }\n}\nlayer {\n name: \"conv2\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 256\n pad: 1 kernel_size: 5 stride: 2\n }\n}\nlayer {\n name: \"relu2\"\n type: \"ReLU\"\n bottom: \"conv2\"\n top: \"conv2\"\n}\nlayer {\n name: \"norm2\"\n type: \"LRN\"\n bottom: \"conv2\"\n top: \"norm2\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"norm2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 3 stride: 2\n }\n}\nlayer {\n name: \"conv3\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu3\"\n type: \"ReLU\"\n bottom: \"conv3\"\n top: \"conv3\"\n}\nlayer {\n name: \"conv4\"\n type: \"Convolution\"\n bottom: \"conv3\"\n top: \"conv4\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu4\"\n type: \"ReLU\"\n bottom: \"conv4\"\n top: \"conv4\"\n}\nlayer {\n name: \"conv5\"\n type: \"Convolution\"\n bottom: \"conv4\"\n top: \"conv5\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 512\n pad: 1 kernel_size: 3\n }\n}\nlayer {\n name: \"relu5\"\n type: \"ReLU\"\n bottom: \"conv5\"\n top: \"conv5\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"conv5\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RCNN ============\n\nlayer {\n name: \"dummy_roi_pool_conv5\"\n type: \"DummyData\"\n top: \"dummy_roi_pool_conv5\"\n dummy_data_param {\n shape { dim: 1 dim: 18432 }\n data_filler { type: \"gaussian\" std: 0.01 }\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"dummy_roi_pool_conv5\"\n top: \"fc6\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n inner_product_param {\n num_output: 1024\n }\n}\nlayer {\n name: \"silence_fc7\"\n type: \"Silence\"\n bottom: \"fc7\"\n}\n" }, { "path": "models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_end2end/solver.prototxt", "content": "train_net: \"models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_end2end/train.prototxt\"\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 50000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"vgg_cnn_m_1024_faster_rcnn\"\n" }, { "path": "models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_end2end/test.prototxt", "content": "name: \"VGG_CNN_M_1024\"\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\ninput: \"im_info\"\ninput_shape {\n dim: 1\n dim: 3\n}\nlayer {\n name: \"conv1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 96\n kernel_size: 7\n stride: 2\n }\n}\nlayer {\n name: \"relu1\"\n type: \"ReLU\"\n bottom: \"conv1\"\n top: \"conv1\"\n}\nlayer {\n name: \"norm1\"\n type: \"LRN\"\n bottom: \"conv1\"\n top: \"norm1\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"norm1\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 3\n stride: 2\n }\n}\nlayer {\n name: \"conv2\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 5\n stride: 2\n }\n}\nlayer {\n name: \"relu2\"\n type: \"ReLU\"\n bottom: \"conv2\"\n top: \"conv2\"\n}\nlayer {\n name: \"norm2\"\n type: \"LRN\"\n bottom: \"conv2\"\n top: \"norm2\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"norm2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 3\n stride: 2\n }\n}\nlayer {\n name: \"conv3\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3\"\n type: \"ReLU\"\n bottom: \"conv3\"\n top: \"conv3\"\n}\nlayer {\n name: \"conv4\"\n type: \"Convolution\"\n bottom: \"conv3\"\n top: \"conv4\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4\"\n type: \"ReLU\"\n bottom: \"conv4\"\n top: \"conv4\"\n}\nlayer {\n name: \"conv5\"\n type: \"Convolution\"\n bottom: \"conv4\"\n top: \"conv5\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5\"\n type: \"ReLU\"\n bottom: \"conv5\"\n top: \"conv5\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"conv5\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 decay_mult: 1.0 }\n param { lr_mult: 2.0 decay_mult: 0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\n#layer {\n# name: \"rpn_conv/3x3\"\n# type: \"Convolution\"\n# bottom: \"conv5\"\n# top: \"rpn_conv/3x3\"\n# param { lr_mult: 1.0 decay_mult: 1.0 }\n# param { lr_mult: 2.0 decay_mult: 0 }\n# convolution_param {\n# num_output: 192\n# kernel_size: 3 pad: 1 stride: 1\n# weight_filler { type: \"gaussian\" std: 0.01 }\n# bias_filler { type: \"constant\" value: 0 }\n# }\n#}\n#layer {\n# name: \"rpn_conv/5x5\"\n# type: \"Convolution\"\n# bottom: \"conv5\"\n# top: \"rpn_conv/5x5\"\n# param { lr_mult: 1.0 decay_mult: 1.0 }\n# param { lr_mult: 2.0 decay_mult: 0 }\n# convolution_param {\n# num_output: 64\n# kernel_size: 5 pad: 2 stride: 1\n# weight_filler { type: \"gaussian\" std: 0.0036 }\n# bias_filler { type: \"constant\" value: 0 }\n# }\n#}\n#layer {\n# name: \"rpn/output\"\n# type: \"Concat\"\n# bottom: \"rpn_conv/3x3\"\n# bottom: \"rpn_conv/5x5\"\n# top: \"rpn/output\"\n#}\n#layer {\n# name: \"rpn_relu/output\"\n# type: \"ReLU\"\n# bottom: \"rpn/output\"\n# top: \"rpn/output\"\n#}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 decay_mult: 1.0 }\n param { lr_mult: 2.0 decay_mult: 0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 decay_mult: 1.0 }\n param { lr_mult: 2.0 decay_mult: 0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rois'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n#========= RCNN ============\n\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"conv5\"\n bottom: \"rois\"\n top: \"pool5\"\n roi_pooling_param {\n pooled_w: 6\n pooled_h: 6\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"fc6\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"drop6\"\n type: \"Dropout\"\n bottom: \"fc6\"\n top: \"fc6\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 1024\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"drop7\"\n type: \"Dropout\"\n bottom: \"fc7\"\n top: \"fc7\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n decay_mult: 1\n }\n param {\n lr_mult: 2\n decay_mult: 0\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"cls_prob\"\n type: \"Softmax\"\n bottom: \"cls_score\"\n top: \"cls_prob\"\n}\n" }, { "path": "models/pascal_voc/VGG_CNN_M_1024/faster_rcnn_end2end/train.prototxt", "content": "name: \"VGG_CNN_M_1024\"\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\nlayer {\n name: \"conv1\"\n type: \"Convolution\"\n bottom: \"data\"\n top: \"conv1\"\n param {\n lr_mult: 0\n decay_mult: 0\n }\n param {\n lr_mult: 0\n decay_mult: 0\n }\n convolution_param {\n num_output: 96\n kernel_size: 7\n stride: 2\n }\n}\nlayer {\n name: \"relu1\"\n type: \"ReLU\"\n bottom: \"conv1\"\n top: \"conv1\"\n}\nlayer {\n name: \"norm1\"\n type: \"LRN\"\n bottom: \"conv1\"\n top: \"norm1\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool1\"\n type: \"Pooling\"\n bottom: \"norm1\"\n top: \"pool1\"\n pooling_param {\n pool: MAX\n kernel_size: 3\n stride: 2\n }\n}\nlayer {\n name: \"conv2\"\n type: \"Convolution\"\n bottom: \"pool1\"\n top: \"conv2\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 256\n pad: 1\n kernel_size: 5\n stride: 2\n }\n}\nlayer {\n name: \"relu2\"\n type: \"ReLU\"\n bottom: \"conv2\"\n top: \"conv2\"\n}\nlayer {\n name: \"norm2\"\n type: \"LRN\"\n bottom: \"conv2\"\n top: \"norm2\"\n lrn_param {\n local_size: 5\n alpha: 0.0005\n beta: 0.75\n k: 2\n }\n}\nlayer {\n name: \"pool2\"\n type: \"Pooling\"\n bottom: \"norm2\"\n top: \"pool2\"\n pooling_param {\n pool: MAX\n kernel_size: 3\n stride: 2\n }\n}\nlayer {\n name: \"conv3\"\n type: \"Convolution\"\n bottom: \"pool2\"\n top: \"conv3\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu3\"\n type: \"ReLU\"\n bottom: \"conv3\"\n top: \"conv3\"\n}\nlayer {\n name: \"conv4\"\n type: \"Convolution\"\n bottom: \"conv3\"\n top: \"conv4\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu4\"\n type: \"ReLU\"\n bottom: \"conv4\"\n top: \"conv4\"\n}\nlayer {\n name: \"conv5\"\n type: \"Convolution\"\n bottom: \"conv4\"\n top: \"conv5\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n convolution_param {\n num_output: 512\n pad: 1\n kernel_size: 3\n }\n}\nlayer {\n name: \"relu5\"\n type: \"ReLU\"\n bottom: \"conv5\"\n top: \"conv5\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"conv5\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\n\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\n\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\n\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rpn_rois'\n# top: 'rpn_scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n#layer {\n# name: 'debug-data'\n# type: 'Python'\n# bottom: 'data'\n# bottom: 'rpn_rois'\n# bottom: 'rpn_scores'\n# python_param {\n# module: 'rpn.debug_layer'\n# layer: 'RPNDebugLayer'\n# }\n#}\n\nlayer {\n name: 'roi-data'\n type: 'Python'\n bottom: 'rpn_rois'\n bottom: 'gt_boxes'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'rpn.proposal_target_layer'\n layer: 'ProposalTargetLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n#========= RCNN ============\n\nlayer {\n name: \"roi_pool5\"\n type: \"ROIPooling\"\n bottom: \"conv5\"\n bottom: \"rois\"\n top: \"pool5\"\n roi_pooling_param {\n pooled_w: 6\n pooled_h: 6\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"pool5\"\n top: \"fc6\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"drop6\"\n type: \"Dropout\"\n bottom: \"fc6\"\n top: \"fc6\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 1024\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"drop7\"\n type: \"Dropout\"\n bottom: \"fc7\"\n top: \"fc7\"\n dropout_param {\n dropout_ratio: 0.5\n }\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param {\n lr_mult: 1\n }\n param {\n lr_mult: 2\n }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"loss_cls\"\n loss_weight: 1\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"loss_bbox\"\n loss_weight: 1\n}\n" }, { "path": "models/pascal_voc/ZF/fast_rcnn/solver.prototxt", "content": "train_net: \"models/pascal_voc/ZF/fast_rcnn/train.prototxt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 30000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"zf_fast_rcnn\"\n#debug_info: true\n#iter_size: 2\n" }, { "path": "models/pascal_voc/ZF/fast_rcnn/test.prototxt", "content": "name: \"ZF\"\n\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\n\ninput: \"rois\"\ninput_shape {\n dim: 1 # to be changed on-the-fly to num ROIs\n dim: 5 # [batch ind, x1, y1, x2, y2] zero-based indexing\n}\n\n#========= conv1-conv5 ============\n\nlayer {\n\tname: \"conv1\"\n\ttype: \"Convolution\"\n\tbottom: \"data\"\n\ttop: \"conv1\"\n\tconvolution_param {\n\t\tnum_output: 96\n\t\tkernel_size: 7\n\t\tpad: 3\n\t\tstride: 2\n\t}\n}\nlayer {\n\tname: \"relu1\"\n\ttype: \"ReLU\"\n\tbottom: \"conv1\"\n\ttop: \"conv1\"\n}\nlayer {\n\tname: \"norm1\"\n\ttype: \"LRN\"\n\tbottom: \"conv1\"\n\ttop: \"norm1\"\n\tlrn_param {\n\t\tlocal_size: 3\n\t\talpha: 0.00005\n\t\tbeta: 0.75\n\t\tnorm_region: WITHIN_CHANNEL\n engine: CAFFE\n\t}\n}\nlayer {\n\tname: \"pool1\"\n\ttype: \"Pooling\"\n\tbottom: \"norm1\"\n\ttop: \"pool1\"\n\tpooling_param {\n\t\tkernel_size: 3\n\t\tstride: 2\n\t\tpad: 1\n\t\tpool: MAX\n\t}\n}\nlayer {\n\tname: \"conv2\"\n\ttype: \"Convolution\"\n\tbottom: \"pool1\"\n\ttop: \"conv2\"\n\tconvolution_param {\n\t\tnum_output: 256\n\t\tkernel_size: 5\n\t\tpad: 2\n\t\tstride: 2\n\t}\n}\nlayer {\n\tname: \"relu2\"\n\ttype: \"ReLU\"\n\tbottom: \"conv2\"\n\ttop: \"conv2\"\n}\nlayer {\n\tname: \"norm2\"\n\ttype: \"LRN\"\n\tbottom: \"conv2\"\n\ttop: \"norm2\"\n\tlrn_param {\n\t\tlocal_size: 3\n\t\talpha: 0.00005\n\t\tbeta: 0.75\n\t\tnorm_region: WITHIN_CHANNEL\n engine: CAFFE\n\t}\n}\nlayer {\n\tname: \"pool2\"\n\ttype: \"Pooling\"\n\tbottom: \"norm2\"\n\ttop: \"pool2\"\n\tpooling_param {\n\t\tkernel_size: 3\n\t\tstride: 2\n\t\tpad: 1\n\t\tpool: MAX\n\t}\n}\nlayer {\n\tname: \"conv3\"\n\ttype: \"Convolution\"\n\tbottom: \"pool2\"\n\ttop: \"conv3\"\n\tconvolution_param {\n\t\tnum_output: 384\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu3\"\n\ttype: \"ReLU\"\n\tbottom: \"conv3\"\n\ttop: \"conv3\"\n}\nlayer {\n\tname: \"conv4\"\n\ttype: \"Convolution\"\n\tbottom: \"conv3\"\n\ttop: \"conv4\"\n\tconvolution_param {\n\t\tnum_output: 384\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu4\"\n\ttype: \"ReLU\"\n\tbottom: \"conv4\"\n\ttop: \"conv4\"\n}\nlayer {\n\tname: \"conv5\"\n\ttype: \"Convolution\"\n\tbottom: \"conv4\"\n\ttop: \"conv5\"\n\tconvolution_param {\n\t\tnum_output: 256\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu5\"\n\ttype: \"ReLU\"\n\tbottom: \"conv5\"\n\ttop: \"conv5\"\n}\n\n#========= RCNN ============\n\nlayer {\n name: \"roi_pool_conv5\"\n type: \"ROIPooling\"\n bottom: \"conv5\"\n bottom: \"rois\"\n top: \"roi_pool_conv5\"\n roi_pooling_param {\n pooled_w: 6\n pooled_h: 6\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"roi_pool_conv5\"\n top: \"fc6\"\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"drop6\"\n type: \"Dropout\"\n bottom: \"fc6\"\n top: \"fc6\"\n dropout_param {\n dropout_ratio: 0.5\n scale_train: false\n }\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"drop7\"\n type: \"Dropout\"\n bottom: \"fc7\"\n top: \"fc7\"\n dropout_param {\n dropout_ratio: 0.5\n scale_train: false\n }\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n inner_product_param {\n num_output: 21\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n inner_product_param {\n num_output: 84\n }\n}\nlayer {\n name: \"cls_prob\"\n type: \"Softmax\"\n bottom: \"cls_score\"\n top: \"cls_prob\"\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n" }, { "path": "models/pascal_voc/ZF/fast_rcnn/train.prototxt", "content": "name: \"ZF\"\nlayer {\n name: 'data'\n type: 'Python'\n top: 'data'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n#========= conv1-conv5 ============\n\nlayer {\n\tname: \"conv1\"\n\ttype: \"Convolution\"\n\tbottom: \"data\"\n\ttop: \"conv1\"\n\tparam { lr_mult: 1.0 }\n\tparam { lr_mult: 2.0 }\n\tconvolution_param {\n\t\tnum_output: 96\n\t\tkernel_size: 7\n\t\tpad: 3\n\t\tstride: 2\n\t}\n}\nlayer {\n\tname: \"relu1\"\n\ttype: \"ReLU\"\n\tbottom: \"conv1\"\n\ttop: \"conv1\"\n}\nlayer {\n\tname: \"norm1\"\n\ttype: \"LRN\"\n\tbottom: \"conv1\"\n\ttop: \"norm1\"\n\tlrn_param {\n\t\tlocal_size: 3\n\t\talpha: 0.00005\n\t\tbeta: 0.75\n\t\tnorm_region: WITHIN_CHANNEL\n engine: CAFFE\n\t}\n}\nlayer {\n\tname: \"pool1\"\n\ttype: \"Pooling\"\n\tbottom: \"norm1\"\n\ttop: \"pool1\"\n\tpooling_param {\n\t\tkernel_size: 3\n\t\tstride: 2\n\t\tpad: 1\n\t\tpool: MAX\n\t}\n}\nlayer {\n\tname: \"conv2\"\n\ttype: \"Convolution\"\n\tbottom: \"pool1\"\n\ttop: \"conv2\"\n\tparam { lr_mult: 1.0 }\n\tparam { lr_mult: 2.0 }\n\tconvolution_param {\n\t\tnum_output: 256\n\t\tkernel_size: 5\n\t\tpad: 2\n\t\tstride: 2\n\t}\n}\nlayer {\n\tname: \"relu2\"\n\ttype: \"ReLU\"\n\tbottom: \"conv2\"\n\ttop: \"conv2\"\n}\nlayer {\n\tname: \"norm2\"\n\ttype: \"LRN\"\n\tbottom: \"conv2\"\n\ttop: \"norm2\"\n\tlrn_param {\n\t\tlocal_size: 3\n\t\talpha: 0.00005\n\t\tbeta: 0.75\n\t\tnorm_region: WITHIN_CHANNEL\n engine: CAFFE\n\t}\n}\nlayer {\n\tname: \"pool2\"\n\ttype: \"Pooling\"\n\tbottom: \"norm2\"\n\ttop: \"pool2\"\n\tpooling_param {\n\t\tkernel_size: 3\n\t\tstride: 2\n\t\tpad: 1\n\t\tpool: MAX\n\t}\n}\nlayer {\n\tname: \"conv3\"\n\ttype: \"Convolution\"\n\tbottom: \"pool2\"\n\ttop: \"conv3\"\n\tparam { lr_mult: 1.0 }\n\tparam { lr_mult: 2.0 }\n\tconvolution_param {\n\t\tnum_output: 384\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu3\"\n\ttype: \"ReLU\"\n\tbottom: \"conv3\"\n\ttop: \"conv3\"\n}\nlayer {\n\tname: \"conv4\"\n\ttype: \"Convolution\"\n\tbottom: \"conv3\"\n\ttop: \"conv4\"\n\tparam { lr_mult: 1.0 }\n\tparam { lr_mult: 2.0 }\n\tconvolution_param {\n\t\tnum_output: 384\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu4\"\n\ttype: \"ReLU\"\n\tbottom: \"conv4\"\n\ttop: \"conv4\"\n}\nlayer {\n\tname: \"conv5\"\n\ttype: \"Convolution\"\n\tbottom: \"conv4\"\n\ttop: \"conv5\"\n\tparam { lr_mult: 1.0 }\n\tparam { lr_mult: 2.0 }\n\tconvolution_param {\n\t\tnum_output: 256\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu5\"\n\ttype: \"ReLU\"\n\tbottom: \"conv5\"\n\ttop: \"conv5\"\n}\n\n#========= RCNN ============\n\nlayer {\n name: \"roi_pool_conv5\"\n type: \"ROIPooling\"\n bottom: \"conv5\"\n bottom: \"rois\"\n top: \"roi_pool_conv5\"\n roi_pooling_param {\n pooled_w: 6\n pooled_h: 6\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"roi_pool_conv5\"\n top: \"fc6\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"drop6\"\n type: \"Dropout\"\n bottom: \"fc6\"\n top: \"fc6\"\n dropout_param {\n dropout_ratio: 0.5\n scale_train: false\n }\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"drop7\"\n type: \"Dropout\"\n bottom: \"fc7\"\n top: \"fc7\"\n dropout_param {\n dropout_ratio: 0.5\n scale_train: false\n }\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"bbox_loss\"\n loss_weight: 1\n}\n" }, { "path": "models/pascal_voc/ZF/faster_rcnn_alt_opt/faster_rcnn_test.pt", "content": "name: \"ZF\"\n\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\n\ninput: \"im_info\"\ninput_shape {\n dim: 1\n dim: 3\n}\n\n#========= conv1-conv5 ============\n\nlayer {\n\tname: \"conv1\"\n\ttype: \"Convolution\"\n\tbottom: \"data\"\n\ttop: \"conv1\"\n\tconvolution_param {\n\t\tnum_output: 96\n\t\tkernel_size: 7\n\t\tpad: 3\n\t\tstride: 2\n\t}\n}\nlayer {\n\tname: \"relu1\"\n\ttype: \"ReLU\"\n\tbottom: \"conv1\"\n\ttop: \"conv1\"\n}\nlayer {\n\tname: \"norm1\"\n\ttype: \"LRN\"\n\tbottom: \"conv1\"\n\ttop: \"norm1\"\n\tlrn_param {\n\t\tlocal_size: 3\n\t\talpha: 0.00005\n\t\tbeta: 0.75\n\t\tnorm_region: WITHIN_CHANNEL\n engine: CAFFE\n\t}\n}\nlayer {\n\tname: \"pool1\"\n\ttype: \"Pooling\"\n\tbottom: \"norm1\"\n\ttop: \"pool1\"\n\tpooling_param {\n\t\tkernel_size: 3\n\t\tstride: 2\n\t\tpad: 1\n\t\tpool: MAX\n\t}\n}\nlayer {\n\tname: \"conv2\"\n\ttype: \"Convolution\"\n\tbottom: \"pool1\"\n\ttop: \"conv2\"\n\tconvolution_param {\n\t\tnum_output: 256\n\t\tkernel_size: 5\n\t\tpad: 2\n\t\tstride: 2\n\t}\n}\nlayer {\n\tname: \"relu2\"\n\ttype: \"ReLU\"\n\tbottom: \"conv2\"\n\ttop: \"conv2\"\n}\nlayer {\n\tname: \"norm2\"\n\ttype: \"LRN\"\n\tbottom: \"conv2\"\n\ttop: \"norm2\"\n\tlrn_param {\n\t\tlocal_size: 3\n\t\talpha: 0.00005\n\t\tbeta: 0.75\n\t\tnorm_region: WITHIN_CHANNEL\n engine: CAFFE\n\t}\n}\nlayer {\n\tname: \"pool2\"\n\ttype: \"Pooling\"\n\tbottom: \"norm2\"\n\ttop: \"pool2\"\n\tpooling_param {\n\t\tkernel_size: 3\n\t\tstride: 2\n\t\tpad: 1\n\t\tpool: MAX\n\t}\n}\nlayer {\n\tname: \"conv3\"\n\ttype: \"Convolution\"\n\tbottom: \"pool2\"\n\ttop: \"conv3\"\n\tconvolution_param {\n\t\tnum_output: 384\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu3\"\n\ttype: \"ReLU\"\n\tbottom: \"conv3\"\n\ttop: \"conv3\"\n}\nlayer {\n\tname: \"conv4\"\n\ttype: \"Convolution\"\n\tbottom: \"conv3\"\n\ttop: \"conv4\"\n\tconvolution_param {\n\t\tnum_output: 384\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu4\"\n\ttype: \"ReLU\"\n\tbottom: \"conv4\"\n\ttop: \"conv4\"\n}\nlayer {\n\tname: \"conv5\"\n\ttype: \"Convolution\"\n\tbottom: \"conv4\"\n\ttop: \"conv5\"\n\tconvolution_param {\n\t\tnum_output: 256\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu5\"\n\ttype: \"ReLU\"\n\tbottom: \"conv5\"\n\ttop: \"conv5\"\n}\n\n#========= RPN ============\n\n\nlayer {\n name: \"rpn_conv1\"\n type: \"Convolution\"\n bottom: \"conv5\"\n top: \"rpn_conv1\"\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n }\n}\nlayer {\n name: \"rpn_relu1\"\n type: \"ReLU\"\n bottom: \"rpn_conv1\"\n top: \"rpn_conv1\"\n}\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn_conv1\"\n top: \"rpn_cls_score\"\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn_conv1\"\n top: \"rpn_bbox_pred\"\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n }\n}\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rois'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n#========= RCNN ============\n\nlayer {\n name: \"roi_pool_conv5\"\n type: \"ROIPooling\"\n bottom: \"conv5\"\n bottom: \"rois\"\n top: \"roi_pool_conv5\"\n roi_pooling_param {\n pooled_w: 6\n pooled_h: 6\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"roi_pool_conv5\"\n top: \"fc6\"\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"drop6\"\n type: \"Dropout\"\n bottom: \"fc6\"\n top: \"fc6\"\n dropout_param {\n dropout_ratio: 0.5\n scale_train: false\n }\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"drop7\"\n type: \"Dropout\"\n bottom: \"fc7\"\n top: \"fc7\"\n dropout_param {\n dropout_ratio: 0.5\n scale_train: false\n }\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n inner_product_param {\n num_output: 21\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n inner_product_param {\n num_output: 84\n }\n}\nlayer {\n name: \"cls_prob\"\n type: \"Softmax\"\n bottom: \"cls_score\"\n top: \"cls_prob\"\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n" }, { "path": "models/pascal_voc/ZF/faster_rcnn_alt_opt/rpn_test.pt", "content": "name: \"ZF\"\n\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\n\ninput: \"im_info\"\ninput_shape {\n dim: 1\n dim: 3\n}\n\n# ------------------------ layer 1 -----------------------------\nlayer {\n\tname: \"conv1\"\n\ttype: \"Convolution\"\n\tbottom: \"data\"\n\ttop: \"conv1\"\n\tconvolution_param {\n\t\tnum_output: 96\n\t\tkernel_size: 7\n\t\tpad: 3\n\t\tstride: 2\n\t}\n}\nlayer {\n\tname: \"relu1\"\n\ttype: \"ReLU\"\n\tbottom: \"conv1\"\n\ttop: \"conv1\"\n}\nlayer {\n\tname: \"norm1\"\n\ttype: \"LRN\"\n\tbottom: \"conv1\"\n\ttop: \"norm1\"\n\tlrn_param {\n\t\tlocal_size: 3\n\t\talpha: 0.00005\n\t\tbeta: 0.75\n\t\tnorm_region: WITHIN_CHANNEL\n engine: CAFFE\n\t}\n}\nlayer {\n\tname: \"pool1\"\n\ttype: \"Pooling\"\n\tbottom: \"norm1\"\n\ttop: \"pool1\"\n\tpooling_param {\n\t\tkernel_size: 3\n\t\tstride: 2\n\t\tpad: 1\n\t\tpool: MAX\n\t}\n}\nlayer {\n\tname: \"conv2\"\n\ttype: \"Convolution\"\n\tbottom: \"pool1\"\n\ttop: \"conv2\"\n\tconvolution_param {\n\t\tnum_output: 256\n\t\tkernel_size: 5\n\t\tpad: 2\n\t\tstride: 2\n\t}\n}\nlayer {\n\tname: \"relu2\"\n\ttype: \"ReLU\"\n\tbottom: \"conv2\"\n\ttop: \"conv2\"\n}\n\nlayer {\n\tname: \"norm2\"\n\ttype: \"LRN\"\n\tbottom: \"conv2\"\n\ttop: \"norm2\"\n\tlrn_param {\n\t\tlocal_size: 3\n\t\talpha: 0.00005\n\t\tbeta: 0.75\n\t\tnorm_region: WITHIN_CHANNEL\n engine: CAFFE\n\t}\n}\nlayer {\n\tname: \"pool2\"\n\ttype: \"Pooling\"\n\tbottom: \"norm2\"\n\ttop: \"pool2\"\n\tpooling_param {\n\t\tkernel_size: 3\n\t\tstride: 2\n\t\tpad: 1\n\t\tpool: MAX\n\t}\n}\nlayer {\n\tname: \"conv3\"\n\ttype: \"Convolution\"\n\tbottom: \"pool2\"\n\ttop: \"conv3\"\n\tconvolution_param {\n\t\tnum_output: 384\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu3\"\n\ttype: \"ReLU\"\n\tbottom: \"conv3\"\n\ttop: \"conv3\"\n}\nlayer {\n\tname: \"conv4\"\n\ttype: \"Convolution\"\n\tbottom: \"conv3\"\n\ttop: \"conv4\"\n\tconvolution_param {\n\t\tnum_output: 384\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu4\"\n\ttype: \"ReLU\"\n\tbottom: \"conv4\"\n\ttop: \"conv4\"\n}\nlayer {\n\tname: \"conv5\"\n\ttype: \"Convolution\"\n\tbottom: \"conv4\"\n\ttop: \"conv5\"\n\tconvolution_param {\n\t\tnum_output: 256\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu5\"\n\ttype: \"ReLU\"\n\tbottom: \"conv5\"\n\ttop: \"conv5\"\n}\n\n#-----------------------layer +-------------------------\n\nlayer {\n name: \"rpn_conv1\"\n type: \"Convolution\"\n bottom: \"conv5\"\n top: \"rpn_conv1\"\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n }\n}\nlayer {\n name: \"rpn_relu1\"\n type: \"ReLU\"\n bottom: \"rpn_conv1\"\n top: \"rpn_conv1\"\n}\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn_conv1\"\n top: \"rpn_cls_score\"\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn_conv1\"\n top: \"rpn_bbox_pred\"\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n }\n}\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\n#-----------------------output------------------------\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rois'\n top: 'scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n" }, { "path": "models/pascal_voc/ZF/faster_rcnn_alt_opt/stage1_fast_rcnn_solver30k40k.pt", "content": "train_net: \"models/pascal_voc/ZF/faster_rcnn_alt_opt/stage1_fast_rcnn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 30000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"zf_fast_rcnn\"\n" }, { "path": "models/pascal_voc/ZF/faster_rcnn_alt_opt/stage1_fast_rcnn_train.pt", "content": "name: \"ZF\"\nlayer {\n name: 'data'\n type: 'Python'\n top: 'data'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n#========= conv1-conv5 ============\n\nlayer {\n\tname: \"conv1\"\n\ttype: \"Convolution\"\n\tbottom: \"data\"\n\ttop: \"conv1\"\n\tparam { lr_mult: 1.0 }\n\tparam { lr_mult: 2.0 }\n\tconvolution_param {\n\t\tnum_output: 96\n\t\tkernel_size: 7\n\t\tpad: 3\n\t\tstride: 2\n\t}\n}\nlayer {\n\tname: \"relu1\"\n\ttype: \"ReLU\"\n\tbottom: \"conv1\"\n\ttop: \"conv1\"\n}\nlayer {\n\tname: \"norm1\"\n\ttype: \"LRN\"\n\tbottom: \"conv1\"\n\ttop: \"norm1\"\n\tlrn_param {\n\t\tlocal_size: 3\n\t\talpha: 0.00005\n\t\tbeta: 0.75\n\t\tnorm_region: WITHIN_CHANNEL\n engine: CAFFE\n\t}\n}\nlayer {\n\tname: \"pool1\"\n\ttype: \"Pooling\"\n\tbottom: \"norm1\"\n\ttop: \"pool1\"\n\tpooling_param {\n\t\tkernel_size: 3\n\t\tstride: 2\n\t\tpad: 1\n\t\tpool: MAX\n\t}\n}\nlayer {\n\tname: \"conv2\"\n\ttype: \"Convolution\"\n\tbottom: \"pool1\"\n\ttop: \"conv2\"\n\tparam { lr_mult: 1.0 }\n\tparam { lr_mult: 2.0 }\n\tconvolution_param {\n\t\tnum_output: 256\n\t\tkernel_size: 5\n\t\tpad: 2\n\t\tstride: 2\n\t}\n}\nlayer {\n\tname: \"relu2\"\n\ttype: \"ReLU\"\n\tbottom: \"conv2\"\n\ttop: \"conv2\"\n}\nlayer {\n\tname: \"norm2\"\n\ttype: \"LRN\"\n\tbottom: \"conv2\"\n\ttop: \"norm2\"\n\tlrn_param {\n\t\tlocal_size: 3\n\t\talpha: 0.00005\n\t\tbeta: 0.75\n\t\tnorm_region: WITHIN_CHANNEL\n engine: CAFFE\n\t}\n}\nlayer {\n\tname: \"pool2\"\n\ttype: \"Pooling\"\n\tbottom: \"norm2\"\n\ttop: \"pool2\"\n\tpooling_param {\n\t\tkernel_size: 3\n\t\tstride: 2\n\t\tpad: 1\n\t\tpool: MAX\n\t}\n}\nlayer {\n\tname: \"conv3\"\n\ttype: \"Convolution\"\n\tbottom: \"pool2\"\n\ttop: \"conv3\"\n\tparam { lr_mult: 1.0 }\n\tparam { lr_mult: 2.0 }\n\tconvolution_param {\n\t\tnum_output: 384\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu3\"\n\ttype: \"ReLU\"\n\tbottom: \"conv3\"\n\ttop: \"conv3\"\n}\nlayer {\n\tname: \"conv4\"\n\ttype: \"Convolution\"\n\tbottom: \"conv3\"\n\ttop: \"conv4\"\n\tparam { lr_mult: 1.0 }\n\tparam { lr_mult: 2.0 }\n\tconvolution_param {\n\t\tnum_output: 384\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu4\"\n\ttype: \"ReLU\"\n\tbottom: \"conv4\"\n\ttop: \"conv4\"\n}\nlayer {\n\tname: \"conv5\"\n\ttype: \"Convolution\"\n\tbottom: \"conv4\"\n\ttop: \"conv5\"\n\tparam { lr_mult: 1.0 }\n\tparam { lr_mult: 2.0 }\n\tconvolution_param {\n\t\tnum_output: 256\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu5\"\n\ttype: \"ReLU\"\n\tbottom: \"conv5\"\n\ttop: \"conv5\"\n}\n\n#========= RCNN ============\n\nlayer {\n name: \"roi_pool_conv5\"\n type: \"ROIPooling\"\n bottom: \"conv5\"\n bottom: \"rois\"\n top: \"roi_pool_conv5\"\n roi_pooling_param {\n pooled_w: 6\n pooled_h: 6\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"roi_pool_conv5\"\n top: \"fc6\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"drop6\"\n type: \"Dropout\"\n bottom: \"fc6\"\n top: \"fc6\"\n dropout_param {\n dropout_ratio: 0.5\n scale_train: false\n }\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"drop7\"\n type: \"Dropout\"\n bottom: \"fc7\"\n top: \"fc7\"\n dropout_param {\n dropout_ratio: 0.5\n scale_train: false\n }\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"bbox_loss\"\n loss_weight: 1\n}\n\n#========= RPN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"rpn_conv1\"\n type: \"Convolution\"\n bottom: \"conv5\"\n top: \"rpn_conv1\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu1\"\n type: \"ReLU\"\n bottom: \"rpn_conv1\"\n top: \"rpn_conv1\"\n}\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn_conv1\"\n top: \"rpn_cls_score\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn_conv1\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"silence_rpn_cls_score\"\n type: \"Silence\"\n bottom: \"rpn_cls_score\"\n}\nlayer {\n name: \"silence_rpn_bbox_pred\"\n type: \"Silence\"\n bottom: \"rpn_bbox_pred\"\n}\n" }, { "path": "models/pascal_voc/ZF/faster_rcnn_alt_opt/stage1_rpn_solver60k80k.pt", "content": "train_net: \"models/pascal_voc/ZF/faster_rcnn_alt_opt/stage1_rpn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 60000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"zf_rpn\"\n" }, { "path": "models/pascal_voc/ZF/faster_rcnn_alt_opt/stage1_rpn_train.pt", "content": "name: \"ZF\"\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n#========= conv1-conv5 ============\n\nlayer {\n\tname: \"conv1\"\n\ttype: \"Convolution\"\n\tbottom: \"data\"\n\ttop: \"conv1\"\n\tparam { lr_mult: 1.0 }\n\tparam { lr_mult: 2.0 }\n\tconvolution_param {\n\t\tnum_output: 96\n\t\tkernel_size: 7\n\t\tpad: 3\n\t\tstride: 2\n\t}\n}\nlayer {\n\tname: \"relu1\"\n\ttype: \"ReLU\"\n\tbottom: \"conv1\"\n\ttop: \"conv1\"\n}\nlayer {\n\tname: \"norm1\"\n\ttype: \"LRN\"\n\tbottom: \"conv1\"\n\ttop: \"norm1\"\n\tlrn_param {\n\t\tlocal_size: 3\n\t\talpha: 0.00005\n\t\tbeta: 0.75\n\t\tnorm_region: WITHIN_CHANNEL\n engine: CAFFE\n\t}\n}\nlayer {\n\tname: \"pool1\"\n\ttype: \"Pooling\"\n\tbottom: \"norm1\"\n\ttop: \"pool1\"\n\tpooling_param {\n\t\tkernel_size: 3\n\t\tstride: 2\n\t\tpad: 1\n\t\tpool: MAX\n\t}\n}\nlayer {\n\tname: \"conv2\"\n\ttype: \"Convolution\"\n\tbottom: \"pool1\"\n\ttop: \"conv2\"\n\tparam { lr_mult: 1.0 }\n\tparam { lr_mult: 2.0 }\n\tconvolution_param {\n\t\tnum_output: 256\n\t\tkernel_size: 5\n\t\tpad: 2\n\t\tstride: 2\n\t}\n}\nlayer {\n\tname: \"relu2\"\n\ttype: \"ReLU\"\n\tbottom: \"conv2\"\n\ttop: \"conv2\"\n}\nlayer {\n\tname: \"norm2\"\n\ttype: \"LRN\"\n\tbottom: \"conv2\"\n\ttop: \"norm2\"\n\tlrn_param {\n\t\tlocal_size: 3\n\t\talpha: 0.00005\n\t\tbeta: 0.75\n\t\tnorm_region: WITHIN_CHANNEL\n engine: CAFFE\n\t}\n}\nlayer {\n\tname: \"pool2\"\n\ttype: \"Pooling\"\n\tbottom: \"norm2\"\n\ttop: \"pool2\"\n\tpooling_param {\n\t\tkernel_size: 3\n\t\tstride: 2\n\t\tpad: 1\n\t\tpool: MAX\n\t}\n}\nlayer {\n\tname: \"conv3\"\n\ttype: \"Convolution\"\n\tbottom: \"pool2\"\n\ttop: \"conv3\"\n\tparam { lr_mult: 1.0 }\n\tparam { lr_mult: 2.0 }\n\tconvolution_param {\n\t\tnum_output: 384\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu3\"\n\ttype: \"ReLU\"\n\tbottom: \"conv3\"\n\ttop: \"conv3\"\n}\nlayer {\n\tname: \"conv4\"\n\ttype: \"Convolution\"\n\tbottom: \"conv3\"\n\ttop: \"conv4\"\n\tparam { lr_mult: 1.0 }\n\tparam { lr_mult: 2.0 }\n\tconvolution_param {\n\t\tnum_output: 384\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu4\"\n\ttype: \"ReLU\"\n\tbottom: \"conv4\"\n\ttop: \"conv4\"\n}\nlayer {\n\tname: \"conv5\"\n\ttype: \"Convolution\"\n\tbottom: \"conv4\"\n\ttop: \"conv5\"\n\tparam { lr_mult: 1.0 }\n\tparam { lr_mult: 2.0 }\n\tconvolution_param {\n\t\tnum_output: 256\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu5\"\n\ttype: \"ReLU\"\n\tbottom: \"conv5\"\n\ttop: \"conv5\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv1\"\n type: \"Convolution\"\n bottom: \"conv5\"\n top: \"rpn_conv1\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu1\"\n type: \"ReLU\"\n bottom: \"rpn_conv1\"\n top: \"rpn_conv1\"\n}\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn_conv1\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn_conv1\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: \"rpn_bbox_inside_weights\"\n bottom: \"rpn_bbox_outside_weights\"\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RCNN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"dummy_roi_pool_conv5\"\n type: \"DummyData\"\n top: \"dummy_roi_pool_conv5\"\n dummy_data_param {\n shape { dim: 1 dim: 9216 }\n data_filler { type: \"gaussian\" std: 0.01 }\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"dummy_roi_pool_conv5\"\n top: \"fc6\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"silence_fc7\"\n type: \"Silence\"\n bottom: \"fc7\"\n}\n" }, { "path": "models/pascal_voc/ZF/faster_rcnn_alt_opt/stage2_fast_rcnn_solver30k40k.pt", "content": "train_net: \"models/pascal_voc/ZF/faster_rcnn_alt_opt/stage2_fast_rcnn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 30000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"zf_fast_rcnn\"\n" }, { "path": "models/pascal_voc/ZF/faster_rcnn_alt_opt/stage2_fast_rcnn_train.pt", "content": "name: \"ZF\"\nlayer {\n name: 'data'\n type: 'Python'\n top: 'data'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n#========= conv1-conv5 ============\n\nlayer {\n\tname: \"conv1\"\n\ttype: \"Convolution\"\n\tbottom: \"data\"\n\ttop: \"conv1\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n\tconvolution_param {\n\t\tnum_output: 96\n\t\tkernel_size: 7\n\t\tpad: 3\n\t\tstride: 2\n\t}\n}\nlayer {\n\tname: \"relu1\"\n\ttype: \"ReLU\"\n\tbottom: \"conv1\"\n\ttop: \"conv1\"\n}\nlayer {\n\tname: \"norm1\"\n\ttype: \"LRN\"\n\tbottom: \"conv1\"\n\ttop: \"norm1\"\n\tlrn_param {\n\t\tlocal_size: 3\n\t\talpha: 0.00005\n\t\tbeta: 0.75\n\t\tnorm_region: WITHIN_CHANNEL\n engine: CAFFE\n\t}\n}\nlayer {\n\tname: \"pool1\"\n\ttype: \"Pooling\"\n\tbottom: \"norm1\"\n\ttop: \"pool1\"\n\tpooling_param {\n\t\tkernel_size: 3\n\t\tstride: 2\n\t\tpad: 1\n\t\tpool: MAX\n\t}\n}\nlayer {\n\tname: \"conv2\"\n\ttype: \"Convolution\"\n\tbottom: \"pool1\"\n\ttop: \"conv2\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n\tconvolution_param {\n\t\tnum_output: 256\n\t\tkernel_size: 5\n\t\tpad: 2\n\t\tstride: 2\n\t}\n}\nlayer {\n\tname: \"relu2\"\n\ttype: \"ReLU\"\n\tbottom: \"conv2\"\n\ttop: \"conv2\"\n}\nlayer {\n\tname: \"norm2\"\n\ttype: \"LRN\"\n\tbottom: \"conv2\"\n\ttop: \"norm2\"\n\tlrn_param {\n\t\tlocal_size: 3\n\t\talpha: 0.00005\n\t\tbeta: 0.75\n\t\tnorm_region: WITHIN_CHANNEL\n engine: CAFFE\n\t}\n}\nlayer {\n\tname: \"pool2\"\n\ttype: \"Pooling\"\n\tbottom: \"norm2\"\n\ttop: \"pool2\"\n\tpooling_param {\n\t\tkernel_size: 3\n\t\tstride: 2\n\t\tpad: 1\n\t\tpool: MAX\n\t}\n}\nlayer {\n\tname: \"conv3\"\n\ttype: \"Convolution\"\n\tbottom: \"pool2\"\n\ttop: \"conv3\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n\tconvolution_param {\n\t\tnum_output: 384\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu3\"\n\ttype: \"ReLU\"\n\tbottom: \"conv3\"\n\ttop: \"conv3\"\n}\nlayer {\n\tname: \"conv4\"\n\ttype: \"Convolution\"\n\tbottom: \"conv3\"\n\ttop: \"conv4\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n\tconvolution_param {\n\t\tnum_output: 384\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu4\"\n\ttype: \"ReLU\"\n\tbottom: \"conv4\"\n\ttop: \"conv4\"\n}\nlayer {\n\tname: \"conv5\"\n\ttype: \"Convolution\"\n\tbottom: \"conv4\"\n\ttop: \"conv5\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n\tconvolution_param {\n\t\tnum_output: 256\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu5\"\n\ttype: \"ReLU\"\n\tbottom: \"conv5\"\n\ttop: \"conv5\"\n}\n\n#========= RCNN ============\n\nlayer {\n name: \"roi_pool_conv5\"\n type: \"ROIPooling\"\n bottom: \"conv5\"\n bottom: \"rois\"\n top: \"roi_pool_conv5\"\n roi_pooling_param {\n pooled_w: 6\n pooled_h: 6\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"roi_pool_conv5\"\n top: \"fc6\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"drop6\"\n type: \"Dropout\"\n bottom: \"fc6\"\n top: \"fc6\"\n dropout_param {\n dropout_ratio: 0.5\n scale_train: false\n }\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"drop7\"\n type: \"Dropout\"\n bottom: \"fc7\"\n top: \"fc7\"\n dropout_param {\n dropout_ratio: 0.5\n scale_train: false\n }\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: \"bbox_inside_weights\"\n bottom: \"bbox_outside_weights\"\n top: \"bbox_loss\"\n loss_weight: 1\n}\n\n#========= RPN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"rpn_conv1\"\n type: \"Convolution\"\n bottom: \"conv5\"\n top: \"rpn_conv1\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu1\"\n type: \"ReLU\"\n bottom: \"rpn_conv1\"\n top: \"rpn_conv1\"\n}\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn_conv1\"\n top: \"rpn_cls_score\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn_conv1\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"silence_rpn_cls_score\"\n type: \"Silence\"\n bottom: \"rpn_cls_score\"\n}\nlayer {\n name: \"silence_rpn_bbox_pred\"\n type: \"Silence\"\n bottom: \"rpn_bbox_pred\"\n}\n" }, { "path": "models/pascal_voc/ZF/faster_rcnn_alt_opt/stage2_rpn_solver60k80k.pt", "content": "train_net: \"models/pascal_voc/ZF/faster_rcnn_alt_opt/stage2_rpn_train.pt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 60000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"zf_rpn\"\n" }, { "path": "models/pascal_voc/ZF/faster_rcnn_alt_opt/stage2_rpn_train.pt", "content": "name: \"ZF\"\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n#========= conv1-conv5 ============\n\nlayer {\n\tname: \"conv1\"\n\ttype: \"Convolution\"\n\tbottom: \"data\"\n\ttop: \"conv1\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n\tconvolution_param {\n\t\tnum_output: 96\n\t\tkernel_size: 7\n\t\tpad: 3\n\t\tstride: 2\n\t}\n}\nlayer {\n\tname: \"relu1\"\n\ttype: \"ReLU\"\n\tbottom: \"conv1\"\n\ttop: \"conv1\"\n}\nlayer {\n\tname: \"norm1\"\n\ttype: \"LRN\"\n\tbottom: \"conv1\"\n\ttop: \"norm1\"\n\tlrn_param {\n\t\tlocal_size: 3\n\t\talpha: 0.00005\n\t\tbeta: 0.75\n\t\tnorm_region: WITHIN_CHANNEL\n engine: CAFFE\n\t}\n}\nlayer {\n\tname: \"pool1\"\n\ttype: \"Pooling\"\n\tbottom: \"norm1\"\n\ttop: \"pool1\"\n\tpooling_param {\n\t\tkernel_size: 3\n\t\tstride: 2\n\t\tpad: 1\n\t\tpool: MAX\n\t}\n}\nlayer {\n\tname: \"conv2\"\n\ttype: \"Convolution\"\n\tbottom: \"pool1\"\n\ttop: \"conv2\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n\tconvolution_param {\n\t\tnum_output: 256\n\t\tkernel_size: 5\n\t\tpad: 2\n\t\tstride: 2\n\t}\n}\nlayer {\n\tname: \"relu2\"\n\ttype: \"ReLU\"\n\tbottom: \"conv2\"\n\ttop: \"conv2\"\n}\nlayer {\n\tname: \"norm2\"\n\ttype: \"LRN\"\n\tbottom: \"conv2\"\n\ttop: \"norm2\"\n\tlrn_param {\n\t\tlocal_size: 3\n\t\talpha: 0.00005\n\t\tbeta: 0.75\n\t\tnorm_region: WITHIN_CHANNEL\n engine: CAFFE\n\t}\n}\nlayer {\n\tname: \"pool2\"\n\ttype: \"Pooling\"\n\tbottom: \"norm2\"\n\ttop: \"pool2\"\n\tpooling_param {\n\t\tkernel_size: 3\n\t\tstride: 2\n\t\tpad: 1\n\t\tpool: MAX\n\t}\n}\nlayer {\n\tname: \"conv3\"\n\ttype: \"Convolution\"\n\tbottom: \"pool2\"\n\ttop: \"conv3\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n\tconvolution_param {\n\t\tnum_output: 384\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu3\"\n\ttype: \"ReLU\"\n\tbottom: \"conv3\"\n\ttop: \"conv3\"\n}\nlayer {\n\tname: \"conv4\"\n\ttype: \"Convolution\"\n\tbottom: \"conv3\"\n\ttop: \"conv4\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n\tconvolution_param {\n\t\tnum_output: 384\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu4\"\n\ttype: \"ReLU\"\n\tbottom: \"conv4\"\n\ttop: \"conv4\"\n}\nlayer {\n\tname: \"conv5\"\n\ttype: \"Convolution\"\n\tbottom: \"conv4\"\n\ttop: \"conv5\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n\tconvolution_param {\n\t\tnum_output: 256\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu5\"\n\ttype: \"ReLU\"\n\tbottom: \"conv5\"\n\ttop: \"conv5\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv1\"\n type: \"Convolution\"\n bottom: \"conv5\"\n top: \"rpn_conv1\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu1\"\n type: \"ReLU\"\n bottom: \"rpn_conv1\"\n top: \"rpn_conv1\"\n}\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn_conv1\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn_conv1\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: \"rpn_bbox_inside_weights\"\n bottom: \"rpn_bbox_outside_weights\"\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RCNN ============\n# Dummy layers so that initial parameters are saved into the output net\n\nlayer {\n name: \"dummy_roi_pool_conv5\"\n type: \"DummyData\"\n top: \"dummy_roi_pool_conv5\"\n dummy_data_param {\n shape { dim: 1 dim: 9216 }\n data_filler { type: \"gaussian\" std: 0.01 }\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"dummy_roi_pool_conv5\"\n top: \"fc6\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param { lr_mult: 0 decay_mult: 0 }\n param { lr_mult: 0 decay_mult: 0 }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"silence_fc7\"\n type: \"Silence\"\n bottom: \"fc7\"\n}\n" }, { "path": "models/pascal_voc/ZF/faster_rcnn_end2end/solver.prototxt", "content": "train_net: \"models/pascal_voc/ZF/faster_rcnn_end2end/train.prototxt\"\n\nbase_lr: 0.001\nlr_policy: \"step\"\ngamma: 0.1\nstepsize: 50000\ndisplay: 20\naverage_loss: 100\nmomentum: 0.9\nweight_decay: 0.0005\n\n#base_lr: 0.001\n#lr_policy: \"exp\"\n#gamma: 0.999539589 # (0.00001/0.001)^(1/10000)\n#display: 1\n#average_loss: 100\n#momentum: 0.9\n#weight_decay: 0.0005\n\n# We disable standard caffe solver snapshotting and implement our own snapshot\n# function\nsnapshot: 0\n# We still use the snapshot prefix, though\nsnapshot_prefix: \"zf_faster_rcnn\"\niter_size: 2\n" }, { "path": "models/pascal_voc/ZF/faster_rcnn_end2end/test.prototxt", "content": "name: \"ZF\"\n\ninput: \"data\"\ninput_shape {\n dim: 1\n dim: 3\n dim: 224\n dim: 224\n}\n\ninput: \"im_info\"\ninput_shape {\n dim: 1\n dim: 3\n}\n\n#========= conv1-conv5 ============\n\nlayer {\n\tname: \"conv1\"\n\ttype: \"Convolution\"\n\tbottom: \"data\"\n\ttop: \"conv1\"\n\tconvolution_param {\n\t\tnum_output: 96\n\t\tkernel_size: 7\n\t\tpad: 3\n\t\tstride: 2\n\t}\n}\nlayer {\n\tname: \"relu1\"\n\ttype: \"ReLU\"\n\tbottom: \"conv1\"\n\ttop: \"conv1\"\n}\nlayer {\n\tname: \"norm1\"\n\ttype: \"LRN\"\n\tbottom: \"conv1\"\n\ttop: \"norm1\"\n\tlrn_param {\n\t\tlocal_size: 3\n\t\talpha: 0.00005\n\t\tbeta: 0.75\n\t\tnorm_region: WITHIN_CHANNEL\n engine: CAFFE\n\t}\n}\nlayer {\n\tname: \"pool1\"\n\ttype: \"Pooling\"\n\tbottom: \"norm1\"\n\ttop: \"pool1\"\n\tpooling_param {\n\t\tkernel_size: 3\n\t\tstride: 2\n\t\tpad: 1\n\t\tpool: MAX\n\t}\n}\nlayer {\n\tname: \"conv2\"\n\ttype: \"Convolution\"\n\tbottom: \"pool1\"\n\ttop: \"conv2\"\n\tconvolution_param {\n\t\tnum_output: 256\n\t\tkernel_size: 5\n\t\tpad: 2\n\t\tstride: 2\n\t}\n}\nlayer {\n\tname: \"relu2\"\n\ttype: \"ReLU\"\n\tbottom: \"conv2\"\n\ttop: \"conv2\"\n}\nlayer {\n\tname: \"norm2\"\n\ttype: \"LRN\"\n\tbottom: \"conv2\"\n\ttop: \"norm2\"\n\tlrn_param {\n\t\tlocal_size: 3\n\t\talpha: 0.00005\n\t\tbeta: 0.75\n\t\tnorm_region: WITHIN_CHANNEL\n engine: CAFFE\n\t}\n}\nlayer {\n\tname: \"pool2\"\n\ttype: \"Pooling\"\n\tbottom: \"norm2\"\n\ttop: \"pool2\"\n\tpooling_param {\n\t\tkernel_size: 3\n\t\tstride: 2\n\t\tpad: 1\n\t\tpool: MAX\n\t}\n}\nlayer {\n\tname: \"conv3\"\n\ttype: \"Convolution\"\n\tbottom: \"pool2\"\n\ttop: \"conv3\"\n\tconvolution_param {\n\t\tnum_output: 384\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu3\"\n\ttype: \"ReLU\"\n\tbottom: \"conv3\"\n\ttop: \"conv3\"\n}\nlayer {\n\tname: \"conv4\"\n\ttype: \"Convolution\"\n\tbottom: \"conv3\"\n\ttop: \"conv4\"\n\tconvolution_param {\n\t\tnum_output: 384\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu4\"\n\ttype: \"ReLU\"\n\tbottom: \"conv4\"\n\ttop: \"conv4\"\n}\nlayer {\n\tname: \"conv5\"\n\ttype: \"Convolution\"\n\tbottom: \"conv4\"\n\ttop: \"conv5\"\n\tconvolution_param {\n\t\tnum_output: 256\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu5\"\n\ttype: \"ReLU\"\n\tbottom: \"conv5\"\n\ttop: \"conv5\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"conv5\"\n top: \"rpn/output\"\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n#layer {\n# name: \"rpn_conv/3x3\"\n# type: \"Convolution\"\n# bottom: \"conv5\"\n# top: \"rpn_conv/3x3\"\n# param { lr_mult: 1.0 decay_mult: 1.0 }\n# param { lr_mult: 2.0 decay_mult: 0 }\n# convolution_param {\n# num_output: 192\n# kernel_size: 3 pad: 1 stride: 1\n# weight_filler { type: \"gaussian\" std: 0.01 }\n# bias_filler { type: \"constant\" value: 0 }\n# }\n#}\n#layer {\n# name: \"rpn_conv/5x5\"\n# type: \"Convolution\"\n# bottom: \"conv5\"\n# top: \"rpn_conv/5x5\"\n# param { lr_mult: 1.0 decay_mult: 1.0 }\n# param { lr_mult: 2.0 decay_mult: 0 }\n# convolution_param {\n# num_output: 64\n# kernel_size: 5 pad: 2 stride: 1\n# weight_filler { type: \"gaussian\" std: 0.0036 }\n# bias_filler { type: \"constant\" value: 0 }\n# }\n#}\n#layer {\n# name: \"rpn/output\"\n# type: \"Concat\"\n# bottom: \"rpn_conv/3x3\"\n# bottom: \"rpn_conv/5x5\"\n# top: \"rpn/output\"\n#}\n#layer {\n# name: \"rpn_relu/output\"\n# type: \"ReLU\"\n# bottom: \"rpn/output\"\n# top: \"rpn/output\"\n#}\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rois'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n\n#========= RCNN ============\n\nlayer {\n name: \"roi_pool_conv5\"\n type: \"ROIPooling\"\n bottom: \"conv5\"\n bottom: \"rois\"\n top: \"roi_pool_conv5\"\n roi_pooling_param {\n pooled_w: 6\n pooled_h: 6\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"roi_pool_conv5\"\n top: \"fc6\"\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"drop6\"\n type: \"Dropout\"\n bottom: \"fc6\"\n top: \"fc6\"\n dropout_param {\n dropout_ratio: 0.5\n scale_train: false\n }\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"drop7\"\n type: \"Dropout\"\n bottom: \"fc7\"\n top: \"fc7\"\n dropout_param {\n dropout_ratio: 0.5\n scale_train: false\n }\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n inner_product_param {\n num_output: 21\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n inner_product_param {\n num_output: 84\n }\n}\nlayer {\n name: \"cls_prob\"\n type: \"Softmax\"\n bottom: \"cls_score\"\n top: \"cls_prob\"\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\n" }, { "path": "models/pascal_voc/ZF/faster_rcnn_end2end/train.prototxt", "content": "name: \"ZF\"\nlayer {\n name: 'input-data'\n type: 'Python'\n top: 'data'\n top: 'im_info'\n top: 'gt_boxes'\n python_param {\n module: 'roi_data_layer.layer'\n layer: 'RoIDataLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n#========= conv1-conv5 ============\n\nlayer {\n\tname: \"conv1\"\n\ttype: \"Convolution\"\n\tbottom: \"data\"\n\ttop: \"conv1\"\n\tparam { lr_mult: 1.0 }\n\tparam { lr_mult: 2.0 }\n\tconvolution_param {\n\t\tnum_output: 96\n\t\tkernel_size: 7\n\t\tpad: 3\n\t\tstride: 2\n\t}\n}\nlayer {\n\tname: \"relu1\"\n\ttype: \"ReLU\"\n\tbottom: \"conv1\"\n\ttop: \"conv1\"\n}\nlayer {\n\tname: \"norm1\"\n\ttype: \"LRN\"\n\tbottom: \"conv1\"\n\ttop: \"norm1\"\n\tlrn_param {\n\t\tlocal_size: 3\n\t\talpha: 0.00005\n\t\tbeta: 0.75\n\t\tnorm_region: WITHIN_CHANNEL\n engine: CAFFE\n\t}\n}\nlayer {\n\tname: \"pool1\"\n\ttype: \"Pooling\"\n\tbottom: \"norm1\"\n\ttop: \"pool1\"\n\tpooling_param {\n\t\tkernel_size: 3\n\t\tstride: 2\n\t\tpad: 1\n\t\tpool: MAX\n\t}\n}\nlayer {\n\tname: \"conv2\"\n\ttype: \"Convolution\"\n\tbottom: \"pool1\"\n\ttop: \"conv2\"\n\tparam { lr_mult: 1.0 }\n\tparam { lr_mult: 2.0 }\n\tconvolution_param {\n\t\tnum_output: 256\n\t\tkernel_size: 5\n\t\tpad: 2\n\t\tstride: 2\n\t}\n}\nlayer {\n\tname: \"relu2\"\n\ttype: \"ReLU\"\n\tbottom: \"conv2\"\n\ttop: \"conv2\"\n}\nlayer {\n\tname: \"norm2\"\n\ttype: \"LRN\"\n\tbottom: \"conv2\"\n\ttop: \"norm2\"\n\tlrn_param {\n\t\tlocal_size: 3\n\t\talpha: 0.00005\n\t\tbeta: 0.75\n\t\tnorm_region: WITHIN_CHANNEL\n engine: CAFFE\n\t}\n}\nlayer {\n\tname: \"pool2\"\n\ttype: \"Pooling\"\n\tbottom: \"norm2\"\n\ttop: \"pool2\"\n\tpooling_param {\n\t\tkernel_size: 3\n\t\tstride: 2\n\t\tpad: 1\n\t\tpool: MAX\n\t}\n}\nlayer {\n\tname: \"conv3\"\n\ttype: \"Convolution\"\n\tbottom: \"pool2\"\n\ttop: \"conv3\"\n\tparam { lr_mult: 1.0 }\n\tparam { lr_mult: 2.0 }\n\tconvolution_param {\n\t\tnum_output: 384\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu3\"\n\ttype: \"ReLU\"\n\tbottom: \"conv3\"\n\ttop: \"conv3\"\n}\nlayer {\n\tname: \"conv4\"\n\ttype: \"Convolution\"\n\tbottom: \"conv3\"\n\ttop: \"conv4\"\n\tparam { lr_mult: 1.0 }\n\tparam { lr_mult: 2.0 }\n\tconvolution_param {\n\t\tnum_output: 384\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu4\"\n\ttype: \"ReLU\"\n\tbottom: \"conv4\"\n\ttop: \"conv4\"\n}\nlayer {\n\tname: \"conv5\"\n\ttype: \"Convolution\"\n\tbottom: \"conv4\"\n\ttop: \"conv5\"\n\tparam { lr_mult: 1.0 }\n\tparam { lr_mult: 2.0 }\n\tconvolution_param {\n\t\tnum_output: 256\n\t\tkernel_size: 3\n\t\tpad: 1\n\t\tstride: 1\n\t}\n}\nlayer {\n\tname: \"relu5\"\n\ttype: \"ReLU\"\n\tbottom: \"conv5\"\n\ttop: \"conv5\"\n}\n\n#========= RPN ============\n\nlayer {\n name: \"rpn_conv/3x3\"\n type: \"Convolution\"\n bottom: \"conv5\"\n top: \"rpn/output\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 256\n kernel_size: 3 pad: 1 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_relu/3x3\"\n type: \"ReLU\"\n bottom: \"rpn/output\"\n top: \"rpn/output\"\n}\n\n#layer {\n# name: \"rpn_conv/3x3\"\n# type: \"Convolution\"\n# bottom: \"conv5\"\n# top: \"rpn_conv/3x3\"\n# param { lr_mult: 1.0 }\n# param { lr_mult: 2.0 }\n# convolution_param {\n# num_output: 192\n# kernel_size: 3 pad: 1 stride: 1\n# weight_filler { type: \"gaussian\" std: 0.01 }\n# bias_filler { type: \"constant\" value: 0 }\n# }\n#}\n#layer {\n# name: \"rpn_conv/5x5\"\n# type: \"Convolution\"\n# bottom: \"conv5\"\n# top: \"rpn_conv/5x5\"\n# param { lr_mult: 1.0 }\n# param { lr_mult: 2.0 }\n# convolution_param {\n# num_output: 64\n# kernel_size: 5 pad: 2 stride: 1\n# weight_filler { type: \"gaussian\" std: 0.0036 }\n# bias_filler { type: \"constant\" value: 0 }\n# }\n#}\n#layer {\n# name: \"rpn/output\"\n# type: \"Concat\"\n# bottom: \"rpn_conv/3x3\"\n# bottom: \"rpn_conv/5x5\"\n# top: \"rpn/output\"\n#}\n#layer {\n# name: \"rpn_relu/output\"\n# type: \"ReLU\"\n# bottom: \"rpn/output\"\n# top: \"rpn/output\"\n#}\n\nlayer {\n name: \"rpn_cls_score\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 18 # 2(bg/fg) * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n name: \"rpn_bbox_pred\"\n type: \"Convolution\"\n bottom: \"rpn/output\"\n top: \"rpn_bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n convolution_param {\n num_output: 36 # 4 * 9(anchors)\n kernel_size: 1 pad: 0 stride: 1\n weight_filler { type: \"gaussian\" std: 0.01 }\n bias_filler { type: \"constant\" value: 0 }\n }\n}\nlayer {\n bottom: \"rpn_cls_score\"\n top: \"rpn_cls_score_reshape\"\n name: \"rpn_cls_score_reshape\"\n type: \"Reshape\"\n reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'rpn-data'\n type: 'Python'\n bottom: 'rpn_cls_score'\n bottom: 'gt_boxes'\n bottom: 'im_info'\n bottom: 'data'\n top: 'rpn_labels'\n top: 'rpn_bbox_targets'\n top: 'rpn_bbox_inside_weights'\n top: 'rpn_bbox_outside_weights'\n python_param {\n module: 'rpn.anchor_target_layer'\n layer: 'AnchorTargetLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\nlayer {\n name: \"rpn_loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"rpn_cls_score_reshape\"\n bottom: \"rpn_labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"rpn_cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\nlayer {\n name: \"rpn_loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"rpn_bbox_pred\"\n bottom: \"rpn_bbox_targets\"\n bottom: 'rpn_bbox_inside_weights'\n bottom: 'rpn_bbox_outside_weights'\n top: \"rpn_loss_bbox\"\n loss_weight: 1\n smooth_l1_loss_param { sigma: 3.0 }\n}\n\n#========= RoI Proposal ============\n\nlayer {\n name: \"rpn_cls_prob\"\n type: \"Softmax\"\n bottom: \"rpn_cls_score_reshape\"\n top: \"rpn_cls_prob\"\n}\nlayer {\n name: 'rpn_cls_prob_reshape'\n type: 'Reshape'\n bottom: 'rpn_cls_prob'\n top: 'rpn_cls_prob_reshape'\n reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }\n}\nlayer {\n name: 'proposal'\n type: 'Python'\n bottom: 'rpn_cls_prob_reshape'\n bottom: 'rpn_bbox_pred'\n bottom: 'im_info'\n top: 'rpn_rois'\n# top: 'rpn_scores'\n python_param {\n module: 'rpn.proposal_layer'\n layer: 'ProposalLayer'\n param_str: \"'feat_stride': 16\"\n }\n}\n#layer {\n# name: 'debug-data'\n# type: 'Python'\n# bottom: 'data'\n# bottom: 'rpn_rois'\n# bottom: 'rpn_scores'\n# python_param {\n# module: 'rpn.debug_layer'\n# layer: 'RPNDebugLayer'\n# }\n#}\nlayer {\n name: 'roi-data'\n type: 'Python'\n bottom: 'rpn_rois'\n bottom: 'gt_boxes'\n top: 'rois'\n top: 'labels'\n top: 'bbox_targets'\n top: 'bbox_inside_weights'\n top: 'bbox_outside_weights'\n python_param {\n module: 'rpn.proposal_target_layer'\n layer: 'ProposalTargetLayer'\n param_str: \"'num_classes': 21\"\n }\n}\n\n#========= RCNN ============\n\nlayer {\n name: \"roi_pool_conv5\"\n type: \"ROIPooling\"\n bottom: \"conv5\"\n bottom: \"rois\"\n top: \"roi_pool_conv5\"\n roi_pooling_param {\n pooled_w: 6\n pooled_h: 6\n spatial_scale: 0.0625 # 1/16\n }\n}\nlayer {\n name: \"fc6\"\n type: \"InnerProduct\"\n bottom: \"roi_pool_conv5\"\n top: \"fc6\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu6\"\n type: \"ReLU\"\n bottom: \"fc6\"\n top: \"fc6\"\n}\nlayer {\n name: \"drop6\"\n type: \"Dropout\"\n bottom: \"fc6\"\n top: \"fc6\"\n dropout_param {\n dropout_ratio: 0.5\n scale_train: false\n }\n}\nlayer {\n name: \"fc7\"\n type: \"InnerProduct\"\n bottom: \"fc6\"\n top: \"fc7\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n inner_product_param {\n num_output: 4096\n }\n}\nlayer {\n name: \"relu7\"\n type: \"ReLU\"\n bottom: \"fc7\"\n top: \"fc7\"\n}\nlayer {\n name: \"drop7\"\n type: \"Dropout\"\n bottom: \"fc7\"\n top: \"fc7\"\n dropout_param {\n dropout_ratio: 0.5\n scale_train: false\n }\n}\nlayer {\n name: \"cls_score\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"cls_score\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n inner_product_param {\n num_output: 21\n weight_filler {\n type: \"gaussian\"\n std: 0.01\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"bbox_pred\"\n type: \"InnerProduct\"\n bottom: \"fc7\"\n top: \"bbox_pred\"\n param { lr_mult: 1.0 }\n param { lr_mult: 2.0 }\n inner_product_param {\n num_output: 84\n weight_filler {\n type: \"gaussian\"\n std: 0.001\n }\n bias_filler {\n type: \"constant\"\n value: 0\n }\n }\n}\nlayer {\n name: \"loss_cls\"\n type: \"SoftmaxWithLoss\"\n bottom: \"cls_score\"\n bottom: \"labels\"\n propagate_down: 1\n propagate_down: 0\n top: \"cls_loss\"\n loss_weight: 1\n loss_param {\n ignore_label: -1\n normalize: true\n }\n}\nlayer {\n name: \"loss_bbox\"\n type: \"SmoothL1Loss\"\n bottom: \"bbox_pred\"\n bottom: \"bbox_targets\"\n bottom: 'bbox_inside_weights'\n bottom: 'bbox_outside_weights'\n top: \"bbox_loss\"\n loss_weight: 1\n}\n" }, { "path": "tools/README.md", "content": "Tools for training, testing, and compressing Fast R-CNN networks.\n" }, { "path": "tools/_init_paths.py", "content": "# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\n\"\"\"Set up paths for Fast R-CNN.\"\"\"\n\nimport os.path as osp\nimport sys\n\ndef add_path(path):\n if path not in sys.path:\n sys.path.insert(0, path)\n\nthis_dir = osp.dirname(__file__)\n\n# Add caffe to PYTHONPATH\ncaffe_path = osp.join(this_dir, '..', 'caffe-fast-rcnn', 'python')\nadd_path(caffe_path)\n\n# Add lib to PYTHONPATH\nlib_path = osp.join(this_dir, '..', 'lib')\nadd_path(lib_path)\n" }, { "path": "tools/compress_net.py", "content": "#!/usr/bin/env python\n\n# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\n\"\"\"Compress a Fast R-CNN network using truncated SVD.\"\"\"\n\nimport _init_paths\nimport caffe\nimport argparse\nimport numpy as np\nimport os, sys\n\ndef parse_args():\n \"\"\"Parse input arguments.\"\"\"\n parser = argparse.ArgumentParser(description='Compress a Fast R-CNN network')\n parser.add_argument('--def', dest='prototxt',\n help='prototxt file defining the uncompressed network',\n default=None, type=str)\n parser.add_argument('--def-svd', dest='prototxt_svd',\n help='prototxt file defining the SVD compressed network',\n default=None, type=str)\n parser.add_argument('--net', dest='caffemodel',\n help='model to compress',\n default=None, type=str)\n\n if len(sys.argv) == 1:\n parser.print_help()\n sys.exit(1)\n\n args = parser.parse_args()\n return args\n\ndef compress_weights(W, l):\n \"\"\"Compress the weight matrix W of an inner product (fully connected) layer\n using truncated SVD.\n\n Parameters:\n W: N x M weights matrix\n l: number of singular values to retain\n\n Returns:\n Ul, L: matrices such that W \\approx Ul*L\n \"\"\"\n\n # numpy doesn't seem to have a fast truncated SVD algorithm...\n # this could be faster\n U, s, V = np.linalg.svd(W, full_matrices=False)\n\n Ul = U[:, :l]\n sl = s[:l]\n Vl = V[:l, :]\n\n L = np.dot(np.diag(sl), Vl)\n return Ul, L\n\ndef main():\n args = parse_args()\n\n # prototxt = 'models/VGG16/test.prototxt'\n # caffemodel = 'snapshots/vgg16_fast_rcnn_iter_40000.caffemodel'\n net = caffe.Net(args.prototxt, args.caffemodel, caffe.TEST)\n\n # prototxt_svd = 'models/VGG16/svd/test_fc6_fc7.prototxt'\n # caffemodel = 'snapshots/vgg16_fast_rcnn_iter_40000.caffemodel'\n net_svd = caffe.Net(args.prototxt_svd, args.caffemodel, caffe.TEST)\n\n print('Uncompressed network {} : {}'.format(args.prototxt, args.caffemodel))\n print('Compressed network prototxt {}'.format(args.prototxt_svd))\n\n out = os.path.splitext(os.path.basename(args.caffemodel))[0] + '_svd'\n out_dir = os.path.dirname(args.caffemodel)\n\n # Compress fc6\n if net_svd.params.has_key('fc6_L'):\n l_fc6 = net_svd.params['fc6_L'][0].data.shape[0]\n print(' fc6_L bottleneck size: {}'.format(l_fc6))\n\n # uncompressed weights and biases\n W_fc6 = net.params['fc6'][0].data\n B_fc6 = net.params['fc6'][1].data\n\n print(' compressing fc6...')\n Ul_fc6, L_fc6 = compress_weights(W_fc6, l_fc6)\n\n assert(len(net_svd.params['fc6_L']) == 1)\n\n # install compressed matrix factors (and original biases)\n net_svd.params['fc6_L'][0].data[...] = L_fc6\n\n net_svd.params['fc6_U'][0].data[...] = Ul_fc6\n net_svd.params['fc6_U'][1].data[...] = B_fc6\n\n out += '_fc6_{}'.format(l_fc6)\n\n # Compress fc7\n if net_svd.params.has_key('fc7_L'):\n l_fc7 = net_svd.params['fc7_L'][0].data.shape[0]\n print ' fc7_L bottleneck size: {}'.format(l_fc7)\n\n W_fc7 = net.params['fc7'][0].data\n B_fc7 = net.params['fc7'][1].data\n\n print(' compressing fc7...')\n Ul_fc7, L_fc7 = compress_weights(W_fc7, l_fc7)\n\n assert(len(net_svd.params['fc7_L']) == 1)\n\n net_svd.params['fc7_L'][0].data[...] = L_fc7\n\n net_svd.params['fc7_U'][0].data[...] = Ul_fc7\n net_svd.params['fc7_U'][1].data[...] = B_fc7\n\n out += '_fc7_{}'.format(l_fc7)\n\n filename = '{}/{}.caffemodel'.format(out_dir, out)\n net_svd.save(filename)\n print 'Wrote svd model to: {:s}'.format(filename)\n\nif __name__ == '__main__':\n main()\n" }, { "path": "tools/demo.py", "content": "#!/usr/bin/env python\n\n# --------------------------------------------------------\n# Faster R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\n\"\"\"\nDemo script showing detections in sample images.\n\nSee README.md for installation instructions before running.\n\"\"\"\n\nimport _init_paths\nfrom fast_rcnn.config import cfg\nfrom fast_rcnn.test import im_detect\nfrom fast_rcnn.nms_wrapper import nms\nfrom utils.timer import Timer\nimport matplotlib.pyplot as plt\nimport numpy as np\nimport scipy.io as sio\nimport caffe, os, sys, cv2\nimport argparse\n\nCLASSES = ('__background__',\n 'aeroplane', 'bicycle', 'bird', 'boat',\n 'bottle', 'bus', 'car', 'cat', 'chair',\n 'cow', 'diningtable', 'dog', 'horse',\n 'motorbike', 'person', 'pottedplant',\n 'sheep', 'sofa', 'train', 'tvmonitor')\n\nNETS = {'vgg16': ('VGG16',\n 'VGG16_faster_rcnn_final.caffemodel'),\n 'zf': ('ZF',\n 'ZF_faster_rcnn_final.caffemodel')}\n\n\ndef vis_detections(im, class_name, dets, thresh=0.5):\n \"\"\"Draw detected bounding boxes.\"\"\"\n inds = np.where(dets[:, -1] >= thresh)[0]\n if len(inds) == 0:\n return\n\n im = im[:, :, (2, 1, 0)]\n fig, ax = plt.subplots(figsize=(12, 12))\n ax.imshow(im, aspect='equal')\n for i in inds:\n bbox = dets[i, :4]\n score = dets[i, -1]\n\n ax.add_patch(\n plt.Rectangle((bbox[0], bbox[1]),\n bbox[2] - bbox[0],\n bbox[3] - bbox[1], fill=False,\n edgecolor='red', linewidth=3.5)\n )\n ax.text(bbox[0], bbox[1] - 2,\n '{:s} {:.3f}'.format(class_name, score),\n bbox=dict(facecolor='blue', alpha=0.5),\n fontsize=14, color='white')\n\n ax.set_title(('{} detections with '\n 'p({} | box) >= {:.1f}').format(class_name, class_name,\n thresh),\n fontsize=14)\n plt.axis('off')\n plt.tight_layout()\n plt.draw()\n\ndef demo(net, image_name):\n \"\"\"Detect object classes in an image using pre-computed object proposals.\"\"\"\n\n # Load the demo image\n im_file = os.path.join(cfg.DATA_DIR, 'demo', image_name)\n im = cv2.imread(im_file)\n\n # Detect all object classes and regress object bounds\n timer = Timer()\n timer.tic()\n scores, boxes = im_detect(net, im)\n timer.toc()\n print ('Detection took {:.3f}s for '\n '{:d} object proposals').format(timer.total_time, boxes.shape[0])\n\n # Visualize detections for each class\n CONF_THRESH = 0.8\n NMS_THRESH = 0.3\n for cls_ind, cls in enumerate(CLASSES[1:]):\n cls_ind += 1 # because we skipped background\n cls_boxes = boxes[:, 4*cls_ind:4*(cls_ind + 1)]\n cls_scores = scores[:, cls_ind]\n dets = np.hstack((cls_boxes,\n cls_scores[:, np.newaxis])).astype(np.float32)\n keep = nms(dets, NMS_THRESH)\n dets = dets[keep, :]\n vis_detections(im, cls, dets, thresh=CONF_THRESH)\n\ndef parse_args():\n \"\"\"Parse input arguments.\"\"\"\n parser = argparse.ArgumentParser(description='Faster R-CNN demo')\n parser.add_argument('--gpu', dest='gpu_id', help='GPU device id to use [0]',\n default=0, type=int)\n parser.add_argument('--cpu', dest='cpu_mode',\n help='Use CPU mode (overrides --gpu)',\n action='store_true')\n parser.add_argument('--net', dest='demo_net', help='Network to use [vgg16]',\n choices=NETS.keys(), default='vgg16')\n\n args = parser.parse_args()\n\n return args\n\nif __name__ == '__main__':\n cfg.TEST.HAS_RPN = True # Use RPN for proposals\n\n args = parse_args()\n\n prototxt = os.path.join(cfg.MODELS_DIR, NETS[args.demo_net][0],\n 'faster_rcnn_alt_opt', 'faster_rcnn_test.pt')\n caffemodel = os.path.join(cfg.DATA_DIR, 'faster_rcnn_models',\n NETS[args.demo_net][1])\n\n if not os.path.isfile(caffemodel):\n raise IOError(('{:s} not found.\\nDid you run ./data/script/'\n 'fetch_faster_rcnn_models.sh?').format(caffemodel))\n\n if args.cpu_mode:\n caffe.set_mode_cpu()\n else:\n caffe.set_mode_gpu()\n caffe.set_device(args.gpu_id)\n cfg.GPU_ID = args.gpu_id\n net = caffe.Net(prototxt, caffemodel, caffe.TEST)\n\n print '\\n\\nLoaded network {:s}'.format(caffemodel)\n\n # Warmup on a dummy image\n im = 128 * np.ones((300, 500, 3), dtype=np.uint8)\n for i in xrange(2):\n _, _= im_detect(net, im)\n\n im_names = ['000456.jpg', '000542.jpg', '001150.jpg',\n '001763.jpg', '004545.jpg']\n for im_name in im_names:\n print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'\n print 'Demo for data/demo/{}'.format(im_name)\n demo(net, im_name)\n\n plt.show()\n" }, { "path": "tools/eval_recall.py", "content": "#!/usr/bin/env python\n\nimport _init_paths\nfrom fast_rcnn.config import cfg, cfg_from_file, cfg_from_list\nfrom datasets.factory import get_imdb\nimport argparse\nimport time, os, sys\nimport numpy as np\n\ndef parse_args():\n \"\"\"\n Parse input arguments\n \"\"\"\n parser = argparse.ArgumentParser(description='Test a Fast R-CNN network')\n parser.add_argument('--imdb', dest='imdb_name',\n help='dataset to test',\n default='voc_2007_test', type=str)\n parser.add_argument('--method', dest='method',\n help='proposal method',\n default='selective_search', type=str)\n parser.add_argument('--rpn-file', dest='rpn_file',\n default=None, type=str)\n\n if len(sys.argv) == 1:\n parser.print_help()\n sys.exit(1)\n\n args = parser.parse_args()\n return args\n\nif __name__ == '__main__':\n args = parse_args()\n\n print('Called with args:')\n print(args)\n\n imdb = get_imdb(args.imdb_name)\n imdb.set_proposal_method(args.method)\n if args.rpn_file is not None:\n imdb.config['rpn_file'] = args.rpn_file\n\n candidate_boxes = None\n if 0:\n import scipy.io as sio\n filename = 'debug/stage1_rpn_voc_2007_test.mat'\n raw_data = sio.loadmat(filename)['aboxes'].ravel()\n candidate_boxes = raw_data\n\n ar, gt_overlaps, recalls, thresholds = \\\n imdb.evaluate_recall(candidate_boxes=candidate_boxes)\n print 'Method: {}'.format(args.method)\n print 'AverageRec: {:.3f}'.format(ar)\n\n def recall_at(t):\n ind = np.where(thresholds > t - 1e-5)[0][0]\n assert np.isclose(thresholds[ind], t)\n return recalls[ind]\n\n print 'Recall@0.5: {:.3f}'.format(recall_at(0.5))\n print 'Recall@0.6: {:.3f}'.format(recall_at(0.6))\n print 'Recall@0.7: {:.3f}'.format(recall_at(0.7))\n print 'Recall@0.8: {:.3f}'.format(recall_at(0.8))\n print 'Recall@0.9: {:.3f}'.format(recall_at(0.9))\n # print again for easy spreadsheet copying\n print '{:.3f}'.format(ar)\n print '{:.3f}'.format(recall_at(0.5))\n print '{:.3f}'.format(recall_at(0.6))\n print '{:.3f}'.format(recall_at(0.7))\n print '{:.3f}'.format(recall_at(0.8))\n print '{:.3f}'.format(recall_at(0.9))\n" }, { "path": "tools/merge_bn_scale.py", "content": "import _init_paths\nimport numpy as np\nimport caffe\n\ncaffe.set_mode_cpu()\n\nnet = caffe.Net('data/CNN-models/resnet-caffe/ResNet-101-deploy.prototxt',\n 'data/CNN-models/resnet-caffe/ResNet-101-model.caffemodel',\n caffe.TEST)\n\nnew_net = caffe.Net('models/pascal_voc/ResNet101_BN_SCALE_Merged/ResNet101_BN_SCALE_Merged_deploy.prototxt',\n 'data/CNN-models/resnet-caffe/ResNet-101-model.caffemodel',\n caffe.TEST)\n\nfor layer_name in net.params.keys():\n if layer_name[:2] == 'bn':\n scale_layer_name = 'scale' + layer_name[2:]\n mu = net.params[layer_name][0].data\n var = net.params[layer_name][1].data\n gamma = net.params[scale_layer_name][0].data\n beta = net.params[scale_layer_name][1].data\n new_gamma = gamma / (np.power(var, 0.5) + 1e-5)\n new_beta = beta - gamma * mu / (np.power(var, 0.5) + 1e-5)\n\n new_net.params[scale_layer_name][0].data[...] = new_gamma\n new_net.params[scale_layer_name][1].data[...] = new_beta\n\nnew_net.save('data/imagenet_models/ResNet101_BN_SCALE_Merged_deploy.caffemodel')\n" }, { "path": "tools/reval.py", "content": "#!/usr/bin/env python\n\n# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\n\"\"\"Reval = re-eval. Re-evaluate saved detections.\"\"\"\n\nimport _init_paths\nfrom fast_rcnn.test import apply_nms\nfrom fast_rcnn.config import cfg\nfrom datasets.factory import get_imdb\nimport cPickle\nimport os, sys, argparse\nimport numpy as np\n\ndef parse_args():\n \"\"\"\n Parse input arguments\n \"\"\"\n parser = argparse.ArgumentParser(description='Re-evaluate results')\n parser.add_argument('output_dir', nargs=1, help='results directory',\n type=str)\n parser.add_argument('--imdb', dest='imdb_name',\n help='dataset to re-evaluate',\n default='voc_2007_test', type=str)\n parser.add_argument('--matlab', dest='matlab_eval',\n help='use matlab for evaluation',\n action='store_true')\n parser.add_argument('--comp', dest='comp_mode', help='competition mode',\n action='store_true')\n parser.add_argument('--nms', dest='apply_nms', help='apply nms',\n action='store_true')\n\n if len(sys.argv) == 1:\n parser.print_help()\n sys.exit(1)\n\n args = parser.parse_args()\n return args\n\ndef from_dets(imdb_name, output_dir, args):\n imdb = get_imdb(imdb_name)\n imdb.competition_mode(args.comp_mode)\n imdb.config['matlab_eval'] = args.matlab_eval\n with open(os.path.join(output_dir, 'detections.pkl'), 'rb') as f:\n dets = cPickle.load(f)\n\n if args.apply_nms:\n print 'Applying NMS to all detections'\n nms_dets = apply_nms(dets, cfg.TEST.NMS)\n else:\n nms_dets = dets\n\n print 'Evaluating detections'\n imdb.evaluate_detections(nms_dets, output_dir)\n\nif __name__ == '__main__':\n args = parse_args()\n\n output_dir = os.path.abspath(args.output_dir[0])\n imdb_name = args.imdb_name\n from_dets(imdb_name, output_dir, args)\n" }, { "path": "tools/rpn_generate.py", "content": "#!/usr/bin/env python\n\n# --------------------------------------------------------\n# Fast/er/ R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\n\"\"\"Generate RPN proposals.\"\"\"\n\nimport _init_paths\nimport numpy as np\nfrom fast_rcnn.config import cfg, cfg_from_file, cfg_from_list, get_output_dir\nfrom datasets.factory import get_imdb\nfrom rpn.generate import imdb_proposals\nimport cPickle\nimport caffe\nimport argparse\nimport pprint\nimport time, os, sys\n\ndef parse_args():\n \"\"\"\n Parse input arguments\n \"\"\"\n parser = argparse.ArgumentParser(description='Test a Fast R-CNN network')\n parser.add_argument('--gpu', dest='gpu_id', help='GPU id to use',\n default=0, type=int)\n parser.add_argument('--def', dest='prototxt',\n help='prototxt file defining the network',\n default=None, type=str)\n parser.add_argument('--net', dest='caffemodel',\n help='model to test',\n default=None, type=str)\n parser.add_argument('--cfg', dest='cfg_file',\n help='optional config file', default=None, type=str)\n parser.add_argument('--wait', dest='wait',\n help='wait until net file exists',\n default=True, type=bool)\n parser.add_argument('--imdb', dest='imdb_name',\n help='dataset to test',\n default='voc_2007_test', type=str)\n parser.add_argument('--set', dest='set_cfgs',\n help='set config keys', default=None,\n nargs=argparse.REMAINDER)\n\n if len(sys.argv) == 1:\n parser.print_help()\n sys.exit(1)\n\n args = parser.parse_args()\n return args\n\nif __name__ == '__main__':\n args = parse_args()\n\n print('Called with args:')\n print(args)\n\n if args.cfg_file is not None:\n cfg_from_file(args.cfg_file)\n if args.set_cfgs is not None:\n cfg_from_list(args.set_cfgs)\n\n cfg.GPU_ID = args.gpu_id\n\n # RPN test settings\n cfg.TEST.RPN_PRE_NMS_TOP_N = -1\n cfg.TEST.RPN_POST_NMS_TOP_N = 2000\n\n print('Using config:')\n pprint.pprint(cfg)\n\n while not os.path.exists(args.caffemodel) and args.wait:\n print('Waiting for {} to exist...'.format(args.caffemodel))\n time.sleep(10)\n\n caffe.set_mode_gpu()\n caffe.set_device(args.gpu_id)\n net = caffe.Net(args.prototxt, args.caffemodel, caffe.TEST)\n net.name = os.path.splitext(os.path.basename(args.caffemodel))[0]\n\n imdb = get_imdb(args.imdb_name)\n imdb_boxes = imdb_proposals(net, imdb)\n\n output_dir = get_output_dir(imdb, net)\n rpn_file = os.path.join(output_dir, net.name + '_rpn_proposals.pkl')\n with open(rpn_file, 'wb') as f:\n cPickle.dump(imdb_boxes, f, cPickle.HIGHEST_PROTOCOL)\n print 'Wrote RPN proposals to {}'.format(rpn_file)\n" }, { "path": "tools/test_net.py", "content": "#!/usr/bin/env python\n\n# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\n\"\"\"Test a Fast R-CNN network on an image database.\"\"\"\n\nimport _init_paths\nfrom fast_rcnn.test import test_net\nfrom fast_rcnn.config import cfg, cfg_from_file, cfg_from_list\nfrom datasets.factory import get_imdb\nimport caffe\nimport argparse\nimport pprint\nimport time, os, sys\n\ndef parse_args():\n \"\"\"\n Parse input arguments\n \"\"\"\n parser = argparse.ArgumentParser(description='Test a Fast R-CNN network')\n parser.add_argument('--gpu', dest='gpu_id', help='GPU id to use',\n default=0, type=int)\n parser.add_argument('--def', dest='prototxt',\n help='prototxt file defining the network',\n default=None, type=str)\n parser.add_argument('--net', dest='caffemodel',\n help='model to test',\n default=None, type=str)\n parser.add_argument('--cfg', dest='cfg_file',\n help='optional config file', default=None, type=str)\n parser.add_argument('--wait', dest='wait',\n help='wait until net file exists',\n default=True, type=bool)\n parser.add_argument('--imdb', dest='imdb_name',\n help='dataset to test',\n default='voc_2007_test', type=str)\n parser.add_argument('--comp', dest='comp_mode', help='competition mode',\n action='store_true')\n parser.add_argument('--set', dest='set_cfgs',\n help='set config keys', default=None,\n nargs=argparse.REMAINDER)\n parser.add_argument('--vis', dest='vis', help='visualize detections',\n action='store_true')\n parser.add_argument('--num_dets', dest='max_per_image',\n help='max number of detections per image',\n default=100, type=int)\n\n if len(sys.argv) == 1:\n parser.print_help()\n sys.exit(1)\n\n args = parser.parse_args()\n return args\n\nif __name__ == '__main__':\n args = parse_args()\n\n print('Called with args:')\n print(args)\n\n if args.cfg_file is not None:\n cfg_from_file(args.cfg_file)\n if args.set_cfgs is not None:\n cfg_from_list(args.set_cfgs)\n\n cfg.GPU_ID = args.gpu_id\n\n print('Using config:')\n pprint.pprint(cfg)\n\n while not os.path.exists(args.caffemodel) and args.wait:\n print('Waiting for {} to exist...'.format(args.caffemodel))\n time.sleep(10)\n\n caffe.set_mode_gpu()\n caffe.set_device(args.gpu_id)\n net = caffe.Net(args.prototxt, args.caffemodel, caffe.TEST)\n net.name = os.path.splitext(os.path.basename(args.caffemodel))[0]\n\n imdb = get_imdb(args.imdb_name)\n imdb.competition_mode(args.comp_mode)\n if not cfg.TEST.HAS_RPN:\n imdb.set_proposal_method(cfg.TEST.PROPOSAL_METHOD)\n\n test_net(net, imdb, max_per_image=args.max_per_image, vis=args.vis)\n" }, { "path": "tools/train_faster_rcnn_alt_opt.py", "content": "#!/usr/bin/env python\n\n# --------------------------------------------------------\n# Faster R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\n\"\"\"Train a Faster R-CNN network using alternating optimization.\nThis tool implements the alternating optimization algorithm described in our\nNIPS 2015 paper (\"Faster R-CNN: Towards Real-time Object Detection with Region\nProposal Networks.\" Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun.)\n\"\"\"\n\nimport _init_paths\nfrom fast_rcnn.train import get_training_roidb, train_net\nfrom fast_rcnn.config import cfg, cfg_from_file, cfg_from_list, get_output_dir\nfrom datasets.factory import get_imdb\nfrom rpn.generate import imdb_proposals\nimport argparse\nimport pprint\nimport numpy as np\nimport sys, os\nimport multiprocessing as mp\nimport cPickle\nimport shutil\n\ndef parse_args():\n \"\"\"\n Parse input arguments\n \"\"\"\n parser = argparse.ArgumentParser(description='Train a Faster R-CNN network')\n parser.add_argument('--gpu', dest='gpu_id',\n help='GPU device id to use [0]',\n default=0, type=int)\n parser.add_argument('--net_name', dest='net_name',\n help='network name (e.g., \"ZF\")',\n default=None, type=str)\n parser.add_argument('--weights', dest='pretrained_model',\n help='initialize with pretrained model weights',\n default=None, type=str)\n parser.add_argument('--cfg', dest='cfg_file',\n help='optional config file',\n default=None, type=str)\n parser.add_argument('--imdb', dest='imdb_name',\n help='dataset to train on',\n default='voc_2007_trainval', type=str)\n parser.add_argument('--set', dest='set_cfgs',\n help='set config keys', default=None,\n nargs=argparse.REMAINDER)\n\n if len(sys.argv) == 1:\n parser.print_help()\n sys.exit(1)\n\n args = parser.parse_args()\n return args\n\ndef get_roidb(imdb_name, rpn_file=None):\n imdb = get_imdb(imdb_name)\n print 'Loaded dataset `{:s}` for training'.format(imdb.name)\n imdb.set_proposal_method(cfg.TRAIN.PROPOSAL_METHOD)\n print 'Set proposal method: {:s}'.format(cfg.TRAIN.PROPOSAL_METHOD)\n if rpn_file is not None:\n imdb.config['rpn_file'] = rpn_file\n roidb = get_training_roidb(imdb)\n return roidb, imdb\n\ndef get_solvers(net_name):\n # Faster R-CNN Alternating Optimization\n n = 'faster_rcnn_alt_opt'\n # Solver for each training stage\n solvers = [[net_name, n, 'stage1_rpn_solver60k80k.pt'],\n [net_name, n, 'stage1_fast_rcnn_solver30k40k.pt'],\n [net_name, n, 'stage2_rpn_solver60k80k.pt'],\n [net_name, n, 'stage2_fast_rcnn_solver30k40k.pt']]\n solvers = [os.path.join(cfg.MODELS_DIR, *s) for s in solvers]\n # Iterations for each training stage\n max_iters = [80000, 40000, 80000, 40000]\n # max_iters = [100, 100, 100, 100]\n # Test prototxt for the RPN\n rpn_test_prototxt = os.path.join(\n cfg.MODELS_DIR, net_name, n, 'rpn_test.pt')\n return solvers, max_iters, rpn_test_prototxt\n\n# ------------------------------------------------------------------------------\n# Pycaffe doesn't reliably free GPU memory when instantiated nets are discarded\n# (e.g. \"del net\" in Python code). To work around this issue, each training\n# stage is executed in a separate process using multiprocessing.Process.\n# ------------------------------------------------------------------------------\n\ndef _init_caffe(cfg):\n \"\"\"Initialize pycaffe in a training process.\n \"\"\"\n\n import caffe\n # fix the random seeds (numpy and caffe) for reproducibility\n np.random.seed(cfg.RNG_SEED)\n caffe.set_random_seed(cfg.RNG_SEED)\n # set up caffe\n caffe.set_mode_gpu()\n caffe.set_device(cfg.GPU_ID)\n\ndef train_rpn(queue=None, imdb_name=None, init_model=None, solver=None,\n max_iters=None, cfg=None):\n \"\"\"Train a Region Proposal Network in a separate training process.\n \"\"\"\n\n # Not using any proposals, just ground-truth boxes\n cfg.TRAIN.HAS_RPN = True\n cfg.TRAIN.BBOX_REG = False # applies only to Fast R-CNN bbox regression\n cfg.TRAIN.PROPOSAL_METHOD = 'gt'\n cfg.TRAIN.IMS_PER_BATCH = 1\n print 'Init model: {}'.format(init_model)\n print('Using config:')\n pprint.pprint(cfg)\n\n import caffe\n _init_caffe(cfg)\n\n roidb, imdb = get_roidb(imdb_name)\n print 'roidb len: {}'.format(len(roidb))\n output_dir = get_output_dir(imdb)\n print 'Output will be saved to `{:s}`'.format(output_dir)\n\n model_paths = train_net(solver, roidb, output_dir,\n pretrained_model=init_model,\n max_iters=max_iters)\n # Cleanup all but the final model\n for i in model_paths[:-1]:\n os.remove(i)\n rpn_model_path = model_paths[-1]\n # Send final model path through the multiprocessing queue\n queue.put({'model_path': rpn_model_path})\n\ndef rpn_generate(queue=None, imdb_name=None, rpn_model_path=None, cfg=None,\n rpn_test_prototxt=None):\n \"\"\"Use a trained RPN to generate proposals.\n \"\"\"\n\n cfg.TEST.RPN_PRE_NMS_TOP_N = -1 # no pre NMS filtering\n cfg.TEST.RPN_POST_NMS_TOP_N = 2000 # limit top boxes after NMS\n print 'RPN model: {}'.format(rpn_model_path)\n print('Using config:')\n pprint.pprint(cfg)\n\n import caffe\n _init_caffe(cfg)\n\n # NOTE: the matlab implementation computes proposals on flipped images, too.\n # We compute them on the image once and then flip the already computed\n # proposals. This might cause a minor loss in mAP (less proposal jittering).\n imdb = get_imdb(imdb_name)\n print 'Loaded dataset `{:s}` for proposal generation'.format(imdb.name)\n\n # Load RPN and configure output directory\n rpn_net = caffe.Net(rpn_test_prototxt, rpn_model_path, caffe.TEST)\n output_dir = get_output_dir(imdb)\n print 'Output will be saved to `{:s}`'.format(output_dir)\n # Generate proposals on the imdb\n rpn_proposals = imdb_proposals(rpn_net, imdb)\n # Write proposals to disk and send the proposal file path through the\n # multiprocessing queue\n rpn_net_name = os.path.splitext(os.path.basename(rpn_model_path))[0]\n rpn_proposals_path = os.path.join(\n output_dir, rpn_net_name + '_proposals.pkl')\n with open(rpn_proposals_path, 'wb') as f:\n cPickle.dump(rpn_proposals, f, cPickle.HIGHEST_PROTOCOL)\n print 'Wrote RPN proposals to {}'.format(rpn_proposals_path)\n queue.put({'proposal_path': rpn_proposals_path})\n\ndef train_fast_rcnn(queue=None, imdb_name=None, init_model=None, solver=None,\n max_iters=None, cfg=None, rpn_file=None):\n \"\"\"Train a Fast R-CNN using proposals generated by an RPN.\n \"\"\"\n\n cfg.TRAIN.HAS_RPN = False # not generating prosals on-the-fly\n cfg.TRAIN.PROPOSAL_METHOD = 'rpn' # use pre-computed RPN proposals instead\n cfg.TRAIN.IMS_PER_BATCH = 2\n print 'Init model: {}'.format(init_model)\n print 'RPN proposals: {}'.format(rpn_file)\n print('Using config:')\n pprint.pprint(cfg)\n\n import caffe\n _init_caffe(cfg)\n\n roidb, imdb = get_roidb(imdb_name, rpn_file=rpn_file)\n output_dir = get_output_dir(imdb)\n print 'Output will be saved to `{:s}`'.format(output_dir)\n # Train Fast R-CNN\n model_paths = train_net(solver, roidb, output_dir,\n pretrained_model=init_model,\n max_iters=max_iters)\n # Cleanup all but the final model\n for i in model_paths[:-1]:\n os.remove(i)\n fast_rcnn_model_path = model_paths[-1]\n # Send Fast R-CNN model path over the multiprocessing queue\n queue.put({'model_path': fast_rcnn_model_path})\n\nif __name__ == '__main__':\n args = parse_args()\n\n print('Called with args:')\n print(args)\n\n if args.cfg_file is not None:\n cfg_from_file(args.cfg_file)\n if args.set_cfgs is not None:\n cfg_from_list(args.set_cfgs)\n cfg.GPU_ID = args.gpu_id\n\n # --------------------------------------------------------------------------\n # Pycaffe doesn't reliably free GPU memory when instantiated nets are\n # discarded (e.g. \"del net\" in Python code). To work around this issue, each\n # training stage is executed in a separate process using\n # multiprocessing.Process.\n # --------------------------------------------------------------------------\n\n # queue for communicated results between processes\n mp_queue = mp.Queue()\n # solves, iters, etc. for each training stage\n solvers, max_iters, rpn_test_prototxt = get_solvers(args.net_name)\n\n print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'\n print 'Stage 1 RPN, init from ImageNet model'\n print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'\n\n cfg.TRAIN.SNAPSHOT_INFIX = 'stage1'\n mp_kwargs = dict(\n queue=mp_queue,\n imdb_name=args.imdb_name,\n init_model=args.pretrained_model,\n solver=solvers[0],\n max_iters=max_iters[0],\n cfg=cfg)\n p = mp.Process(target=train_rpn, kwargs=mp_kwargs)\n p.start()\n rpn_stage1_out = mp_queue.get()\n p.join()\n\n print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'\n print 'Stage 1 RPN, generate proposals'\n print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'\n\n mp_kwargs = dict(\n queue=mp_queue,\n imdb_name=args.imdb_name,\n rpn_model_path=str(rpn_stage1_out['model_path']),\n cfg=cfg,\n rpn_test_prototxt=rpn_test_prototxt)\n p = mp.Process(target=rpn_generate, kwargs=mp_kwargs)\n p.start()\n rpn_stage1_out['proposal_path'] = mp_queue.get()['proposal_path']\n p.join()\n\n print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'\n print 'Stage 1 Fast R-CNN using RPN proposals, init from ImageNet model'\n print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'\n\n cfg.TRAIN.SNAPSHOT_INFIX = 'stage1'\n mp_kwargs = dict(\n queue=mp_queue,\n imdb_name=args.imdb_name,\n init_model=args.pretrained_model,\n solver=solvers[1],\n max_iters=max_iters[1],\n cfg=cfg,\n rpn_file=rpn_stage1_out['proposal_path'])\n p = mp.Process(target=train_fast_rcnn, kwargs=mp_kwargs)\n p.start()\n fast_rcnn_stage1_out = mp_queue.get()\n p.join()\n\n print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'\n print 'Stage 2 RPN, init from stage 1 Fast R-CNN model'\n print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'\n\n cfg.TRAIN.SNAPSHOT_INFIX = 'stage2'\n mp_kwargs = dict(\n queue=mp_queue,\n imdb_name=args.imdb_name,\n init_model=str(fast_rcnn_stage1_out['model_path']),\n solver=solvers[2],\n max_iters=max_iters[2],\n cfg=cfg)\n p = mp.Process(target=train_rpn, kwargs=mp_kwargs)\n p.start()\n rpn_stage2_out = mp_queue.get()\n p.join()\n\n print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'\n print 'Stage 2 RPN, generate proposals'\n print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'\n\n mp_kwargs = dict(\n queue=mp_queue,\n imdb_name=args.imdb_name,\n rpn_model_path=str(rpn_stage2_out['model_path']),\n cfg=cfg,\n rpn_test_prototxt=rpn_test_prototxt)\n p = mp.Process(target=rpn_generate, kwargs=mp_kwargs)\n p.start()\n rpn_stage2_out['proposal_path'] = mp_queue.get()['proposal_path']\n p.join()\n\n print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'\n print 'Stage 2 Fast R-CNN, init from stage 2 RPN R-CNN model'\n print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'\n\n cfg.TRAIN.SNAPSHOT_INFIX = 'stage2'\n mp_kwargs = dict(\n queue=mp_queue,\n imdb_name=args.imdb_name,\n init_model=str(rpn_stage2_out['model_path']),\n solver=solvers[3],\n max_iters=max_iters[3],\n cfg=cfg,\n rpn_file=rpn_stage2_out['proposal_path'])\n p = mp.Process(target=train_fast_rcnn, kwargs=mp_kwargs)\n p.start()\n fast_rcnn_stage2_out = mp_queue.get()\n p.join()\n\n # Create final model (just a copy of the last stage)\n final_path = os.path.join(\n os.path.dirname(fast_rcnn_stage2_out['model_path']),\n args.net_name + '_faster_rcnn_final.caffemodel')\n print 'cp {} -> {}'.format(\n fast_rcnn_stage2_out['model_path'], final_path)\n shutil.copy(fast_rcnn_stage2_out['model_path'], final_path)\n print 'Final model: {}'.format(final_path)\n" }, { "path": "tools/train_net.py", "content": "#!/usr/bin/env python\n\n# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\n\"\"\"Train a Fast R-CNN network on a region of interest database.\"\"\"\n\nimport _init_paths\nfrom fast_rcnn.train import get_training_roidb, train_net\nfrom fast_rcnn.config import cfg, cfg_from_file, cfg_from_list, get_output_dir\nfrom datasets.factory import get_imdb\nimport datasets.imdb\nimport caffe\nimport argparse\nimport pprint\nimport numpy as np\nimport sys\n\ndef parse_args():\n \"\"\"\n Parse input arguments\n \"\"\"\n parser = argparse.ArgumentParser(description='Train a Fast R-CNN network')\n parser.add_argument('--gpu', dest='gpu_id',\n help='GPU device id to use [0]',\n default=0, type=int)\n parser.add_argument('--solver', dest='solver',\n help='solver prototxt',\n default=None, type=str)\n parser.add_argument('--iters', dest='max_iters',\n help='number of iterations to train',\n default=40000, type=int)\n parser.add_argument('--weights', dest='pretrained_model',\n help='initialize with pretrained model weights',\n default=None, type=str)\n parser.add_argument('--cfg', dest='cfg_file',\n help='optional config file',\n default=None, type=str)\n parser.add_argument('--imdb', dest='imdb_name',\n help='dataset to train on',\n default='voc_2007_trainval', type=str)\n parser.add_argument('--rand', dest='randomize',\n help='randomize (do not use a fixed seed)',\n action='store_true')\n parser.add_argument('--set', dest='set_cfgs',\n help='set config keys', default=None,\n nargs=argparse.REMAINDER)\n\n if len(sys.argv) == 1:\n parser.print_help()\n sys.exit(1)\n\n args = parser.parse_args()\n return args\n\ndef combined_roidb(imdb_names):\n def get_roidb(imdb_name):\n imdb = get_imdb(imdb_name)\n print 'Loaded dataset `{:s}` for training'.format(imdb.name)\n imdb.set_proposal_method(cfg.TRAIN.PROPOSAL_METHOD)\n print 'Set proposal method: {:s}'.format(cfg.TRAIN.PROPOSAL_METHOD)\n roidb = get_training_roidb(imdb)\n return roidb\n\n roidbs = [get_roidb(s) for s in imdb_names.split('+')]\n roidb = roidbs[0]\n if len(roidbs) > 1:\n for r in roidbs[1:]:\n roidb.extend(r)\n imdb = datasets.imdb.imdb(imdb_names)\n else:\n imdb = get_imdb(imdb_names)\n return imdb, roidb\n\nif __name__ == '__main__':\n args = parse_args()\n\n print('Called with args:')\n print(args)\n\n if args.cfg_file is not None:\n cfg_from_file(args.cfg_file)\n if args.set_cfgs is not None:\n cfg_from_list(args.set_cfgs)\n\n cfg.GPU_ID = args.gpu_id\n\n print('Using config:')\n pprint.pprint(cfg)\n\n if not args.randomize:\n # fix the random seeds (numpy and caffe) for reproducibility\n np.random.seed(cfg.RNG_SEED)\n caffe.set_random_seed(cfg.RNG_SEED)\n\n # set up caffe\n caffe.set_mode_gpu()\n caffe.set_device(args.gpu_id)\n\n imdb, roidb = combined_roidb(args.imdb_name)\n print '{:d} roidb entries'.format(len(roidb))\n\n output_dir = get_output_dir(imdb)\n print 'Output will be saved to `{:s}`'.format(output_dir)\n\n train_net(args.solver, roidb, output_dir,\n pretrained_model=args.pretrained_model,\n max_iters=args.max_iters)\n" }, { "path": "tools/train_svms.py", "content": "#!/usr/bin/env python\n\n# --------------------------------------------------------\n# Fast R-CNN\n# Copyright (c) 2015 Microsoft\n# Licensed under The MIT License [see LICENSE for details]\n# Written by Ross Girshick\n# --------------------------------------------------------\n\n\"\"\"\nTrain post-hoc SVMs using the algorithm and hyper-parameters from\ntraditional R-CNN.\n\"\"\"\n\nimport _init_paths\nfrom fast_rcnn.config import cfg, cfg_from_file\nfrom datasets.factory import get_imdb\nfrom fast_rcnn.test import im_detect\nfrom utils.timer import Timer\nimport caffe\nimport argparse\nimport pprint\nimport numpy as np\nimport numpy.random as npr\nimport cv2\nfrom sklearn import svm\nimport os, sys\n\nclass SVMTrainer(object):\n \"\"\"\n Trains post-hoc detection SVMs for all classes using the algorithm\n and hyper-parameters of traditional R-CNN.\n \"\"\"\n\n def __init__(self, net, imdb):\n self.imdb = imdb\n self.net = net\n self.layer = 'fc7'\n self.hard_thresh = -1.0001\n self.neg_iou_thresh = 0.3\n\n dim = net.params['cls_score'][0].data.shape[1]\n scale = self._get_feature_scale()\n print('Feature dim: {}'.format(dim))\n print('Feature scale: {:.3f}'.format(scale))\n self.trainers = [SVMClassTrainer(cls, dim, feature_scale=scale)\n for cls in imdb.classes]\n\n def _get_feature_scale(self, num_images=100):\n TARGET_NORM = 20.0 # Magic value from traditional R-CNN\n _t = Timer()\n roidb = self.imdb.roidb\n total_norm = 0.0\n count = 0.0\n inds = npr.choice(xrange(self.imdb.num_images), size=num_images,\n replace=False)\n for i_, i in enumerate(inds):\n im = cv2.imread(self.imdb.image_path_at(i))\n if roidb[i]['flipped']:\n im = im[:, ::-1, :]\n _t.tic()\n scores, boxes = im_detect(self.net, im, roidb[i]['boxes'])\n _t.toc()\n feat = self.net.blobs[self.layer].data\n total_norm += np.sqrt((feat ** 2).sum(axis=1)).sum()\n count += feat.shape[0]\n print('{}/{}: avg feature norm: {:.3f}'.format(i_ + 1, num_images,\n total_norm / count))\n\n return TARGET_NORM * 1.0 / (total_norm / count)\n\n def _get_pos_counts(self):\n counts = np.zeros((len(self.imdb.classes)), dtype=np.int)\n roidb = self.imdb.roidb\n for i in xrange(len(roidb)):\n for j in xrange(1, self.imdb.num_classes):\n I = np.where(roidb[i]['gt_classes'] == j)[0]\n counts[j] += len(I)\n\n for j in xrange(1, self.imdb.num_classes):\n print('class {:s} has {:d} positives'.\n format(self.imdb.classes[j], counts[j]))\n\n return counts\n\n def get_pos_examples(self):\n counts = self._get_pos_counts()\n for i in xrange(len(counts)):\n self.trainers[i].alloc_pos(counts[i])\n\n _t = Timer()\n roidb = self.imdb.roidb\n num_images = len(roidb)\n # num_images = 100\n for i in xrange(num_images):\n im = cv2.imread(self.imdb.image_path_at(i))\n if roidb[i]['flipped']:\n im = im[:, ::-1, :]\n gt_inds = np.where(roidb[i]['gt_classes'] > 0)[0]\n gt_boxes = roidb[i]['boxes'][gt_inds]\n _t.tic()\n scores, boxes = im_detect(self.net, im, gt_boxes)\n _t.toc()\n feat = self.net.blobs[self.layer].data\n for j in xrange(1, self.imdb.num_classes):\n cls_inds = np.where(roidb[i]['gt_classes'][gt_inds] == j)[0]\n if len(cls_inds) > 0:\n cls_feat = feat[cls_inds, :]\n self.trainers[j].append_pos(cls_feat)\n\n print 'get_pos_examples: {:d}/{:d} {:.3f}s' \\\n .format(i + 1, len(roidb), _t.average_time)\n\n def initialize_net(self):\n # Start all SVM parameters at zero\n self.net.params['cls_score'][0].data[...] = 0\n self.net.params['cls_score'][1].data[...] = 0\n\n # Initialize SVMs in a smart way. Not doing this because its such\n # a good initialization that we might not learn something close to\n # the SVM solution.\n# # subtract background weights and biases for the foreground classes\n# w_bg = self.net.params['cls_score'][0].data[0, :]\n# b_bg = self.net.params['cls_score'][1].data[0]\n# self.net.params['cls_score'][0].data[1:, :] -= w_bg\n# self.net.params['cls_score'][1].data[1:] -= b_bg\n# # set the background weights and biases to 0 (where they shall remain)\n# self.net.params['cls_score'][0].data[0, :] = 0\n# self.net.params['cls_score'][1].data[0] = 0\n\n def update_net(self, cls_ind, w, b):\n self.net.params['cls_score'][0].data[cls_ind, :] = w\n self.net.params['cls_score'][1].data[cls_ind] = b\n\n def train_with_hard_negatives(self):\n _t = Timer()\n roidb = self.imdb.roidb\n num_images = len(roidb)\n # num_images = 100\n for i in xrange(num_images):\n im = cv2.imread(self.imdb.image_path_at(i))\n if roidb[i]['flipped']:\n im = im[:, ::-1, :]\n _t.tic()\n scores, boxes = im_detect(self.net, im, roidb[i]['boxes'])\n _t.toc()\n feat = self.net.blobs[self.layer].data\n for j in xrange(1, self.imdb.num_classes):\n hard_inds = \\\n np.where((scores[:, j] > self.hard_thresh) &\n (roidb[i]['gt_overlaps'][:, j].toarray().ravel() <\n self.neg_iou_thresh))[0]\n if len(hard_inds) > 0:\n hard_feat = feat[hard_inds, :].copy()\n new_w_b = \\\n self.trainers[j].append_neg_and_retrain(feat=hard_feat)\n if new_w_b is not None:\n self.update_net(j, new_w_b[0], new_w_b[1])\n\n print(('train_with_hard_negatives: '\n '{:d}/{:d} {:.3f}s').format(i + 1, len(roidb),\n _t.average_time))\n\n def train(self):\n # Initialize SVMs using\n # a. w_i = fc8_w_i - fc8_w_0\n # b. b_i = fc8_b_i - fc8_b_0\n # c. Install SVMs into net\n self.initialize_net()\n\n # Pass over roidb to count num positives for each class\n # a. Pre-allocate arrays for positive feature vectors\n # Pass over roidb, computing features for positives only\n self.get_pos_examples()\n\n # Pass over roidb\n # a. Compute cls_score with forward pass\n # b. For each class\n # i. Select hard negatives\n # ii. Add them to cache\n # c. For each class\n # i. If SVM retrain criteria met, update SVM\n # ii. Install new SVM into net\n self.train_with_hard_negatives()\n\n # One final SVM retraining for each class\n # Install SVMs into net\n for j in xrange(1, self.imdb.num_classes):\n new_w_b = self.trainers[j].append_neg_and_retrain(force=True)\n self.update_net(j, new_w_b[0], new_w_b[1])\n\nclass SVMClassTrainer(object):\n \"\"\"Manages post-hoc SVM training for a single object class.\"\"\"\n\n def __init__(self, cls, dim, feature_scale=1.0,\n C=0.001, B=10.0, pos_weight=2.0):\n self.pos = np.zeros((0, dim), dtype=np.float32)\n self.neg = np.zeros((0, dim), dtype=np.float32)\n self.B = B\n self.C = C\n self.cls = cls\n self.pos_weight = pos_weight\n self.dim = dim\n self.feature_scale = feature_scale\n self.svm = svm.LinearSVC(C=C, class_weight={1: 2, -1: 1},\n intercept_scaling=B, verbose=1,\n penalty='l2', loss='l1',\n random_state=cfg.RNG_SEED, dual=True)\n self.pos_cur = 0\n self.num_neg_added = 0\n self.retrain_limit = 2000\n self.evict_thresh = -1.1\n self.loss_history = []\n\n def alloc_pos(self, count):\n self.pos_cur = 0\n self.pos = np.zeros((count, self.dim), dtype=np.float32)\n\n def append_pos(self, feat):\n num = feat.shape[0]\n self.pos[self.pos_cur:self.pos_cur + num, :] = feat\n self.pos_cur += num\n\n def train(self):\n print('>>> Updating {} detector <<<'.format(self.cls))\n num_pos = self.pos.shape[0]\n num_neg = self.neg.shape[0]\n print('Cache holds {} pos examples and {} neg examples'.\n format(num_pos, num_neg))\n X = np.vstack((self.pos, self.neg)) * self.feature_scale\n y = np.hstack((np.ones(num_pos),\n -np.ones(num_neg)))\n self.svm.fit(X, y)\n w = self.svm.coef_\n b = self.svm.intercept_[0]\n scores = self.svm.decision_function(X)\n pos_scores = scores[:num_pos]\n neg_scores = scores[num_pos:]\n\n pos_loss = (self.C * self.pos_weight *\n np.maximum(0, 1 - pos_scores).sum())\n neg_loss = self.C * np.maximum(0, 1 + neg_scores).sum()\n reg_loss = 0.5 * np.dot(w.ravel(), w.ravel()) + 0.5 * b ** 2\n tot_loss = pos_loss + neg_loss + reg_loss\n self.loss_history.append((tot_loss, pos_loss, neg_loss, reg_loss))\n\n for i, losses in enumerate(self.loss_history):\n print((' {:d}: obj val: {:.3f} = {:.3f} '\n '(pos) + {:.3f} (neg) + {:.3f} (reg)').format(i, *losses))\n\n # Sanity check\n scores_ret = (\n X * 1.0 / self.feature_scale).dot(w.T * self.feature_scale) + b\n assert np.allclose(scores, scores_ret[:, 0], atol=1e-5), \\\n \"Scores from returned model don't match decision function\"\n\n return ((w * self.feature_scale, b), pos_scores, neg_scores)\n\n def append_neg_and_retrain(self, feat=None, force=False):\n if feat is not None:\n num = feat.shape[0]\n self.neg = np.vstack((self.neg, feat))\n self.num_neg_added += num\n if self.num_neg_added > self.retrain_limit or force:\n self.num_neg_added = 0\n new_w_b, pos_scores, neg_scores = self.train()\n # scores = np.dot(self.neg, new_w_b[0].T) + new_w_b[1]\n # easy_inds = np.where(neg_scores < self.evict_thresh)[0]\n not_easy_inds = np.where(neg_scores >= self.evict_thresh)[0]\n if len(not_easy_inds) > 0:\n self.neg = self.neg[not_easy_inds, :]\n # self.neg = np.delete(self.neg, easy_inds)\n print(' Pruning easy negatives')\n print(' Cache holds {} pos examples and {} neg examples'.\n format(self.pos.shape[0], self.neg.shape[0]))\n print(' {} pos support vectors'.format((pos_scores <= 1).sum()))\n print(' {} neg support vectors'.format((neg_scores >= -1).sum()))\n return new_w_b\n else:\n return None\n\ndef parse_args():\n \"\"\"\n Parse input arguments\n \"\"\"\n parser = argparse.ArgumentParser(description='Train SVMs (old skool)')\n parser.add_argument('--gpu', dest='gpu_id', help='GPU device id to use [0]',\n default=0, type=int)\n parser.add_argument('--def', dest='prototxt',\n help='prototxt file defining the network',\n default=None, type=str)\n parser.add_argument('--net', dest='caffemodel',\n help='model to test',\n default=None, type=str)\n parser.add_argument('--cfg', dest='cfg_file',\n help='optional config file', default=None, type=str)\n parser.add_argument('--imdb', dest='imdb_name',\n help='dataset to train on',\n default='voc_2007_trainval', type=str)\n\n if len(sys.argv) == 1:\n parser.print_help()\n sys.exit(1)\n\n args = parser.parse_args()\n return args\n\nif __name__ == '__main__':\n # Must turn this off to prevent issues when digging into the net blobs to\n # pull out features (tricky!)\n cfg.DEDUP_BOXES = 0\n\n # Must turn this on because we use the test im_detect() method to harvest\n # hard negatives\n cfg.TEST.SVM = True\n\n args = parse_args()\n\n print('Called with args:')\n print(args)\n\n if args.cfg_file is not None:\n cfg_from_file(args.cfg_file)\n\n print('Using config:')\n pprint.pprint(cfg)\n\n # fix the random seed for reproducibility\n np.random.seed(cfg.RNG_SEED)\n\n # set up caffe\n caffe.set_mode_gpu()\n if args.gpu_id is not None:\n caffe.set_device(args.gpu_id)\n net = caffe.Net(args.prototxt, args.caffemodel, caffe.TEST)\n net.name = os.path.splitext(os.path.basename(args.caffemodel))[0]\n out = os.path.splitext(os.path.basename(args.caffemodel))[0] + '_svm'\n out_dir = os.path.dirname(args.caffemodel)\n\n imdb = get_imdb(args.imdb_name)\n print 'Loaded dataset `{:s}` for training'.format(imdb.name)\n\n # enhance roidb to contain flipped examples\n if cfg.TRAIN.USE_FLIPPED:\n print 'Appending horizontally-flipped training examples...'\n imdb.append_flipped_images()\n print 'done'\n\n SVMTrainer(net, imdb).train()\n\n filename = '{}/{}.caffemodel'.format(out_dir, out)\n net.save(filename)\n print 'Wrote svm model to: {:s}'.format(filename)\n" } ]