[
{
"path": ".dockerignore",
"content": "/venv\n.git\n__pycache__\n"
},
{
"path": ".gitignore",
"content": "/.vscode\n__pycache__\n/venv\n"
},
{
"path": "Dockerfile",
"content": "FROM nvcr.io/nvidia/pytorch:21.02-py3\n\nRUN DEBIAN_FRONTEND=noninteractive apt-get -qq update \\\n && DEBIAN_FRONTEND=noninteractive apt-get -qqy install python3-pip ffmpeg git less nano libsm6 libxext6 libxrender-dev \\\n && rm -rf /var/lib/apt/lists/*\n\nCOPY . /app/\nWORKDIR /app\n\nRUN pip3 install --upgrade pip\nRUN pip3 install \\\n git+https://github.com/1adrianb/face-alignment \\\n -r requirements.txt\n"
},
{
"path": "LICENSE.md",
"content": "MIT License\n\nCopyright (c) 2019-2023 Aliaksandr Siarohin\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 all\ncopies 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": "!!! Check out our new [paper](https://arxiv.org/pdf/2104.11280.pdf) and [framework](https://github.com/snap-research/articulated-animation) improved for articulated objects\n\n# First Order Motion Model for Image Animation\n\nThis repository contains the source code for the paper [First Order Motion Model for Image Animation](https://papers.nips.cc/paper/8935-first-order-motion-model-for-image-animation) by Aliaksandr Siarohin, [Stéphane Lathuilière](http://stelat.eu), [Sergey Tulyakov](http://stulyakov.com), [Elisa Ricci](http://elisaricci.eu/) and [Nicu Sebe](http://disi.unitn.it/~sebe/). \n\n[Hugging Face Spaces](https://huggingface.co/spaces/abhishek/first-order-motion-model)\n\n## Example animations\n\nThe videos on the left show the driving videos. The first row on the right for each dataset shows the source videos. The bottom row contains the animated sequences with motion transferred from the driving video and object taken from the source image. We trained a separate network for each task.\n\n### VoxCeleb Dataset\n\n### Fashion Dataset\n\n### MGIF Dataset\n\n\n\n### Installation\n\nWe support ```python3```. To install the dependencies run:\n```\npip install -r requirements.txt\n```\n\n### YAML configs\n\nThere are several configuration (```config/dataset_name.yaml```) files one for each `dataset`. See ```config/taichi-256.yaml``` to get description of each parameter.\n\n\n### Pre-trained checkpoint\nCheckpoints can be found under following link: [google-drive](https://drive.google.com/open?id=1PyQJmkdCsAkOYwUyaj_l-l0as-iLDgeH) or [yandex-disk](https://yadi.sk/d/lEw8uRm140L_eQ).\n\n### Animation Demo\nTo run a demo, download checkpoint and run the following command:\n```\npython demo.py --config config/dataset_name.yaml --driving_video path/to/driving --source_image path/to/source --checkpoint path/to/checkpoint --relative --adapt_scale\n```\nThe result will be stored in ```result.mp4```.\n\nThe driving videos and source images should be cropped before it can be used in our method. To obtain some semi-automatic crop suggestions you can use ```python crop-video.py --inp some_youtube_video.mp4```. It will generate commands for crops using ffmpeg. In order to use the script, face-alligment library is needed:\n```\ngit clone https://github.com/1adrianb/face-alignment\ncd face-alignment\npip install -r requirements.txt\npython setup.py install\n```\n\n### Animation demo with Docker\n\nIf you are having trouble getting the demo to work because of library compatibility issues,\nand you're running Linux, you might try running it inside a Docker container, which would\ngive you better control over the execution environment.\n\nRequirements: Docker 19.03+ and [nvidia-docker](https://github.com/NVIDIA/nvidia-docker)\ninstalled and able to successfully run the `nvidia-docker` usage tests.\n\nWe'll first build the container.\n\n```\ndocker build -t first-order-model .\n```\n\nAnd now that we have the container available locally, we can use it to run the demo.\n\n```\ndocker run -it --rm --gpus all \\\n -v $HOME/first-order-model:/app first-order-model \\\n python3 demo.py --config config/vox-256.yaml \\\n --driving_video driving.mp4 \\\n --source_image source.png \\ \n --checkpoint vox-cpk.pth.tar \\ \n --result_video result.mp4 \\\n --relative --adapt_scale\n```\n\n### Colab Demo \n\n[](https://colab.research.google.com/github/AliaksandrSiarohin/first-order-model/blob/master/demo.ipynb) [](https://kaggle.com/kernels/welcome?src=https://github.com/AliaksandrSiarohin/first-order-model/blob/master/demo.ipynb)\n\n@graphemecluster prepared a GUI demo for the Google Colab. It also works in Kaggle. For the source code, see [```demo.ipynb```](https://github.com/AliaksandrSiarohin/first-order-model/blob/master/demo.ipynb).\n\nFor the old demo, see [```old_demo.ipynb```](https://github.com/AliaksandrSiarohin/first-order-model/blob/master/old_demo.ipynb).\n\n### Face-swap\nIt is possible to modify the method to perform face-swap using supervised segmentation masks.\n\nFor both unsupervised and supervised video editing, such as face-swap, please refer to [Motion Co-Segmentation](https://github.com/AliaksandrSiarohin/motion-cosegmentation).\n\n\n### Training\n\nTo train a model on specific dataset run:\n```\nCUDA_VISIBLE_DEVICES=0,1,2,3 python run.py --config config/dataset_name.yaml --device_ids 0,1,2,3\n```\nThe code will create a folder in the log directory (each run will create a time-stamped new directory).\nCheckpoints will be saved to this folder.\nTo check the loss values during training see ```log.txt```.\nYou can also check training data reconstructions in the ```train-vis``` subfolder.\nBy default the batch size is tuned to run on 2 or 4 Titan-X gpu (apart from speed it does not make much difference). You can change the batch size in the train_params in corresponding ```.yaml``` file.\n\n### Evaluation on video reconstruction\n\nTo evaluate the reconstruction performance run:\n```\nCUDA_VISIBLE_DEVICES=0 python run.py --config config/dataset_name.yaml --mode reconstruction --checkpoint path/to/checkpoint\n```\nYou will need to specify the path to the checkpoint,\nthe ```reconstruction``` subfolder will be created in the checkpoint folder.\nThe generated video will be stored to this folder, also generated videos will be stored in ```png``` subfolder in loss-less '.png' format for evaluation.\nInstructions for computing metrics from the paper can be found: https://github.com/AliaksandrSiarohin/pose-evaluation.\n\n### Image animation\n\nIn order to animate videos run:\n```\nCUDA_VISIBLE_DEVICES=0 python run.py --config config/dataset_name.yaml --mode animate --checkpoint path/to/checkpoint\n```\nYou will need to specify the path to the checkpoint,\nthe ```animation``` subfolder will be created in the same folder as the checkpoint.\nYou can find the generated video there and its loss-less version in the ```png``` subfolder.\nBy default video from test set will be randomly paired, but you can specify the \"source,driving\" pairs in the corresponding ```.csv``` files. The path to this file should be specified in corresponding ```.yaml``` file in pairs_list setting.\n\nThere are 2 different ways of performing animation:\nby using **absolute** keypoint locations or by using **relative** keypoint locations.\n\n1) Animation using absolute coordinates: the animation is performed using the absolute positions of the driving video and appearance of the source image.\nIn this way there are no specific requirements for the driving video and source appearance that is used.\nHowever this usually leads to poor performance since irrelevant details such as shape is transferred.\nCheck animate parameters in ```taichi-256.yaml``` to enable this mode.\n\n![](\"sup-mat/absolute-demo.gif\")
\n\n2) Animation using relative coordinates: from the driving video we first estimate the relative movement of each keypoint,\nthen we add this movement to the absolute position of keypoints in the source image.\nThis keypoint along with source image is used for animation. This usually leads to better performance, however this requires\nthat the object in the first frame of the video and in the source image have the same pose\n\n![](\"sup-mat/relative-demo.gif\")
\n\n\n### Datasets\n\n1) **Bair**. This dataset can be directly [downloaded](https://yadi.sk/d/Rr-fjn-PdmmqeA).\n\n2) **Mgif**. This dataset can be directly [downloaded](https://yadi.sk/d/5VdqLARizmnj3Q).\n\n3) **Fashion**. Follow the instruction on dataset downloading [from](https://vision.cs.ubc.ca/datasets/fashion/).\n\n4) **Taichi**. Follow the instructions in [data/taichi-loading](data/taichi-loading/README.md) or instructions from https://github.com/AliaksandrSiarohin/video-preprocessing. \n\n5) **Nemo**. Please follow the [instructions](https://www.uva-nemo.org/) on how to download the dataset. Then the dataset should be preprocessed using scripts from https://github.com/AliaksandrSiarohin/video-preprocessing.\n \n6) **VoxCeleb**. Please follow the instruction from https://github.com/AliaksandrSiarohin/video-preprocessing.\n\n\n### Training on your own dataset\n1) Resize all the videos to the same size e.g 256x256, the videos can be in '.gif', '.mp4' or folder with images.\nWe recommend the later, for each video make a separate folder with all the frames in '.png' format. This format is loss-less, and it has better i/o performance.\n\n2) Create a folder ```data/dataset_name``` with 2 subfolders ```train``` and ```test```, put training videos in the ```train``` and testing in the ```test```.\n\n3) Create a config ```config/dataset_name.yaml```, in dataset_params specify the root dir the ```root_dir: data/dataset_name```. Also adjust the number of epoch in train_params.\n\n#### Additional notes\n\nCitation:\n\n```\n@InProceedings{Siarohin_2019_NeurIPS,\n author={Siarohin, Aliaksandr and Lathuilière, Stéphane and Tulyakov, Sergey and Ricci, Elisa and Sebe, Nicu},\n title={First Order Motion Model for Image Animation},\n booktitle = {Conference on Neural Information Processing Systems (NeurIPS)},\n month = {December},\n year = {2019}\n}\n```\n"
},
{
"path": "animate.py",
"content": "import os\nfrom tqdm import tqdm\n\nimport torch\nfrom torch.utils.data import DataLoader\n\nfrom frames_dataset import PairedDataset\nfrom logger import Logger, Visualizer\nimport imageio\nfrom scipy.spatial import ConvexHull\nimport numpy as np\n\nfrom sync_batchnorm import DataParallelWithCallback\n\n\ndef normalize_kp(kp_source, kp_driving, kp_driving_initial, adapt_movement_scale=False,\n use_relative_movement=False, use_relative_jacobian=False):\n if adapt_movement_scale:\n source_area = ConvexHull(kp_source['value'][0].data.cpu().numpy()).volume\n driving_area = ConvexHull(kp_driving_initial['value'][0].data.cpu().numpy()).volume\n adapt_movement_scale = np.sqrt(source_area) / np.sqrt(driving_area)\n else:\n adapt_movement_scale = 1\n\n kp_new = {k: v for k, v in kp_driving.items()}\n\n if use_relative_movement:\n kp_value_diff = (kp_driving['value'] - kp_driving_initial['value'])\n kp_value_diff *= adapt_movement_scale\n kp_new['value'] = kp_value_diff + kp_source['value']\n\n if use_relative_jacobian:\n jacobian_diff = torch.matmul(kp_driving['jacobian'], torch.inverse(kp_driving_initial['jacobian']))\n kp_new['jacobian'] = torch.matmul(jacobian_diff, kp_source['jacobian'])\n\n return kp_new\n\n\ndef animate(config, generator, kp_detector, checkpoint, log_dir, dataset):\n log_dir = os.path.join(log_dir, 'animation')\n png_dir = os.path.join(log_dir, 'png')\n animate_params = config['animate_params']\n\n dataset = PairedDataset(initial_dataset=dataset, number_of_pairs=animate_params['num_pairs'])\n dataloader = DataLoader(dataset, batch_size=1, shuffle=False, num_workers=1)\n\n if checkpoint is not None:\n Logger.load_cpk(checkpoint, generator=generator, kp_detector=kp_detector)\n else:\n raise AttributeError(\"Checkpoint should be specified for mode='animate'.\")\n\n if not os.path.exists(log_dir):\n os.makedirs(log_dir)\n\n if not os.path.exists(png_dir):\n os.makedirs(png_dir)\n\n if torch.cuda.is_available():\n generator = DataParallelWithCallback(generator)\n kp_detector = DataParallelWithCallback(kp_detector)\n\n generator.eval()\n kp_detector.eval()\n\n for it, x in tqdm(enumerate(dataloader)):\n with torch.no_grad():\n predictions = []\n visualizations = []\n\n driving_video = x['driving_video']\n source_frame = x['source_video'][:, :, 0, :, :]\n\n kp_source = kp_detector(source_frame)\n kp_driving_initial = kp_detector(driving_video[:, :, 0])\n\n for frame_idx in range(driving_video.shape[2]):\n driving_frame = driving_video[:, :, frame_idx]\n kp_driving = kp_detector(driving_frame)\n kp_norm = normalize_kp(kp_source=kp_source, kp_driving=kp_driving,\n kp_driving_initial=kp_driving_initial, **animate_params['normalization_params'])\n out = generator(source_frame, kp_source=kp_source, kp_driving=kp_norm)\n\n out['kp_driving'] = kp_driving\n out['kp_source'] = kp_source\n out['kp_norm'] = kp_norm\n\n del out['sparse_deformed']\n\n predictions.append(np.transpose(out['prediction'].data.cpu().numpy(), [0, 2, 3, 1])[0])\n\n visualization = Visualizer(**config['visualizer_params']).visualize(source=source_frame,\n driving=driving_frame, out=out)\n visualization = visualization\n visualizations.append(visualization)\n\n predictions = np.concatenate(predictions, axis=1)\n result_name = \"-\".join([x['driving_name'][0], x['source_name'][0]])\n imageio.imsave(os.path.join(png_dir, result_name + '.png'), (255 * predictions).astype(np.uint8))\n\n image_name = result_name + animate_params['format']\n imageio.mimsave(os.path.join(log_dir, image_name), visualizations)\n"
},
{
"path": "augmentation.py",
"content": "\"\"\"\nCode from https://github.com/hassony2/torch_videovision\n\"\"\"\n\nimport numbers\n\nimport random\nimport numpy as np\nimport PIL\n\nfrom skimage.transform import resize, rotate\nfrom numpy import pad\nimport torchvision\n\nimport warnings\n\nfrom skimage import img_as_ubyte, img_as_float\n\n\ndef crop_clip(clip, min_h, min_w, h, w):\n if isinstance(clip[0], np.ndarray):\n cropped = [img[min_h:min_h + h, min_w:min_w + w, :] for img in clip]\n\n elif isinstance(clip[0], PIL.Image.Image):\n cropped = [\n img.crop((min_w, min_h, min_w + w, min_h + h)) for img in clip\n ]\n else:\n raise TypeError('Expected numpy.ndarray or PIL.Image' +\n 'but got list of {0}'.format(type(clip[0])))\n return cropped\n\n\ndef pad_clip(clip, h, w):\n im_h, im_w = clip[0].shape[:2]\n pad_h = (0, 0) if h < im_h else ((h - im_h) // 2, (h - im_h + 1) // 2)\n pad_w = (0, 0) if w < im_w else ((w - im_w) // 2, (w - im_w + 1) // 2)\n\n return pad(clip, ((0, 0), pad_h, pad_w, (0, 0)), mode='edge')\n\n\ndef resize_clip(clip, size, interpolation='bilinear'):\n if isinstance(clip[0], np.ndarray):\n if isinstance(size, numbers.Number):\n im_h, im_w, im_c = clip[0].shape\n # Min spatial dim already matches minimal size\n if (im_w <= im_h and im_w == size) or (im_h <= im_w\n and im_h == size):\n return clip\n new_h, new_w = get_resize_sizes(im_h, im_w, size)\n size = (new_w, new_h)\n else:\n size = size[1], size[0]\n\n scaled = [\n resize(img, size, order=1 if interpolation == 'bilinear' else 0, preserve_range=True,\n mode='constant', anti_aliasing=True) for img in clip\n ]\n elif isinstance(clip[0], PIL.Image.Image):\n if isinstance(size, numbers.Number):\n im_w, im_h = clip[0].size\n # Min spatial dim already matches minimal size\n if (im_w <= im_h and im_w == size) or (im_h <= im_w\n and im_h == size):\n return clip\n new_h, new_w = get_resize_sizes(im_h, im_w, size)\n size = (new_w, new_h)\n else:\n size = size[1], size[0]\n if interpolation == 'bilinear':\n pil_inter = PIL.Image.NEAREST\n else:\n pil_inter = PIL.Image.BILINEAR\n scaled = [img.resize(size, pil_inter) for img in clip]\n else:\n raise TypeError('Expected numpy.ndarray or PIL.Image' +\n 'but got list of {0}'.format(type(clip[0])))\n return scaled\n\n\ndef get_resize_sizes(im_h, im_w, size):\n if im_w < im_h:\n ow = size\n oh = int(size * im_h / im_w)\n else:\n oh = size\n ow = int(size * im_w / im_h)\n return oh, ow\n\n\nclass RandomFlip(object):\n def __init__(self, time_flip=False, horizontal_flip=False):\n self.time_flip = time_flip\n self.horizontal_flip = horizontal_flip\n\n def __call__(self, clip):\n if random.random() < 0.5 and self.time_flip:\n return clip[::-1]\n if random.random() < 0.5 and self.horizontal_flip:\n return [np.fliplr(img) for img in clip]\n\n return clip\n\n\nclass RandomResize(object):\n \"\"\"Resizes a list of (H x W x C) numpy.ndarray to the final size\n The larger the original image is, the more times it takes to\n interpolate\n Args:\n interpolation (str): Can be one of 'nearest', 'bilinear'\n defaults to nearest\n size (tuple): (widht, height)\n \"\"\"\n\n def __init__(self, ratio=(3. / 4., 4. / 3.), interpolation='nearest'):\n self.ratio = ratio\n self.interpolation = interpolation\n\n def __call__(self, clip):\n scaling_factor = random.uniform(self.ratio[0], self.ratio[1])\n\n if isinstance(clip[0], np.ndarray):\n im_h, im_w, im_c = clip[0].shape\n elif isinstance(clip[0], PIL.Image.Image):\n im_w, im_h = clip[0].size\n\n new_w = int(im_w * scaling_factor)\n new_h = int(im_h * scaling_factor)\n new_size = (new_w, new_h)\n resized = resize_clip(\n clip, new_size, interpolation=self.interpolation)\n\n return resized\n\n\nclass RandomCrop(object):\n \"\"\"Extract random crop at the same location for a list of videos\n Args:\n size (sequence or int): Desired output size for the\n crop in format (h, w)\n \"\"\"\n\n def __init__(self, size):\n if isinstance(size, numbers.Number):\n size = (size, size)\n\n self.size = size\n\n def __call__(self, clip):\n \"\"\"\n Args:\n img (PIL.Image or numpy.ndarray): List of videos to be cropped\n in format (h, w, c) in numpy.ndarray\n Returns:\n PIL.Image or numpy.ndarray: Cropped list of videos\n \"\"\"\n h, w = self.size\n if isinstance(clip[0], np.ndarray):\n im_h, im_w, im_c = clip[0].shape\n elif isinstance(clip[0], PIL.Image.Image):\n im_w, im_h = clip[0].size\n else:\n raise TypeError('Expected numpy.ndarray or PIL.Image' +\n 'but got list of {0}'.format(type(clip[0])))\n\n clip = pad_clip(clip, h, w)\n im_h, im_w = clip.shape[1:3]\n x1 = 0 if h == im_h else random.randint(0, im_w - w)\n y1 = 0 if w == im_w else random.randint(0, im_h - h)\n cropped = crop_clip(clip, y1, x1, h, w)\n\n return cropped\n\n\nclass RandomRotation(object):\n \"\"\"Rotate entire clip randomly by a random angle within\n given bounds\n Args:\n degrees (sequence or int): Range of degrees to select from\n If degrees is a number instead of sequence like (min, max),\n the range of degrees, will be (-degrees, +degrees).\n \"\"\"\n\n def __init__(self, degrees):\n if isinstance(degrees, numbers.Number):\n if degrees < 0:\n raise ValueError('If degrees is a single number,'\n 'must be positive')\n degrees = (-degrees, degrees)\n else:\n if len(degrees) != 2:\n raise ValueError('If degrees is a sequence,'\n 'it must be of len 2.')\n\n self.degrees = degrees\n\n def __call__(self, clip):\n \"\"\"\n Args:\n img (PIL.Image or numpy.ndarray): List of videos to be cropped\n in format (h, w, c) in numpy.ndarray\n Returns:\n PIL.Image or numpy.ndarray: Cropped list of videos\n \"\"\"\n angle = random.uniform(self.degrees[0], self.degrees[1])\n if isinstance(clip[0], np.ndarray):\n rotated = [rotate(image=img, angle=angle, preserve_range=True) for img in clip]\n elif isinstance(clip[0], PIL.Image.Image):\n rotated = [img.rotate(angle) for img in clip]\n else:\n raise TypeError('Expected numpy.ndarray or PIL.Image' +\n 'but got list of {0}'.format(type(clip[0])))\n\n return rotated\n\n\nclass ColorJitter(object):\n \"\"\"Randomly change the brightness, contrast and saturation and hue of the clip\n Args:\n brightness (float): How much to jitter brightness. brightness_factor\n is chosen uniformly from [max(0, 1 - brightness), 1 + brightness].\n contrast (float): How much to jitter contrast. contrast_factor\n is chosen uniformly from [max(0, 1 - contrast), 1 + contrast].\n saturation (float): How much to jitter saturation. saturation_factor\n is chosen uniformly from [max(0, 1 - saturation), 1 + saturation].\n hue(float): How much to jitter hue. hue_factor is chosen uniformly from\n [-hue, hue]. Should be >=0 and <= 0.5.\n \"\"\"\n\n def __init__(self, brightness=0, contrast=0, saturation=0, hue=0):\n self.brightness = brightness\n self.contrast = contrast\n self.saturation = saturation\n self.hue = hue\n\n def get_params(self, brightness, contrast, saturation, hue):\n if brightness > 0:\n brightness_factor = random.uniform(\n max(0, 1 - brightness), 1 + brightness)\n else:\n brightness_factor = None\n\n if contrast > 0:\n contrast_factor = random.uniform(\n max(0, 1 - contrast), 1 + contrast)\n else:\n contrast_factor = None\n\n if saturation > 0:\n saturation_factor = random.uniform(\n max(0, 1 - saturation), 1 + saturation)\n else:\n saturation_factor = None\n\n if hue > 0:\n hue_factor = random.uniform(-hue, hue)\n else:\n hue_factor = None\n return brightness_factor, contrast_factor, saturation_factor, hue_factor\n\n def __call__(self, clip):\n \"\"\"\n Args:\n clip (list): list of PIL.Image\n Returns:\n list PIL.Image : list of transformed PIL.Image\n \"\"\"\n if isinstance(clip[0], np.ndarray):\n brightness, contrast, saturation, hue = self.get_params(\n self.brightness, self.contrast, self.saturation, self.hue)\n\n # Create img transform function sequence\n img_transforms = []\n if brightness is not None:\n img_transforms.append(lambda img: torchvision.transforms.functional.adjust_brightness(img, brightness))\n if saturation is not None:\n img_transforms.append(lambda img: torchvision.transforms.functional.adjust_saturation(img, saturation))\n if hue is not None:\n img_transforms.append(lambda img: torchvision.transforms.functional.adjust_hue(img, hue))\n if contrast is not None:\n img_transforms.append(lambda img: torchvision.transforms.functional.adjust_contrast(img, contrast))\n random.shuffle(img_transforms)\n img_transforms = [img_as_ubyte, torchvision.transforms.ToPILImage()] + img_transforms + [np.array,\n img_as_float]\n\n with warnings.catch_warnings():\n warnings.simplefilter(\"ignore\")\n jittered_clip = []\n for img in clip:\n jittered_img = img\n for func in img_transforms:\n jittered_img = func(jittered_img)\n jittered_clip.append(jittered_img.astype('float32'))\n elif isinstance(clip[0], PIL.Image.Image):\n brightness, contrast, saturation, hue = self.get_params(\n self.brightness, self.contrast, self.saturation, self.hue)\n\n # Create img transform function sequence\n img_transforms = []\n if brightness is not None:\n img_transforms.append(lambda img: torchvision.transforms.functional.adjust_brightness(img, brightness))\n if saturation is not None:\n img_transforms.append(lambda img: torchvision.transforms.functional.adjust_saturation(img, saturation))\n if hue is not None:\n img_transforms.append(lambda img: torchvision.transforms.functional.adjust_hue(img, hue))\n if contrast is not None:\n img_transforms.append(lambda img: torchvision.transforms.functional.adjust_contrast(img, contrast))\n random.shuffle(img_transforms)\n\n # Apply to all videos\n jittered_clip = []\n for img in clip:\n for func in img_transforms:\n jittered_img = func(img)\n jittered_clip.append(jittered_img)\n\n else:\n raise TypeError('Expected numpy.ndarray or PIL.Image' +\n 'but got list of {0}'.format(type(clip[0])))\n return jittered_clip\n\n\nclass AllAugmentationTransform:\n def __init__(self, resize_param=None, rotation_param=None, flip_param=None, crop_param=None, jitter_param=None):\n self.transforms = []\n\n if flip_param is not None:\n self.transforms.append(RandomFlip(**flip_param))\n\n if rotation_param is not None:\n self.transforms.append(RandomRotation(**rotation_param))\n\n if resize_param is not None:\n self.transforms.append(RandomResize(**resize_param))\n\n if crop_param is not None:\n self.transforms.append(RandomCrop(**crop_param))\n\n if jitter_param is not None:\n self.transforms.append(ColorJitter(**jitter_param))\n\n def __call__(self, clip):\n for t in self.transforms:\n clip = t(clip)\n return clip\n"
},
{
"path": "config/bair-256.yaml",
"content": "dataset_params:\n root_dir: data/bair\n frame_shape: [256, 256, 3]\n id_sampling: False\n augmentation_params:\n flip_param:\n horizontal_flip: True\n time_flip: True\n jitter_param:\n brightness: 0.1\n contrast: 0.1\n saturation: 0.1\n hue: 0.1\n\n\nmodel_params:\n common_params:\n num_kp: 10\n num_channels: 3\n estimate_jacobian: True\n kp_detector_params:\n temperature: 0.1\n block_expansion: 32\n max_features: 1024\n scale_factor: 0.25\n num_blocks: 5\n generator_params:\n block_expansion: 64\n max_features: 512\n num_down_blocks: 2\n num_bottleneck_blocks: 6\n estimate_occlusion_map: True\n dense_motion_params:\n block_expansion: 64\n max_features: 1024\n num_blocks: 5\n scale_factor: 0.25\n discriminator_params:\n scales: [1]\n block_expansion: 32\n max_features: 512\n num_blocks: 4\n sn: True\n\ntrain_params:\n num_epochs: 20\n num_repeats: 1\n epoch_milestones: [12, 18]\n lr_generator: 2.0e-4\n lr_discriminator: 2.0e-4\n lr_kp_detector: 2.0e-4\n batch_size: 36\n scales: [1, 0.5, 0.25, 0.125]\n checkpoint_freq: 10\n transform_params:\n sigma_affine: 0.05\n sigma_tps: 0.005\n points_tps: 5\n loss_weights:\n generator_gan: 1\n discriminator_gan: 1\n feature_matching: [10, 10, 10, 10]\n perceptual: [10, 10, 10, 10, 10]\n equivariance_value: 10\n equivariance_jacobian: 10\n\nreconstruction_params:\n num_videos: 1000\n format: '.mp4'\n\nanimate_params:\n num_pairs: 50\n format: '.mp4'\n normalization_params:\n adapt_movement_scale: False\n use_relative_movement: True\n use_relative_jacobian: True\n\nvisualizer_params:\n kp_size: 5\n draw_border: True\n colormap: 'gist_rainbow'\n"
},
{
"path": "config/fashion-256.yaml",
"content": "dataset_params:\n root_dir: data/fashion-png\n frame_shape: [256, 256, 3]\n id_sampling: False\n augmentation_params:\n flip_param:\n horizontal_flip: True\n time_flip: True\n jitter_param:\n hue: 0.1\n\nmodel_params:\n common_params:\n num_kp: 10\n num_channels: 3\n estimate_jacobian: True\n kp_detector_params:\n temperature: 0.1\n block_expansion: 32\n max_features: 1024\n scale_factor: 0.25\n num_blocks: 5\n generator_params:\n block_expansion: 64\n max_features: 512\n num_down_blocks: 2\n num_bottleneck_blocks: 6\n estimate_occlusion_map: True\n dense_motion_params:\n block_expansion: 64\n max_features: 1024\n num_blocks: 5\n scale_factor: 0.25\n discriminator_params:\n scales: [1]\n block_expansion: 32\n max_features: 512\n num_blocks: 4\n\ntrain_params:\n num_epochs: 100\n num_repeats: 50\n epoch_milestones: [60, 90]\n lr_generator: 2.0e-4\n lr_discriminator: 2.0e-4\n lr_kp_detector: 2.0e-4\n batch_size: 27\n scales: [1, 0.5, 0.25, 0.125]\n checkpoint_freq: 50\n transform_params:\n sigma_affine: 0.05\n sigma_tps: 0.005\n points_tps: 5\n loss_weights:\n generator_gan: 1\n discriminator_gan: 1\n feature_matching: [10, 10, 10, 10]\n perceptual: [10, 10, 10, 10, 10]\n equivariance_value: 10\n equivariance_jacobian: 10\n\nreconstruction_params:\n num_videos: 1000\n format: '.mp4'\n\nanimate_params:\n num_pairs: 50\n format: '.mp4'\n normalization_params:\n adapt_movement_scale: False\n use_relative_movement: True\n use_relative_jacobian: True\n\nvisualizer_params:\n kp_size: 5\n draw_border: True\n colormap: 'gist_rainbow'\n"
},
{
"path": "config/mgif-256.yaml",
"content": "dataset_params:\n root_dir: data/moving-gif\n frame_shape: [256, 256, 3]\n id_sampling: False\n augmentation_params:\n flip_param:\n horizontal_flip: True\n time_flip: True\n crop_param:\n size: [256, 256]\n resize_param:\n ratio: [0.9, 1.1]\n jitter_param:\n hue: 0.5\n\nmodel_params:\n common_params:\n num_kp: 10\n num_channels: 3\n estimate_jacobian: True\n kp_detector_params:\n temperature: 0.1\n block_expansion: 32\n max_features: 1024\n scale_factor: 0.25\n num_blocks: 5\n single_jacobian_map: True\n generator_params:\n block_expansion: 64\n max_features: 512\n num_down_blocks: 2\n num_bottleneck_blocks: 6\n estimate_occlusion_map: True\n dense_motion_params:\n block_expansion: 64\n max_features: 1024\n num_blocks: 5\n scale_factor: 0.25\n discriminator_params:\n scales: [1]\n block_expansion: 32\n max_features: 512\n num_blocks: 4\n sn: True\n\ntrain_params:\n num_epochs: 100\n num_repeats: 25\n epoch_milestones: [60, 90]\n lr_generator: 2.0e-4\n lr_discriminator: 2.0e-4\n lr_kp_detector: 2.0e-4\n \n batch_size: 36\n scales: [1, 0.5, 0.25, 0.125]\n checkpoint_freq: 100\n transform_params:\n sigma_affine: 0.05\n sigma_tps: 0.005\n points_tps: 5\n loss_weights:\n generator_gan: 1\n discriminator_gan: 1\n feature_matching: [10, 10, 10, 10]\n perceptual: [10, 10, 10, 10, 10]\n equivariance_value: 10\n equivariance_jacobian: 10\n\nreconstruction_params:\n num_videos: 1000\n format: '.mp4'\n\nanimate_params:\n num_pairs: 50\n format: '.mp4'\n normalization_params:\n adapt_movement_scale: False\n use_relative_movement: True\n use_relative_jacobian: True\n\nvisualizer_params:\n kp_size: 5\n draw_border: True\n colormap: 'gist_rainbow'\n"
},
{
"path": "config/nemo-256.yaml",
"content": "dataset_params:\n root_dir: data/nemo-png \n frame_shape: [256, 256, 3]\n id_sampling: False\n augmentation_params:\n flip_param:\n horizontal_flip: True\n time_flip: True\n\nmodel_params:\n common_params:\n num_kp: 10\n num_channels: 3\n estimate_jacobian: True\n kp_detector_params:\n temperature: 0.1\n block_expansion: 32\n max_features: 1024\n scale_factor: 0.25\n num_blocks: 5\n generator_params:\n block_expansion: 64\n max_features: 512\n num_down_blocks: 2\n num_bottleneck_blocks: 6\n estimate_occlusion_map: True\n dense_motion_params:\n block_expansion: 64\n max_features: 1024\n num_blocks: 5\n scale_factor: 0.25\n discriminator_params:\n scales: [1]\n block_expansion: 32\n max_features: 512\n num_blocks: 4\n sn: True\n\ntrain_params:\n num_epochs: 100\n num_repeats: 8\n epoch_milestones: [60, 90]\n lr_generator: 2.0e-4\n lr_discriminator: 2.0e-4\n lr_kp_detector: 2.0e-4\n batch_size: 36\n scales: [1, 0.5, 0.25, 0.125]\n checkpoint_freq: 50\n transform_params:\n sigma_affine: 0.05\n sigma_tps: 0.005\n points_tps: 5\n loss_weights:\n generator_gan: 1\n discriminator_gan: 1\n feature_matching: [10, 10, 10, 10]\n perceptual: [10, 10, 10, 10, 10]\n equivariance_value: 10\n equivariance_jacobian: 10\n\nreconstruction_params:\n num_videos: 1000\n format: '.mp4'\n\nanimate_params:\n num_pairs: 50\n format: '.mp4'\n normalization_params:\n adapt_movement_scale: False\n use_relative_movement: True\n use_relative_jacobian: True\n\nvisualizer_params:\n kp_size: 5\n draw_border: True\n colormap: 'gist_rainbow'\n"
},
{
"path": "config/taichi-256.yaml",
"content": "# Dataset parameters\n# Each dataset should contain 2 folders train and test\n# Each video can be represented as:\n# - an image of concatenated frames\n# - '.mp4' or '.gif'\n# - folder with all frames from a specific video\n# In case of Taichi. Same (youtube) video can be splitted in many parts (chunks). Each part has a following\n# format (id)#other#info.mp4. For example '12335#adsbf.mp4' has an id 12335. In case of TaiChi id stands for youtube\n# video id.\ndataset_params:\n # Path to data, data can be stored in several formats: .mp4 or .gif videos, stacked .png images or folders with frames.\n root_dir: data/taichi-png\n # Image shape, needed for staked .png format.\n frame_shape: [256, 256, 3]\n # In case of TaiChi single video can be splitted in many chunks, or the maybe several videos for single person.\n # In this case epoch can be a pass over different videos (if id_sampling=True) or over different chunks (if id_sampling=False)\n # If the name of the video '12335#adsbf.mp4' the id is assumed to be 12335\n id_sampling: True\n # List with pairs for animation, None for random pairs\n pairs_list: data/taichi256.csv\n # Augmentation parameters see augmentation.py for all posible augmentations\n augmentation_params:\n flip_param:\n horizontal_flip: True\n time_flip: True\n jitter_param:\n brightness: 0.1\n contrast: 0.1\n saturation: 0.1\n hue: 0.1\n\n# Defines model architecture\nmodel_params:\n common_params:\n # Number of keypoint\n num_kp: 10\n # Number of channels per image\n num_channels: 3\n # Using first or zero order model\n estimate_jacobian: True\n kp_detector_params:\n # Softmax temperature for keypoint heatmaps\n temperature: 0.1\n # Number of features mutliplier\n block_expansion: 32\n # Maximum allowed number of features\n max_features: 1024\n # Number of block in Unet. Can be increased or decreased depending or resolution.\n num_blocks: 5\n # Keypioint is predicted on smaller images for better performance,\n # scale_factor=0.25 means that 256x256 image will be resized to 64x64\n scale_factor: 0.25\n generator_params:\n # Number of features mutliplier\n block_expansion: 64\n # Maximum allowed number of features\n max_features: 512\n # Number of downsampling blocks in Jonson architecture.\n # Can be increased or decreased depending or resolution.\n num_down_blocks: 2\n # Number of ResBlocks in Jonson architecture.\n num_bottleneck_blocks: 6\n # Use occlusion map or not\n estimate_occlusion_map: True\n\n dense_motion_params:\n # Number of features mutliplier\n block_expansion: 64\n # Maximum allowed number of features\n max_features: 1024\n # Number of block in Unet. Can be increased or decreased depending or resolution.\n num_blocks: 5\n # Dense motion is predicted on smaller images for better performance,\n # scale_factor=0.25 means that 256x256 image will be resized to 64x64\n scale_factor: 0.25\n discriminator_params:\n # Discriminator can be multiscale, if you want 2 discriminator on original\n # resolution and half of the original, specify scales: [1, 0.5]\n scales: [1]\n # Number of features mutliplier\n block_expansion: 32\n # Maximum allowed number of features\n max_features: 512\n # Number of blocks. Can be increased or decreased depending or resolution.\n num_blocks: 4\n\n# Parameters of training\ntrain_params:\n # Number of training epochs \n num_epochs: 100\n # For better i/o performance when number of videos is small number of epochs can be multiplied by this number.\n # Thus effectivlly with num_repeats=100 each epoch is 100 times larger. \n num_repeats: 150\n # Drop learning rate by 10 times after this epochs \n epoch_milestones: [60, 90]\n # Initial learing rate for all modules\n lr_generator: 2.0e-4\n lr_discriminator: 2.0e-4\n lr_kp_detector: 2.0e-4\n batch_size: 30\n # Scales for perceptual pyramide loss. If scales = [1, 0.5, 0.25, 0.125] and image resolution is 256x256,\n # than the loss will be computer on resolutions 256x256, 128x128, 64x64, 32x32.\n scales: [1, 0.5, 0.25, 0.125]\n # Save checkpoint this frequently. If checkpoint_freq=50, checkpoint will be saved every 50 epochs.\n checkpoint_freq: 50\n # Parameters of transform for equivariance loss\n transform_params:\n # Sigma for affine part\n sigma_affine: 0.05\n # Sigma for deformation part\n sigma_tps: 0.005\n # Number of point in the deformation grid\n points_tps: 5\n loss_weights:\n # Weight for LSGAN loss in generator, 0 for no adversarial loss.\n generator_gan: 0\n # Weight for LSGAN loss in discriminator\n discriminator_gan: 1\n # Weights for feature matching loss, the number should be the same as number of blocks in discriminator.\n feature_matching: [10, 10, 10, 10]\n # Weights for perceptual loss.\n perceptual: [10, 10, 10, 10, 10]\n # Weights for value equivariance.\n equivariance_value: 10\n # Weights for jacobian equivariance.\n equivariance_jacobian: 10\n\n# Parameters of reconstruction\nreconstruction_params:\n # Maximum number of videos for reconstruction\n num_videos: 1000\n # Format for visualization, note that results will be also stored in staked .png.\n format: '.mp4'\n\n# Parameters of animation\nanimate_params:\n # Maximum number of pairs for animation, the pairs will be either taken from pairs_list or random.\n num_pairs: 50\n # Format for visualization, note that results will be also stored in staked .png.\n format: '.mp4'\n # Normalization of diriving keypoints\n normalization_params:\n # Increase or decrease relative movement scale depending on the size of the object\n adapt_movement_scale: False\n # Apply only relative displacement of the keypoint\n use_relative_movement: True\n # Apply only relative change in jacobian\n use_relative_jacobian: True\n\n# Visualization parameters\nvisualizer_params:\n # Draw keypoints of this size, increase or decrease depending on resolution\n kp_size: 5\n # Draw white border around images\n draw_border: True\n # Color map for keypoints\n colormap: 'gist_rainbow'\n"
},
{
"path": "config/taichi-adv-256.yaml",
"content": "# Dataset parameters\ndataset_params:\n # Path to data, data can be stored in several formats: .mp4 or .gif videos, stacked .png images or folders with frames.\n root_dir: data/taichi-png\n # Image shape, needed for staked .png format.\n frame_shape: [256, 256, 3]\n # In case of TaiChi single video can be splitted in many chunks, or the maybe several videos for single person.\n # In this case epoch can be a pass over different videos (if id_sampling=True) or over different chunks (if id_sampling=False)\n # If the name of the video '12335#adsbf.mp4' the id is assumed to be 12335\n id_sampling: True\n # List with pairs for animation, None for random pairs\n pairs_list: data/taichi256.csv\n # Augmentation parameters see augmentation.py for all posible augmentations\n augmentation_params:\n flip_param:\n horizontal_flip: True\n time_flip: True\n jitter_param:\n brightness: 0.1\n contrast: 0.1\n saturation: 0.1\n hue: 0.1\n\n# Defines model architecture\nmodel_params:\n common_params:\n # Number of keypoint\n num_kp: 10\n # Number of channels per image\n num_channels: 3\n # Using first or zero order model\n estimate_jacobian: True\n kp_detector_params:\n # Softmax temperature for keypoint heatmaps\n temperature: 0.1\n # Number of features mutliplier\n block_expansion: 32\n # Maximum allowed number of features\n max_features: 1024\n # Number of block in Unet. Can be increased or decreased depending or resolution.\n num_blocks: 5\n # Keypioint is predicted on smaller images for better performance,\n # scale_factor=0.25 means that 256x256 image will be resized to 64x64\n scale_factor: 0.25\n generator_params:\n # Number of features mutliplier\n block_expansion: 64\n # Maximum allowed number of features\n max_features: 512\n # Number of downsampling blocks in Jonson architecture.\n # Can be increased or decreased depending or resolution.\n num_down_blocks: 2\n # Number of ResBlocks in Jonson architecture.\n num_bottleneck_blocks: 6\n # Use occlusion map or not\n estimate_occlusion_map: True\n\n dense_motion_params:\n # Number of features mutliplier\n block_expansion: 64\n # Maximum allowed number of features\n max_features: 1024\n # Number of block in Unet. Can be increased or decreased depending or resolution.\n num_blocks: 5\n # Dense motion is predicted on smaller images for better performance,\n # scale_factor=0.25 means that 256x256 image will be resized to 64x64\n scale_factor: 0.25\n discriminator_params:\n # Discriminator can be multiscale, if you want 2 discriminator on original\n # resolution and half of the original, specify scales: [1, 0.5]\n scales: [1]\n # Number of features mutliplier\n block_expansion: 32\n # Maximum allowed number of features\n max_features: 512\n # Number of blocks. Can be increased or decreased depending or resolution.\n num_blocks: 4\n use_kp: True\n\n# Parameters of training\ntrain_params:\n # Number of training epochs \n num_epochs: 150\n # For better i/o performance when number of videos is small number of epochs can be multiplied by this number.\n # Thus effectivlly with num_repeats=100 each epoch is 100 times larger. \n num_repeats: 150\n # Drop learning rate by 10 times after this epochs \n epoch_milestones: []\n # Initial learing rate for all modules\n lr_generator: 2.0e-4\n lr_discriminator: 2.0e-4\n lr_kp_detector: 0\n batch_size: 27\n # Scales for perceptual pyramide loss. If scales = [1, 0.5, 0.25, 0.125] and image resolution is 256x256,\n # than the loss will be computer on resolutions 256x256, 128x128, 64x64, 32x32.\n scales: [1, 0.5, 0.25, 0.125]\n # Save checkpoint this frequently. If checkpoint_freq=50, checkpoint will be saved every 50 epochs.\n checkpoint_freq: 50\n # Parameters of transform for equivariance loss\n transform_params:\n # Sigma for affine part\n sigma_affine: 0.05\n # Sigma for deformation part\n sigma_tps: 0.005\n # Number of point in the deformation grid\n points_tps: 5\n loss_weights:\n # Weight for LSGAN loss in generator\n generator_gan: 1\n # Weight for LSGAN loss in discriminator\n discriminator_gan: 1\n # Weights for feature matching loss, the number should be the same as number of blocks in discriminator.\n feature_matching: [10, 10, 10, 10]\n # Weights for perceptual loss.\n perceptual: [10, 10, 10, 10, 10]\n # Weights for value equivariance.\n equivariance_value: 10\n # Weights for jacobian equivariance.\n equivariance_jacobian: 10\n\n# Parameters of reconstruction\nreconstruction_params:\n # Maximum number of videos for reconstruction\n num_videos: 1000\n # Format for visualization, note that results will be also stored in staked .png.\n format: '.mp4'\n\n# Parameters of animation\nanimate_params:\n # Maximum number of pairs for animation, the pairs will be either taken from pairs_list or random.\n num_pairs: 50\n # Format for visualization, note that results will be also stored in staked .png.\n format: '.mp4'\n # Normalization of diriving keypoints\n normalization_params:\n # Increase or decrease relative movement scale depending on the size of the object\n adapt_movement_scale: False\n # Apply only relative displacement of the keypoint\n use_relative_movement: True\n # Apply only relative change in jacobian\n use_relative_jacobian: True\n\n# Visualization parameters\nvisualizer_params:\n # Draw keypoints of this size, increase or decrease depending on resolution\n kp_size: 5\n # Draw white border around images\n draw_border: True\n # Color map for keypoints\n colormap: 'gist_rainbow'\n"
},
{
"path": "config/vox-256.yaml",
"content": "dataset_params:\n root_dir: data/vox-png\n frame_shape: [256, 256, 3]\n id_sampling: True\n pairs_list: data/vox256.csv\n augmentation_params:\n flip_param:\n horizontal_flip: True\n time_flip: True\n jitter_param:\n brightness: 0.1\n contrast: 0.1\n saturation: 0.1\n hue: 0.1\n\n\nmodel_params:\n common_params:\n num_kp: 10\n num_channels: 3\n estimate_jacobian: True\n kp_detector_params:\n temperature: 0.1\n block_expansion: 32\n max_features: 1024\n scale_factor: 0.25\n num_blocks: 5\n generator_params:\n block_expansion: 64\n max_features: 512\n num_down_blocks: 2\n num_bottleneck_blocks: 6\n estimate_occlusion_map: True\n dense_motion_params:\n block_expansion: 64\n max_features: 1024\n num_blocks: 5\n scale_factor: 0.25\n discriminator_params:\n scales: [1]\n block_expansion: 32\n max_features: 512\n num_blocks: 4\n sn: True\n\ntrain_params:\n num_epochs: 100\n num_repeats: 75\n epoch_milestones: [60, 90]\n lr_generator: 2.0e-4\n lr_discriminator: 2.0e-4\n lr_kp_detector: 2.0e-4\n batch_size: 40\n scales: [1, 0.5, 0.25, 0.125]\n checkpoint_freq: 50\n transform_params:\n sigma_affine: 0.05\n sigma_tps: 0.005\n points_tps: 5\n loss_weights:\n generator_gan: 0\n discriminator_gan: 1\n feature_matching: [10, 10, 10, 10]\n perceptual: [10, 10, 10, 10, 10]\n equivariance_value: 10\n equivariance_jacobian: 10\n\nreconstruction_params:\n num_videos: 1000\n format: '.mp4'\n\nanimate_params:\n num_pairs: 50\n format: '.mp4'\n normalization_params:\n adapt_movement_scale: False\n use_relative_movement: True\n use_relative_jacobian: True\n\nvisualizer_params:\n kp_size: 5\n draw_border: True\n colormap: 'gist_rainbow'\n"
},
{
"path": "config/vox-adv-256.yaml",
"content": "dataset_params:\n root_dir: data/vox-png\n frame_shape: [256, 256, 3]\n id_sampling: True\n pairs_list: data/vox256.csv\n augmentation_params:\n flip_param:\n horizontal_flip: True\n time_flip: True\n jitter_param:\n brightness: 0.1\n contrast: 0.1\n saturation: 0.1\n hue: 0.1\n\n\nmodel_params:\n common_params:\n num_kp: 10\n num_channels: 3\n estimate_jacobian: True\n kp_detector_params:\n temperature: 0.1\n block_expansion: 32\n max_features: 1024\n scale_factor: 0.25\n num_blocks: 5\n generator_params:\n block_expansion: 64\n max_features: 512\n num_down_blocks: 2\n num_bottleneck_blocks: 6\n estimate_occlusion_map: True\n dense_motion_params:\n block_expansion: 64\n max_features: 1024\n num_blocks: 5\n scale_factor: 0.25\n discriminator_params:\n scales: [1]\n block_expansion: 32\n max_features: 512\n num_blocks: 4\n use_kp: True\n\n\ntrain_params:\n num_epochs: 150\n num_repeats: 75\n epoch_milestones: []\n lr_generator: 2.0e-4\n lr_discriminator: 2.0e-4\n lr_kp_detector: 2.0e-4\n batch_size: 36\n scales: [1, 0.5, 0.25, 0.125]\n checkpoint_freq: 50\n transform_params:\n sigma_affine: 0.05\n sigma_tps: 0.005\n points_tps: 5\n loss_weights:\n generator_gan: 1\n discriminator_gan: 1\n feature_matching: [10, 10, 10, 10]\n perceptual: [10, 10, 10, 10, 10]\n equivariance_value: 10\n equivariance_jacobian: 10\n\nreconstruction_params:\n num_videos: 1000\n format: '.mp4'\n\nanimate_params:\n num_pairs: 50\n format: '.mp4'\n normalization_params:\n adapt_movement_scale: False\n use_relative_movement: True\n use_relative_jacobian: True\n\nvisualizer_params:\n kp_size: 5\n draw_border: True\n colormap: 'gist_rainbow'\n"
},
{
"path": "crop-video.py",
"content": "import face_alignment\nimport skimage.io\nimport numpy\nfrom argparse import ArgumentParser\nfrom skimage import img_as_ubyte\nfrom skimage.transform import resize\nfrom tqdm import tqdm\nimport os\nimport imageio\nimport numpy as np\nimport warnings\nwarnings.filterwarnings(\"ignore\")\n\ndef extract_bbox(frame, fa):\n if max(frame.shape[0], frame.shape[1]) > 640:\n scale_factor = max(frame.shape[0], frame.shape[1]) / 640.0\n frame = resize(frame, (int(frame.shape[0] / scale_factor), int(frame.shape[1] / scale_factor)))\n frame = img_as_ubyte(frame)\n else:\n scale_factor = 1\n frame = frame[..., :3]\n bboxes = fa.face_detector.detect_from_image(frame[..., ::-1])\n if len(bboxes) == 0:\n return []\n return np.array(bboxes)[:, :-1] * scale_factor\n\n\n\ndef bb_intersection_over_union(boxA, boxB):\n xA = max(boxA[0], boxB[0])\n yA = max(boxA[1], boxB[1])\n xB = min(boxA[2], boxB[2])\n yB = min(boxA[3], boxB[3])\n interArea = max(0, xB - xA + 1) * max(0, yB - yA + 1)\n boxAArea = (boxA[2] - boxA[0] + 1) * (boxA[3] - boxA[1] + 1)\n boxBArea = (boxB[2] - boxB[0] + 1) * (boxB[3] - boxB[1] + 1)\n iou = interArea / float(boxAArea + boxBArea - interArea)\n return iou\n\n\ndef join(tube_bbox, bbox):\n xA = min(tube_bbox[0], bbox[0])\n yA = min(tube_bbox[1], bbox[1])\n xB = max(tube_bbox[2], bbox[2])\n yB = max(tube_bbox[3], bbox[3])\n return (xA, yA, xB, yB)\n\n\ndef compute_bbox(start, end, fps, tube_bbox, frame_shape, inp, image_shape, increase_area=0.1):\n left, top, right, bot = tube_bbox\n width = right - left\n height = bot - top\n\n #Computing aspect preserving bbox\n width_increase = max(increase_area, ((1 + 2 * increase_area) * height - width) / (2 * width))\n height_increase = max(increase_area, ((1 + 2 * increase_area) * width - height) / (2 * height))\n\n left = int(left - width_increase * width)\n top = int(top - height_increase * height)\n right = int(right + width_increase * width)\n bot = int(bot + height_increase * height)\n\n top, bot, left, right = max(0, top), min(bot, frame_shape[0]), max(0, left), min(right, frame_shape[1])\n h, w = bot - top, right - left\n\n start = start / fps\n end = end / fps\n time = end - start\n\n scale = f'{image_shape[0]}:{image_shape[1]}'\n\n return f'ffmpeg -i {inp} -ss {start} -t {time} -filter:v \"crop={w}:{h}:{left}:{top}, scale={scale}\" crop.mp4'\n\n\ndef compute_bbox_trajectories(trajectories, fps, frame_shape, args):\n commands = []\n for i, (bbox, tube_bbox, start, end) in enumerate(trajectories):\n if (end - start) > args.min_frames:\n command = compute_bbox(start, end, fps, tube_bbox, frame_shape, inp=args.inp, image_shape=args.image_shape, increase_area=args.increase)\n commands.append(command)\n return commands\n\n\ndef process_video(args):\n device = 'cpu' if args.cpu else 'cuda'\n fa = face_alignment.FaceAlignment(face_alignment.LandmarksType._2D, flip_input=False, device=device)\n video = imageio.get_reader(args.inp)\n\n trajectories = []\n previous_frame = None\n fps = video.get_meta_data()['fps']\n commands = []\n try:\n for i, frame in tqdm(enumerate(video)):\n frame_shape = frame.shape\n bboxes = extract_bbox(frame, fa)\n ## For each trajectory check the criterion\n not_valid_trajectories = []\n valid_trajectories = []\n\n for trajectory in trajectories:\n tube_bbox = trajectory[0]\n intersection = 0\n for bbox in bboxes:\n intersection = max(intersection, bb_intersection_over_union(tube_bbox, bbox))\n if intersection > args.iou_with_initial:\n valid_trajectories.append(trajectory)\n else:\n not_valid_trajectories.append(trajectory)\n\n commands += compute_bbox_trajectories(not_valid_trajectories, fps, frame_shape, args)\n trajectories = valid_trajectories\n\n ## Assign bbox to trajectories, create new trajectories\n for bbox in bboxes:\n intersection = 0\n current_trajectory = None\n for trajectory in trajectories:\n tube_bbox = trajectory[0]\n current_intersection = bb_intersection_over_union(tube_bbox, bbox)\n if intersection < current_intersection and current_intersection > args.iou_with_initial:\n intersection = bb_intersection_over_union(tube_bbox, bbox)\n current_trajectory = trajectory\n\n ## Create new trajectory\n if current_trajectory is None:\n trajectories.append([bbox, bbox, i, i])\n else:\n current_trajectory[3] = i\n current_trajectory[1] = join(current_trajectory[1], bbox)\n\n\n except IndexError as e:\n raise (e)\n\n commands += compute_bbox_trajectories(trajectories, fps, frame_shape, args)\n return commands\n\n\nif __name__ == \"__main__\":\n parser = ArgumentParser()\n\n parser.add_argument(\"--image_shape\", default=(256, 256), type=lambda x: tuple(map(int, x.split(','))),\n help=\"Image shape\")\n parser.add_argument(\"--increase\", default=0.1, type=float, help='Increase bbox by this amount')\n parser.add_argument(\"--iou_with_initial\", type=float, default=0.25, help=\"The minimal allowed iou with inital bbox\")\n parser.add_argument(\"--inp\", required=True, help='Input image or video')\n parser.add_argument(\"--min_frames\", type=int, default=150, help='Minimum number of frames')\n parser.add_argument(\"--cpu\", dest=\"cpu\", action=\"store_true\", help=\"cpu mode.\")\n\n\n args = parser.parse_args()\n\n commands = process_video(args)\n for command in commands:\n print (command)\n\n "
},
{
"path": "data/bair256.csv",
"content": "distance,source,driving,frame\n0,000054.mp4,000048.mp4,0\n0,000050.mp4,000063.mp4,0\n0,000073.mp4,000007.mp4,0\n0,000021.mp4,000010.mp4,0\n0,000084.mp4,000046.mp4,0\n0,000031.mp4,000102.mp4,0\n0,000029.mp4,000111.mp4,0\n0,000090.mp4,000112.mp4,0\n0,000039.mp4,000010.mp4,0\n0,000008.mp4,000069.mp4,0\n0,000068.mp4,000076.mp4,0\n0,000051.mp4,000052.mp4,0\n0,000022.mp4,000098.mp4,0\n0,000096.mp4,000032.mp4,0\n0,000032.mp4,000099.mp4,0\n0,000006.mp4,000053.mp4,0\n0,000098.mp4,000020.mp4,0\n0,000029.mp4,000066.mp4,0\n0,000022.mp4,000007.mp4,0\n0,000027.mp4,000065.mp4,0\n0,000026.mp4,000059.mp4,0\n0,000015.mp4,000112.mp4,0\n0,000086.mp4,000123.mp4,0\n0,000103.mp4,000052.mp4,0\n0,000123.mp4,000103.mp4,0\n0,000051.mp4,000005.mp4,0\n0,000062.mp4,000125.mp4,0\n0,000126.mp4,000111.mp4,0\n0,000066.mp4,000090.mp4,0\n0,000075.mp4,000106.mp4,0\n0,000020.mp4,000010.mp4,0\n0,000076.mp4,000028.mp4,0\n0,000062.mp4,000002.mp4,0\n0,000095.mp4,000127.mp4,0\n0,000113.mp4,000072.mp4,0\n0,000027.mp4,000104.mp4,0\n0,000054.mp4,000124.mp4,0\n0,000019.mp4,000089.mp4,0\n0,000052.mp4,000072.mp4,0\n0,000108.mp4,000033.mp4,0\n0,000044.mp4,000118.mp4,0\n0,000029.mp4,000086.mp4,0\n0,000068.mp4,000066.mp4,0\n0,000014.mp4,000036.mp4,0\n0,000053.mp4,000071.mp4,0\n0,000022.mp4,000094.mp4,0\n0,000000.mp4,000121.mp4,0\n0,000071.mp4,000079.mp4,0\n0,000127.mp4,000005.mp4,0\n0,000085.mp4,000023.mp4,0\n"
},
{
"path": "data/taichi-loading/README.md",
"content": "# TaiChi dataset\n\nThe scripst for loading the TaiChi dataset. \n\nWe provide only the id of the corresponding video and the bounding box. Following script will download videos from youtube and crop them according to the provided bounding boxes.\n\n1) Load youtube-dl:\n```\nwget https://yt-dl.org/downloads/latest/youtube-dl -O youtube-dl\nchmod a+rx youtube-dl\n```\n\n2) Run script to download videos, there are 2 formats that can be used for storing videos one is .mp4 and another is folder with .png images. While .png images occupy significantly more space, the format is loss-less and have better i/o performance when training.\n\n```\npython load_videos.py --metadata taichi-metadata.csv --format .mp4 --out_folder taichi --workers 8\n```\nselect number of workers based on number of cpu avaliable. Note .png format take aproximatly 80GB.\n"
},
{
"path": "data/taichi-loading/load_videos.py",
"content": "import numpy as np\nimport pandas as pd\nimport imageio\nimport os\nimport subprocess\nfrom multiprocessing import Pool\nfrom itertools import cycle\nimport warnings\nimport glob\nimport time\nfrom tqdm import tqdm\nfrom argparse import ArgumentParser\nfrom skimage import img_as_ubyte\nfrom skimage.transform import resize\nwarnings.filterwarnings(\"ignore\")\n\nDEVNULL = open(os.devnull, 'wb')\n\n\ndef save(path, frames, format):\n if format == '.mp4':\n imageio.mimsave(path, frames)\n elif format == '.png':\n if os.path.exists(path):\n print (\"Warning: skiping video %s\" % os.path.basename(path))\n return\n else:\n os.makedirs(path)\n for j, frame in enumerate(frames):\n imageio.imsave(os.path.join(path, str(j).zfill(7) + '.png'), frames[j]) \n else:\n print (\"Unknown format %s\" % format)\n exit()\n\n\ndef download(video_id, args):\n video_path = os.path.join(args.video_folder, video_id + \".mp4\")\n subprocess.call([args.youtube, '-f', \"''best/mp4''\", '--write-auto-sub', '--write-sub',\n '--sub-lang', 'en', '--skip-unavailable-fragments',\n \"https://www.youtube.com/watch?v=\" + video_id, \"--output\",\n video_path], stdout=DEVNULL, stderr=DEVNULL)\n return video_path\n\n\ndef run(data):\n video_id, args = data\n if not os.path.exists(os.path.join(args.video_folder, video_id.split('#')[0] + '.mp4')):\n download(video_id.split('#')[0], args)\n\n if not os.path.exists(os.path.join(args.video_folder, video_id.split('#')[0] + '.mp4')):\n print ('Can not load video %s, broken link' % video_id.split('#')[0])\n return \n reader = imageio.get_reader(os.path.join(args.video_folder, video_id.split('#')[0] + '.mp4'))\n fps = reader.get_meta_data()['fps']\n\n df = pd.read_csv(args.metadata)\n df = df[df['video_id'] == video_id]\n \n all_chunks_dict = [{'start': df['start'].iloc[j], 'end': df['end'].iloc[j],\n 'bbox': list(map(int, df['bbox'].iloc[j].split('-'))), 'frames':[]} for j in range(df.shape[0])]\n ref_fps = df['fps'].iloc[0]\n ref_height = df['height'].iloc[0]\n ref_width = df['width'].iloc[0]\n partition = df['partition'].iloc[0]\n try:\n for i, frame in enumerate(reader):\n for entry in all_chunks_dict:\n if (i * ref_fps >= entry['start'] * fps) and (i * ref_fps < entry['end'] * fps):\n left, top, right, bot = entry['bbox']\n left = int(left / (ref_width / frame.shape[1]))\n top = int(top / (ref_height / frame.shape[0]))\n right = int(right / (ref_width / frame.shape[1]))\n bot = int(bot / (ref_height / frame.shape[0]))\n crop = frame[top:bot, left:right]\n if args.image_shape is not None:\n crop = img_as_ubyte(resize(crop, args.image_shape, anti_aliasing=True))\n entry['frames'].append(crop)\n except imageio.core.format.CannotReadFrameError:\n None\n\n for entry in all_chunks_dict:\n first_part = '#'.join(video_id.split('#')[::-1])\n path = first_part + '#' + str(entry['start']).zfill(6) + '#' + str(entry['end']).zfill(6) + '.mp4'\n save(os.path.join(args.out_folder, partition, path), entry['frames'], args.format)\n\n\nif __name__ == \"__main__\":\n parser = ArgumentParser()\n parser.add_argument(\"--video_folder\", default='youtube-taichi', help='Path to youtube videos')\n parser.add_argument(\"--metadata\", default='taichi-metadata-new.csv', help='Path to metadata')\n parser.add_argument(\"--out_folder\", default='taichi-png', help='Path to output')\n parser.add_argument(\"--format\", default='.png', help='Storing format')\n parser.add_argument(\"--workers\", default=1, type=int, help='Number of workers')\n parser.add_argument(\"--youtube\", default='./youtube-dl', help='Path to youtube-dl')\n \n parser.add_argument(\"--image_shape\", default=(256, 256), type=lambda x: tuple(map(int, x.split(','))),\n help=\"Image shape, None for no resize\")\n\n args = parser.parse_args()\n if not os.path.exists(args.video_folder):\n os.makedirs(args.video_folder)\n if not os.path.exists(args.out_folder):\n os.makedirs(args.out_folder)\n for partition in ['test', 'train']:\n if not os.path.exists(os.path.join(args.out_folder, partition)):\n os.makedirs(os.path.join(args.out_folder, partition))\n\n df = pd.read_csv(args.metadata)\n video_ids = set(df['video_id'])\n pool = Pool(processes=args.workers)\n args_list = cycle([args])\n for chunks_data in tqdm(pool.imap_unordered(run, zip(video_ids, args_list))):\n None \n"
},
{
"path": "data/taichi-loading/taichi-metadata.csv",
"content": "video_id,start,end,bbox,fps,width,height,partition\nu6rJiF-gPx8,80,300,118-82-508-472,29.97,640,480,train\nu6rJiF-gPx8,575,717,168-99-488-419,29.97,640,480,train\nu6rJiF-gPx8,1257,1550,132-46-539-453,29.97,640,480,train\nu6rJiF-gPx8,1551,1808,151-59-547-455,29.97,640,480,train\nu6rJiF-gPx8,1888,2161,124-37-541-454,29.97,640,480,train\nu6rJiF-gPx8,2484,2719,150-40-570-460,29.97,640,480,train\nu6rJiF-gPx8,3000,3129,89-69-473-453,29.97,640,480,train\nu6rJiF-gPx8,3300,3450,124-95-491-462,29.97,640,480,train\nu6rJiF-gPx8,3600,3750,117-104-443-430,29.97,640,480,train\nu6rJiF-gPx8,4157,4350,150-87-525-462,29.97,640,480,train\nNBGys-uxScs,134,312,152-118-440-406,29.97,640,480,train\nNBGys-uxScs,403,587,145-136-410-401,29.97,640,480,train\nNBGys-uxScs,898,1092,95-79-409-393,29.97,640,480,train\nNBGys-uxScs,1262,1535,49-57-391-399,29.97,640,480,train\nNBGys-uxScs,1923,2165,232-80-554-402,29.97,640,480,train\nNBGys-uxScs,2165,2324,138-63-465-390,29.97,640,480,train\nNBGys-uxScs,2324,2503,88-72-410-394,29.97,640,480,train\nNBGys-uxScs,2698,2840,154-73-486-405,29.97,640,480,train\nNBGys-uxScs,2840,3222,191-53-537-399,29.97,640,480,train\nNBGys-uxScs,3634,4177,186-67-521-402,29.97,640,480,train\nNBGys-uxScs,4222,4367,255-80-575-400,29.97,640,480,train\nNBGys-uxScs,5361,5656,165-67-501-403,29.97,640,480,train\nNBGys-uxScs,5719,5923,160-78-485-403,29.97,640,480,train\nNBGys-uxScs,6359,6577,152-51-499-398,29.97,640,480,train\nNBGys-uxScs,7477,7830,131-64-476-409,29.97,640,480,train\nuEqWZ9S_-Lw,89,581,51-38-489-476,25.0,600,480,test\nuEqWZ9S_-Lw,660,1470,69-51-492-474,25.0,600,480,test\nuEqWZ9S_-Lw,1470,1773,7-45-437-475,25.0,600,480,test\nuEqWZ9S_-Lw,1773,1905,92-74-490-472,25.0,600,480,test\nuEqWZ9S_-Lw,2600,2868,106-60-517-471,25.0,600,480,test\nuEqWZ9S_-Lw,3142,3350,59-50-478-469,25.0,600,480,test\nuEqWZ9S_-Lw,3414,3576,37-56-456-475,25.0,600,480,test\nuEqWZ9S_-Lw,3662,3864,103-45-523-465,25.0,600,480,test\nuEqWZ9S_-Lw,4340,4738,75-75-472-472,25.0,600,480,test\nuEqWZ9S_-Lw,4947,5107,49-34-484-469,25.0,600,480,test\nuEqWZ9S_-Lw,5252,5990,44-70-438-464,25.0,600,480,test\nuEqWZ9S_-Lw,7083,7713,72-51-499-478,25.0,600,480,test\nuEqWZ9S_-Lw,9388,9729,71-55-483-467,25.0,600,480,test\nuEqWZ9S_-Lw,9881,10091,46-62-458-474,25.0,600,480,test\nctzMBulw1lI,320,577,85-71-478-464,30.0,640,480,train\nctzMBulw1lI,669,871,162-56-544-438,30.0,640,480,train\nctzMBulw1lI,1191,1338,144-55-533-444,30.0,640,480,train\nctzMBulw1lI,1822,1962,62-55-448-441,30.0,640,480,train\nctzMBulw1lI,2016,2175,125-61-498-434,30.0,640,480,train\nctzMBulw1lI,2509,2680,66-66-440-440,30.0,640,480,train\nctzMBulw1lI,2680,2823,152-107-491-446,30.0,640,480,train\nctzMBulw1lI,2832,3121,141-88-499-446,30.0,640,480,train\nctzMBulw1lI,4044,4326,108-16-546-454,30.0,640,480,train\nctzMBulw1lI,4326,4496,101-40-520-459,30.0,640,480,train\nctzMBulw1lI,4516,4755,56-35-483-462,30.0,640,480,train\nctzMBulw1lI,4796,4972,37-19-477-459,30.0,640,480,train\nctzMBulw1lI,5008,5236,37-2-503-468,30.0,640,480,train\nctzMBulw1lI,5548,5684,66-46-455-435,30.0,640,480,train\nctzMBulw1lI,6610,6754,78-44-491-457,30.0,640,480,train\nctzMBulw1lI,6811,7033,113-41-514-442,30.0,640,480,train\nctzMBulw1lI,7350,7511,203-66-589-452,30.0,640,480,train\nctzMBulw1lI,7659,7916,66-60-448-442,30.0,640,480,train\nctzMBulw1lI,9007,9148,94-39-492-437,30.0,640,480,train\nctzMBulw1lI,9643,9910,18-47-426-455,30.0,640,480,train\nctzMBulw1lI,11072,11285,98-44-489-435,30.0,640,480,train\nctzMBulw1lI,11701,11904,45-40-431-426,30.0,640,480,train\ncpDT3xFbP4g,7,1031,133-87-482-436,29.97,640,480,train\ncpDT3xFbP4g,1031,1301,127-97-467-437,29.97,640,480,train\ncpDT3xFbP4g,1395,2419,112-92-473-453,29.97,640,480,train\ncpDT3xFbP4g,2419,2837,136-92-484-440,29.97,640,480,train\ncpDT3xFbP4g,2837,3861,92-89-460-457,29.97,640,480,train\ncpDT3xFbP4g,3861,4805,172-104-508-440,29.97,640,480,train\ncpDT3xFbP4g,4805,5829,153-88-514-449,29.97,640,480,train\ncpDT3xFbP4g,5829,6020,148-101-487-440,29.97,640,480,train\noYlrB4ddEpM,1167,1646,277-23-962-708,25.0,1280,720,train\noYlrB4ddEpM,2815,2985,401-119-992-710,25.0,1280,720,train\noYlrB4ddEpM,3016,3228,483-105-1068-690,25.0,1280,720,train\noYlrB4ddEpM,5318,5453,235-84-846-695,25.0,1280,720,train\noYlrB4ddEpM,5656,5964,450-52-1101-703,25.0,1280,720,train\nYonmpJvwmKM,2264,2578,340-67-963-690,29.97,1280,720,train\nYonmpJvwmKM,4852,5063,231-9-920-698,29.97,1280,720,train\nYonmpJvwmKM,5597,5854,435-48-1078-691,29.97,1280,720,train\nDn0mNZmAh2k,308,450,95-63-498-466,29.97,640,480,train\nDn0mNZmAh2k,495,975,125-114-481-470,29.97,640,480,train\nDn0mNZmAh2k,1369,1557,129-131-461-463,29.97,640,480,train\nDn0mNZmAh2k,1710,1900,35-101-401-467,29.97,640,480,train\nDn0mNZmAh2k,2085,2388,42-94-417-469,29.97,640,480,train\nDn0mNZmAh2k,3180,3377,108-134-445-471,29.97,640,480,train\nDn0mNZmAh2k,4815,5175,180-70-573-463,29.97,640,480,train\nDn0mNZmAh2k,6165,6379,127-109-498-480,29.97,640,480,train\nQlbxd48tQg8,0,263,346-187-617-458,29.97,854,480,train\nQlbxd48tQg8,358,810,251-79-624-452,29.97,854,480,train\nQlbxd48tQg8,941,1096,290-97-651-458,29.97,854,480,train\nQlbxd48tQg8,2777,3009,269-65-659-455,29.97,854,480,train\nQlbxd48tQg8,4052,4190,231-74-606-449,29.97,854,480,train\nQlbxd48tQg8,5244,5418,258-76-634-452,29.97,854,480,train\nQlbxd48tQg8,7183,7329,216-50-616-450,29.97,854,480,train\nQlbxd48tQg8,7329,8248,228-28-657-457,29.97,854,480,train\nQlbxd48tQg8,8248,9272,213-0-670-457,29.97,854,480,train\nQlbxd48tQg8,9429,9934,265-107-609-451,29.97,854,480,train\nQlbxd48tQg8,10527,10655,252-100-599-447,29.97,854,480,train\nQlbxd48tQg8,11211,11405,295-79-661-445,29.97,854,480,train\nQlbxd48tQg8,11431,11616,288-77-659-448,29.97,854,480,train\n_XRyc2kiTlM,3844,4023,458-54-1402-998,25.0,1920,1080,train\n3vcpk5cMDzo,170,1194,582-46-1565-1029,25.0,1920,1080,train\n3vcpk5cMDzo,1410,1943,721-289-1409-977,25.0,1920,1080,train\n3vcpk5cMDzo,1943,2157,576-332-1221-977,25.0,1920,1080,train\n3vcpk5cMDzo,2226,2483,726-321-1430-1025,25.0,1920,1080,train\n3vcpk5cMDzo,2678,3073,530-273-1311-1054,25.0,1920,1080,train\n3vcpk5cMDzo,3119,3261,754-384-1303-933,25.0,1920,1080,train\n3vcpk5cMDzo,3406,3710,723-377-1269-923,25.0,1920,1080,train\n3vcpk5cMDzo,3755,3911,516-331-1159-974,25.0,1920,1080,train\n3vcpk5cMDzo,3973,4159,674-323-1367-1016,25.0,1920,1080,train\n3vcpk5cMDzo,4159,4317,540-294-1298-1052,25.0,1920,1080,train\nD-8bvXjcz8c,120,360,615-63-1203-651,24.0,1280,720,test\nD-8bvXjcz8c,1080,1320,467-61-1116-710,24.0,1280,720,test\nD-8bvXjcz8c,5640,5824,481-43-1117-679,24.0,1280,720,test\nD-8bvXjcz8c,8480,8640,117-72-713-668,24.0,1280,720,test\nD-8bvXjcz8c,10458,10680,166-60-772-666,24.0,1280,720,test\nSn9jYXV6kpg,1008,1196,605-454-1123-972,29.0,1920,1080,train\nSn9jYXV6kpg,3372,3522,533-441-1015-923,29.0,1920,1080,train\nSn9jYXV6kpg,3522,3685,537-416-1036-915,29.0,1920,1080,train\nSn9jYXV6kpg,3796,3996,575-389-1104-918,29.0,1920,1080,train\nSn9jYXV6kpg,4161,4353,657-348-1192-883,29.0,1920,1080,train\nSn9jYXV6kpg,4814,4980,961-301-1502-842,29.0,1920,1080,train\nSn9jYXV6kpg,5194,5336,1036-255-1614-833,29.0,1920,1080,train\nSn9jYXV6kpg,7281,7494,522-360-1026-864,29.0,1920,1080,train\njDdTqi1t_jE,744,885,278-42-939-703,30.0,1280,720,test\njDdTqi1t_jE,2227,2380,225-7-932-714,30.0,1280,720,test\njDdTqi1t_jE,4480,4823,212-0-930-718,30.0,1280,720,test\njDdTqi1t_jE,5195,5550,213-15-909-711,30.0,1280,720,test\nYddPIOYOH6o,0,547,494-313-1089-908,30.0,1920,1080,train\nYddPIOYOH6o,609,755,603-354-1163-914,30.0,1920,1080,train\nYddPIOYOH6o,1414,1578,571-327-1145-901,30.0,1920,1080,train\nYddPIOYOH6o,1681,1862,542-319-1135-912,30.0,1920,1080,train\nYddPIOYOH6o,1896,2064,533-341-1124-932,30.0,1920,1080,train\nYddPIOYOH6o,2305,2613,780-293-1358-871,30.0,1920,1080,train\nYddPIOYOH6o,2736,2955,592-281-1237-926,30.0,1920,1080,train\nYddPIOYOH6o,3018,3178,735-386-1237-888,30.0,1920,1080,train\nGQ0ef8nh9H8,645,1004,191-127-482-418,29.97,640,480,test\nGQ0ef8nh9H8,1004,1380,202-152-464-414,29.97,640,480,test\nGQ0ef8nh9H8,2530,2818,245-155-501-411,29.97,640,480,test\n1HR5NXiNEjA,122,483,139-78-452-391,25.0,640,480,train\n1HR5NXiNEjA,550,864,168-37-525-394,25.0,640,480,train\n1HR5NXiNEjA,864,1176,169-91-469-391,25.0,640,480,train\n1HR5NXiNEjA,1394,1548,181-98-469-386,25.0,640,480,train\n1HR5NXiNEjA,3017,3234,180-23-599-442,25.0,640,480,train\ncCx82sXERCI,133,330,376-33-1048-705,24.0,1280,720,train\ncCx82sXERCI,330,1320,382-33-1048-699,24.0,1280,720,train\ncCx82sXERCI,1340,1680,376-26-1063-713,24.0,1280,720,train\ncCx82sXERCI,1800,2055,393-39-1053-699,24.0,1280,720,train\ncCx82sXERCI,2055,2400,380-35-1051-706,24.0,1280,720,train\ncCx82sXERCI,2400,2588,388-55-1040-707,24.0,1280,720,train\ncCx82sXERCI,2589,2882,365-24-1041-700,24.0,1280,720,train\ncCx82sXERCI,2883,3158,370-43-1025-698,24.0,1280,720,train\ncCx82sXERCI,3158,3334,336-40-1003-707,24.0,1280,720,train\ncCx82sXERCI,3368,3542,290-13-979-702,24.0,1280,720,train\ncCx82sXERCI,4425,4560,317-19-994-696,24.0,1280,720,train\ncCx82sXERCI,4560,4765,355-33-1024-702,24.0,1280,720,train\ncCx82sXERCI,4935,5070,358-39-1017-698,24.0,1280,720,train\nhNRum5Lhdws,0,525,335-142-878-685,30.0,1280,720,train\nhNRum5Lhdws,525,765,376-142-917-683,30.0,1280,720,train\nhNRum5Lhdws,870,1092,393-165-907-679,30.0,1280,720,train\nhNRum5Lhdws,1162,1644,427-169-944-686,30.0,1280,720,train\nhNRum5Lhdws,1644,1827,348-168-849-669,30.0,1280,720,train\nhNRum5Lhdws,1827,1979,475-183-936-644,30.0,1280,720,train\nhNRum5Lhdws,2098,2489,477-153-979-655,30.0,1280,720,train\nhNRum5Lhdws,3144,3283,496-195-948-647,30.0,1280,720,train\nhNRum5Lhdws,3497,3765,566-226-986-646,30.0,1280,720,train\nhNRum5Lhdws,4042,4262,505-229-906-630,30.0,1280,720,train\nhNRum5Lhdws,4802,4994,436-229-863-656,30.0,1280,720,train\nhNRum5Lhdws,5130,5820,396-213-860-677,30.0,1280,720,train\nhNRum5Lhdws,6254,6576,357-208-825-676,30.0,1280,720,train\nhNRum5Lhdws,6576,6739,434-214-896-676,30.0,1280,720,train\nhNRum5Lhdws,6874,7869,367-213-854-700,30.0,1280,720,train\nhNRum5Lhdws,8257,8415,261-199-752-690,30.0,1280,720,train\nhNRum5Lhdws,8415,8649,376-213-866-703,30.0,1280,720,train\nhNRum5Lhdws,8775,9030,441-245-841-645,30.0,1280,720,train\nhNRum5Lhdws,9277,9459,412-236-830-654,30.0,1280,720,train\nhNRum5Lhdws,9459,9960,410-214-857-661,30.0,1280,720,train\nhNRum5Lhdws,10235,10651,359-215-825-681,30.0,1280,720,train\nhNRum5Lhdws,10785,11110,437-214-912-689,30.0,1280,720,train\nhNRum5Lhdws,11224,11526,384-181-890-687,30.0,1280,720,train\nfl9GjEkHFDg,2550,2730,371-25-1004-658,29.97,1280,720,train\nfl9GjEkHFDg,3360,3630,322-28-958-664,29.97,1280,720,train\nfl9GjEkHFDg,3810,3972,336-17-954-635,29.97,1280,720,train\nfl9GjEkHFDg,5250,5430,331-52-942-663,29.97,1280,720,train\nfl9GjEkHFDg,7050,7230,319-39-979-699,29.97,1280,720,train\nsZtU-A3BB8k,0,604,682-385-1238-941,29.97,1920,1080,train\nsZtU-A3BB8k,634,925,727-390-1273-936,29.97,1920,1080,train\n_L745tFFmCQ,5583,5717,1192-143-1800-751,25.0,1920,1080,train\n_L745tFFmCQ,8295,8448,674-75-1430-831,25.0,1920,1080,train\n_L745tFFmCQ,8472,8617,526-179-1304-957,25.0,1920,1080,train\n_zJWt92xoRw,480,902,220-95-760-635,29.97,1280,720,train\n_zJWt92xoRw,902,1197,331-118-833-620,29.97,1280,720,train\n_zJWt92xoRw,1729,1965,297-142-803-648,29.97,1280,720,train\n_zJWt92xoRw,2748,2886,441-137-940-636,29.97,1280,720,train\n_zJWt92xoRw,3003,3162,558-155-1044-641,29.97,1280,720,train\n_zJWt92xoRw,3318,3544,586-149-1076-639,29.97,1280,720,train\n_zJWt92xoRw,4396,4816,622-126-1148-652,29.97,1280,720,train\n_zJWt92xoRw,5455,5636,682-135-1171-624,29.97,1280,720,train\n_zJWt92xoRw,6790,6984,185-139-671-625,29.97,1280,720,train\n_zJWt92xoRw,7392,7623,199-126-716-643,29.97,1280,720,train\n_zJWt92xoRw,10016,10163,709-189-1053-533,29.97,1280,720,train\n_zJWt92xoRw,11616,11760,280-158-684-562,29.97,1280,720,train\n_zJWt92xoRw,12263,12401,169-150-602-583,29.97,1280,720,train\n_zJWt92xoRw,13262,13392,171-130-591-550,29.97,1280,720,train\n_zJWt92xoRw,14658,14877,556-159-999-602,29.97,1280,720,train\n_zJWt92xoRw,15383,15513,529-166-971-608,29.97,1280,720,train\n_zJWt92xoRw,18850,18996,201-174-605-578,29.97,1280,720,train\n_zJWt92xoRw,19464,19699,181-171-584-574,29.97,1280,720,train\n_zJWt92xoRw,19860,20123,149-131-589-571,29.97,1280,720,train\nAXp3aT5pmWs,0,351,125-16-574-465,29.97,720,480,train\nAXp3aT5pmWs,1577,1940,175-17-625-467,29.97,720,480,train\nAXp3aT5pmWs,3218,3553,122-17-579-474,29.97,720,480,train\nAXp3aT5pmWs,4106,4878,218-37-635-454,29.97,720,480,train\nAXp3aT5pmWs,4878,5172,211-10-661-460,29.97,720,480,train\nAXp3aT5pmWs,5206,5592,184-39-579-434,29.97,720,480,train\nAXp3aT5pmWs,5936,6082,105-39-487-421,29.97,720,480,train\ncyN6Eb5Luzo,448,1040,133-186-463-516,29.97,960,720,train\ncyN6Eb5Luzo,1040,1407,138-185-485-532,29.97,960,720,train\ncyN6Eb5Luzo,1923,2217,97-168-473-544,29.97,960,720,train\ncyN6Eb5Luzo,2219,2368,126-183-463-520,29.97,960,720,train\ncyN6Eb5Luzo,2464,3028,95-168-452-525,29.97,960,720,train\ncyN6Eb5Luzo,3028,3370,122-177-486-541,29.97,960,720,train\ncyN6Eb5Luzo,3376,3547,124-191-469-536,29.97,960,720,train\ncyN6Eb5Luzo,3801,4825,295-184-644-533,29.97,960,720,train\nvxsaQvdnEcU,507,779,167-36-606-475,29.97,640,480,train\nvxsaQvdnEcU,876,1057,177-99-525-447,29.97,640,480,train\nvxsaQvdnEcU,1106,1258,148-50-562-464,29.97,640,480,train\nvxsaQvdnEcU,1280,1543,55-54-449-448,29.97,640,480,train\nvxsaQvdnEcU,1676,1810,189-108-553-472,29.97,640,480,train\nvxsaQvdnEcU,3838,4142,138-41-516-419,29.97,640,480,train\nvxsaQvdnEcU,4148,4483,111-91-496-476,29.97,640,480,train\nvxsaQvdnEcU,4844,5018,221-39-640-458,29.97,640,480,train\nv2zjtNjnj3A,844,1000,529-149-862-482,23.97,1280,720,train\nv2zjtNjnj3A,1493,1674,484-89-858-463,23.97,1280,720,train\nv2zjtNjnj3A,3198,3326,471-67-881-477,23.97,1280,720,train\nnLEzl5ntdeQ,149,431,85-379-731-1025,29.0,810,1440,train\nnLEzl5ntdeQ,1080,1280,34-444-676-1086,29.0,810,1440,train\nnLEzl5ntdeQ,1280,1440,57-450-692-1085,29.0,810,1440,train\nnLEzl5ntdeQ,1448,1610,46-457-689-1100,29.0,810,1440,train\nnLEzl5ntdeQ,1610,1920,59-425-744-1110,29.0,810,1440,train\nnLEzl5ntdeQ,2000,2228,96-386-794-1084,29.0,810,1440,train\nnLEzl5ntdeQ,2400,2571,95-434-714-1053,29.0,810,1440,train\nnLEzl5ntdeQ,2670,2880,94-416-758-1080,29.0,810,1440,train\nnLEzl5ntdeQ,2970,3204,97-409-789-1101,29.0,810,1440,train\nnLEzl5ntdeQ,4538,4680,109-473-724-1088,29.0,810,1440,train\nnLEzl5ntdeQ,4980,5220,96-436-767-1107,29.0,810,1440,train\nnLEzl5ntdeQ,5280,5430,111-468-759-1116,29.0,810,1440,train\nnLEzl5ntdeQ,6030,6263,73-484-704-1115,29.0,810,1440,train\nnLEzl5ntdeQ,6302,6444,77-434-769-1126,29.0,810,1440,train\nnLEzl5ntdeQ,6444,6632,131-401-794-1064,29.0,810,1440,train\nnLEzl5ntdeQ,6632,6781,97-402-761-1066,29.0,810,1440,train\nnLEzl5ntdeQ,6781,6961,76-386-760-1070,29.0,810,1440,train\nZwBsM72F0xg,159,608,218-156-602-540,15.79,1280,720,train\nZwBsM72F0xg,812,1041,165-184-547-566,15.79,1280,720,train\nZwBsM72F0xg,1075,1218,94-192-466-564,15.79,1280,720,train\nZwBsM72F0xg,5123,5433,240-179-665-604,15.79,1280,720,train\nZwBsM72F0xg,5644,5780,329-172-751-594,15.79,1280,720,train\nZwBsM72F0xg,7248,7376,584-143-1013-572,15.79,1280,720,train\nYVmF50cMs_0,5490,5998,352-87-951-686,29.97,1280,720,train\nYVmF50cMs_0,6563,6709,356-105-889-638,29.97,1280,720,train\nYVmF50cMs_0,6975,7137,386-49-944-607,29.97,1280,720,train\nYVmF50cMs_0,7664,7802,313-24-883-594,29.97,1280,720,train\nYVmF50cMs_0,8894,9039,254-75-784-605,29.97,1280,720,train\nYVmF50cMs_0,9717,9885,361-79-910-628,29.97,1280,720,train\nYVmF50cMs_0,9885,10159,346-53-893-600,29.97,1280,720,train\nYVmF50cMs_0,10186,10315,326-76-869-619,29.97,1280,720,train\nYVmF50cMs_0,10630,10791,368-144-865-641,29.97,1280,720,train\nYVmF50cMs_0,12090,12260,174-81-725-632,29.97,1280,720,train\nYVmF50cMs_0,12260,12456,358-93-866-601,29.97,1280,720,train\nYVmF50cMs_0,12521,12650,415-179-873-637,29.97,1280,720,train\nYVmF50cMs_0,12650,12897,360-149-850-639,29.97,1280,720,train\nYVmF50cMs_0,13238,13383,381-171-839-629,29.97,1280,720,train\nYVmF50cMs_0,13839,13967,300-76-846-622,29.97,1280,720,train\nFsmIt38CNog,166,740,670-172-1314-816,29.97,1920,1080,train\nFsmIt38CNog,1086,1592,773-238-1339-804,29.97,1920,1080,train\nFsmIt38CNog,1665,1834,786-236-1365-815,29.97,1920,1080,train\nFsmIt38CNog,1881,2069,664-215-1286-837,29.97,1920,1080,train\nFsmIt38CNog,2069,2212,725-248-1275-798,29.97,1920,1080,train\nFsmIt38CNog,2424,2652,450-229-1035-814,29.97,1920,1080,train\nFsmIt38CNog,2652,2973,252-205-876-829,29.97,1920,1080,train\nFsmIt38CNog,4000,4143,375-218-1181-1024,29.97,1920,1080,train\nFsmIt38CNog,4632,4761,589-112-1333-856,29.97,1920,1080,train\nFsmIt38CNog,4882,5164,760-107-1645-992,29.97,1920,1080,train\nFsmIt38CNog,5168,5420,963-131-1802-970,29.97,1920,1080,train\nFsmIt38CNog,5725,6257,937-149-1813-1025,29.97,1920,1080,train\nFsmIt38CNog,6735,6891,752-200-1576-1024,29.97,1920,1080,train\nFsmIt38CNog,7520,7880,810-113-1685-988,29.97,1920,1080,train\nFsmIt38CNog,7880,8058,621-145-1372-896,29.97,1920,1080,train\nFsmIt38CNog,8179,8351,474-215-1181-922,29.97,1920,1080,train\nFsmIt38CNog,8792,9010,174-206-935-967,29.97,1920,1080,train\nFsmIt38CNog,9102,9262,446-242-1227-1023,29.97,1920,1080,train\nFsmIt38CNog,9633,9828,894-296-1634-1036,29.97,1920,1080,train\nFsmIt38CNog,10653,10786,982-148-1749-915,29.97,1920,1080,train\nFsmIt38CNog,10786,10988,915-175-1626-886,29.97,1920,1080,train\nFsmIt38CNog,11065,11230,756-159-1460-863,29.97,1920,1080,train\nFsmIt38CNog,11230,11394,798-163-1483-848,29.97,1920,1080,train\nFsmIt38CNog,11598,11974,810-87-1574-851,29.97,1920,1080,train\nOPcZlXYcdMA,459,913,304-44-919-659,29.97,1280,720,train\nOPcZlXYcdMA,913,1363,294-41-941-688,29.97,1280,720,train\nOPcZlXYcdMA,1577,2084,283-38-909-664,29.97,1280,720,train\nOPcZlXYcdMA,2383,2551,333-49-964-680,29.97,1280,720,train\nOPcZlXYcdMA,2873,3231,331-50-958-677,29.97,1280,720,train\nOPcZlXYcdMA,3417,3801,326-41-965-680,29.97,1280,720,train\nOPcZlXYcdMA,4022,4435,317-39-957-679,29.97,1280,720,train\nOPcZlXYcdMA,4611,4948,255-67-867-679,29.97,1280,720,train\nOPcZlXYcdMA,4948,5155,420-72-1017-669,29.97,1280,720,train\nOPcZlXYcdMA,5363,5913,372-59-974-661,29.97,1280,720,train\nOPcZlXYcdMA,6231,6518,294-66-908-680,29.97,1280,720,train\nOPcZlXYcdMA,8507,8697,279-81-904-706,29.97,1280,720,train\nOPcZlXYcdMA,8697,8896,427-77-1050-700,29.97,1280,720,train\nOPcZlXYcdMA,9675,10053,296-37-927-668,29.97,1280,720,train\nOPcZlXYcdMA,10333,11357,307-55-922-670,29.97,1280,720,train\nOPcZlXYcdMA,11398,11644,324-55-919-650,29.97,1280,720,train\nOPcZlXYcdMA,11644,12197,324-26-951-653,29.97,1280,720,train\nOPcZlXYcdMA,12198,12399,371-60-943-632,29.97,1280,720,train\nOPcZlXYcdMA,12399,13423,316-56-921-661,29.97,1280,720,train\nOPcZlXYcdMA,13457,14198,373-64-953-644,29.97,1280,720,train\nOPcZlXYcdMA,15589,16099,313-45-923-655,29.97,1280,720,train\nL82WHgYRq6I,21,479,494-203-1278-987,25.0,1920,1080,test\nL82WHgYRq6I,525,657,547-182-1371-1006,25.0,1920,1080,test\nL82WHgYRq6I,684,1309,484-31-1464-1011,25.0,1920,1080,test\nL82WHgYRq6I,1384,1524,681-289-1363-971,25.0,1920,1080,test\nL82WHgYRq6I,2175,2417,434-296-1132-994,25.0,1920,1080,test\nL82WHgYRq6I,3035,3238,601-274-1298-971,25.0,1920,1080,test\nL82WHgYRq6I,3345,3475,764-261-1448-945,25.0,1920,1080,test\nL82WHgYRq6I,3583,3821,983-294-1605-916,25.0,1920,1080,test\nL82WHgYRq6I,3967,4149,1101-318-1695-912,25.0,1920,1080,test\nL82WHgYRq6I,5369,5623,593-307-1244-958,25.0,1920,1080,test\nL82WHgYRq6I,6259,6397,220-215-1042-1037,25.0,1920,1080,test\nL82WHgYRq6I,6516,6669,562-254-1273-965,25.0,1920,1080,test\nL82WHgYRq6I,8183,8424,818-329-1427-938,25.0,1920,1080,test\nQ0tIcxMcm4E,0,591,156-113-1024-981,25.0,1920,1080,train\nQ0tIcxMcm4E,798,979,399-176-1194-971,25.0,1920,1080,train\nQ0tIcxMcm4E,1142,1337,714-170-1501-957,25.0,1920,1080,train\nQ0tIcxMcm4E,1337,1628,923-164-1688-929,25.0,1920,1080,train\nQ0tIcxMcm4E,2116,2289,737-158-1499-920,25.0,1920,1080,train\nQ0tIcxMcm4E,2367,2763,940-173-1702-935,25.0,1920,1080,train\nQ0tIcxMcm4E,2859,3003,970-177-1690-897,25.0,1920,1080,train\nQ0tIcxMcm4E,3329,3506,534-163-1269-898,25.0,1920,1080,train\nQ0tIcxMcm4E,3636,3849,320-137-1116-933,25.0,1920,1080,train\nQ0tIcxMcm4E,3892,4228,275-148-1065-938,25.0,1920,1080,train\nQ0tIcxMcm4E,4725,4963,503-161-1267-925,25.0,1920,1080,train\nQ0tIcxMcm4E,5647,5976,451-144-1238-931,25.0,1920,1080,train\nQ0tIcxMcm4E,5976,6132,357-106-1180-929,25.0,1920,1080,train\nQ0tIcxMcm4E,6354,6594,617-119-1442-944,25.0,1920,1080,train\nQ0tIcxMcm4E,6616,7000,866-81-1721-936,25.0,1920,1080,train\nQ0tIcxMcm4E,7000,7156,646-105-1472-931,25.0,1920,1080,train\nQ0tIcxMcm4E,7247,7422,988-155-1756-923,25.0,1920,1080,train\nQ0tIcxMcm4E,8272,8448,914-187-1615-888,25.0,1920,1080,train\nQ0tIcxMcm4E,8984,9176,545-118-1333-906,25.0,1920,1080,train\nQ0tIcxMcm4E,9589,9957,310-163-1052-905,25.0,1920,1080,train\nQ0tIcxMcm4E,10364,10567,368-209-1056-897,25.0,1920,1080,train\nQ0tIcxMcm4E,10884,11290,234-130-1013-909,25.0,1920,1080,train\nQ0tIcxMcm4E,11354,11485,564-218-1269-923,25.0,1920,1080,train\nQ0tIcxMcm4E,11528,11747,603-204-1315-916,25.0,1920,1080,train\nQ0tIcxMcm4E,12030,12519,638-117-1434-913,25.0,1920,1080,train\nceoe2fz648U,116,400,117-103-428-414,29.97,640,480,train\nceoe2fz648U,1401,1532,92-78-425-411,29.97,640,480,train\nceoe2fz648U,1652,1824,119-102-436-419,29.97,640,480,train\nceoe2fz648U,3287,3419,187-134-455-402,29.97,640,480,train\nceoe2fz648U,5820,6002,84-109-395-420,29.97,640,480,train\nJVXDPOICOcw,629,871,181-167-446-432,29.97,640,480,train\nJTMn6S9cS_A,0,438,317-67-890-640,25.0,1280,720,train\nJTMn6S9cS_A,438,677,421-110-976-665,25.0,1280,720,train\nJTMn6S9cS_A,677,878,405-82-973-650,25.0,1280,720,train\nJTMn6S9cS_A,996,1280,362-27-972-637,25.0,1280,720,train\nJTMn6S9cS_A,1280,1456,520-112-1054-646,25.0,1280,720,train\nJTMn6S9cS_A,3190,3404,377-115-930-668,25.0,1280,720,train\nJTMn6S9cS_A,3780,3995,342-109-891-658,25.0,1280,720,train\nJTMn6S9cS_A,4684,4907,642-112-1154-624,25.0,1280,720,train\nJTMn6S9cS_A,5235,5378,577-120-1029-572,25.0,1280,720,train\nJTMn6S9cS_A,6673,6878,187-101-773-687,25.0,1280,720,train\nJTMn6S9cS_A,7378,7582,219-43-891-715,25.0,1280,720,train\nJTMn6S9cS_A,8115,8425,342-64-905-627,25.0,1280,720,train\n-YxgJ_xXcgU,119,281,327-120-643-436,30.0,1280,720,train\n-YxgJ_xXcgU,471,610,105-27-601-523,30.0,1280,720,train\n-YxgJ_xXcgU,3078,3220,619-133-1078-592,30.0,1280,720,train\nl5gCGxF-uM0,1479,1893,139-38-541-440,29.97,654,480,train\nl5gCGxF-uM0,2139,2531,149-71-531-453,29.97,654,480,train\nl5gCGxF-uM0,2772,3096,136-28-565-457,29.97,654,480,train\nl5gCGxF-uM0,3265,3594,180-94-513-427,29.97,654,480,train\nl5gCGxF-uM0,3900,4195,156-68-536-448,29.97,654,480,train\nl5gCGxF-uM0,4385,4618,135-122-452-439,29.97,654,480,train\nl5gCGxF-uM0,4963,5133,117-68-488-439,29.97,654,480,train\nl5gCGxF-uM0,5300,5580,150-50-547-447,29.97,654,480,train\nnFDRPyBl8WY,173,810,123-51-520-448,29.97,640,480,train\nnFDRPyBl8WY,916,1055,175-95-506-426,29.97,640,480,train\nnFDRPyBl8WY,1332,1700,120-86-462-428,29.97,640,480,train\nnFDRPyBl8WY,1702,1919,132-90-463-421,29.97,640,480,train\nnFDRPyBl8WY,2042,2239,122-74-482-434,29.97,640,480,train\nnFDRPyBl8WY,2239,2427,74-55-440-421,29.97,640,480,train\nnFDRPyBl8WY,3036,3235,133-26-569-462,29.97,640,480,train\nnFDRPyBl8WY,4062,4230,149-51-538-440,29.97,640,480,train\nnFDRPyBl8WY,4248,4447,39-57-414-432,29.97,640,480,train\nnFDRPyBl8WY,5504,5652,64-57-427-420,29.97,640,480,train\nnFDRPyBl8WY,5671,5846,112-33-519-440,29.97,640,480,train\nnFDRPyBl8WY,5873,6318,73-21-475-423,29.97,640,480,train\nnFDRPyBl8WY,6831,6980,53-77-413-437,29.97,640,480,train\nnFDRPyBl8WY,7059,7204,82-81-439-438,29.97,640,480,train\nnFDRPyBl8WY,8310,8469,154-111-420-377,29.97,640,480,train\nnFDRPyBl8WY,9525,9690,74-100-370-396,29.97,640,480,train\nnFDRPyBl8WY,10690,10989,149-47-548-446,29.97,640,480,train\nvgk5TBac16A,1158,1338,136-79-503-446,29.97,640,480,test\nvgk5TBac16A,1338,1809,83-81-444-442,29.97,640,480,test\nvgk5TBac16A,2020,2213,74-75-424-425,29.97,640,480,test\nvgk5TBac16A,2213,2654,147-77-494-424,29.97,640,480,test\nvgk5TBac16A,3741,4765,157-15-617-475,29.97,640,480,test\nvgk5TBac16A,4765,5789,148-6-616-474,29.97,640,480,test\nvgk5TBac16A,6244,7268,148-7-613-472,29.97,640,480,test\nvgk5TBac16A,7276,8115,149-15-606-472,29.97,640,480,test\nSllIuMCgJKM,1687,2250,129-85-487-443,29.97,640,480,train\nSllIuMCgJKM,3886,4027,141-61-506-426,29.97,640,480,train\nSllIuMCgJKM,4593,4775,177-51-526-400,29.97,640,480,train\nSllIuMCgJKM,5101,5235,86-54-450-418,29.97,640,480,train\nSllIuMCgJKM,9552,9796,149-34-548-433,29.97,640,480,train\naDyyTMUBoLE,164,351,333-46-1266-979,23.98,1920,1080,test\naDyyTMUBoLE,375,518,319-98-1293-1072,23.98,1920,1080,test\naDyyTMUBoLE,518,884,318-49-1336-1067,23.98,1920,1080,test\naDyyTMUBoLE,949,1092,437-91-1381-1035,23.98,1920,1080,test\naDyyTMUBoLE,1769,1957,241-19-1262-1040,23.98,1920,1080,test\ngSIN9Mhm5oQ,127,303,852-25-1728-901,25.0,1920,1080,train\ngSIN9Mhm5oQ,333,862,785-138-1530-883,25.0,1920,1080,train\ngSIN9Mhm5oQ,1028,1278,722-111-1498-887,25.0,1920,1080,train\ngSIN9Mhm5oQ,1450,1649,848-63-1697-912,25.0,1920,1080,train\ngSIN9Mhm5oQ,1649,1848,755-117-1551-913,25.0,1920,1080,train\ngSIN9Mhm5oQ,2002,2264,770-61-1682-973,25.0,1920,1080,train\ngSIN9Mhm5oQ,2566,2702,453-129-1297-973,25.0,1920,1080,train\ngSIN9Mhm5oQ,3199,3411,391-141-1282-1032,25.0,1920,1080,train\ngSIN9Mhm5oQ,3625,3853,640-143-1512-1015,25.0,1920,1080,train\ngSIN9Mhm5oQ,3992,4127,623-43-1599-1019,25.0,1920,1080,train\ngSIN9Mhm5oQ,4160,4340,614-182-1431-999,25.0,1920,1080,train\ngSIN9Mhm5oQ,4387,4556,639-151-1478-990,25.0,1920,1080,train\ngSIN9Mhm5oQ,4870,5030,119-204-920-1005,25.0,1920,1080,train\ngSIN9Mhm5oQ,5030,5257,299-204-1094-999,25.0,1920,1080,train\ngSIN9Mhm5oQ,5257,5647,355-164-1198-1007,25.0,1920,1080,train\ngSIN9Mhm5oQ,5833,6171,433-135-1291-993,25.0,1920,1080,train\ngSIN9Mhm5oQ,6309,6449,500-153-1357-1010,25.0,1920,1080,train\ngSIN9Mhm5oQ,6567,6711,552-140-1405-993,25.0,1920,1080,train\ngSIN9Mhm5oQ,7285,7664,589-117-1447-975,25.0,1920,1080,train\ngSIN9Mhm5oQ,8046,8212,747-38-1672-963,25.0,1920,1080,train\ngSIN9Mhm5oQ,8217,8453,643-61-1527-945,25.0,1920,1080,train\ngSIN9Mhm5oQ,8453,8586,544-148-1383-987,25.0,1920,1080,train\ngSIN9Mhm5oQ,8682,8867,429-149-1276-996,25.0,1920,1080,train\ngSIN9Mhm5oQ,9189,9506,296-145-1200-1049,25.0,1920,1080,train\ngSIN9Mhm5oQ,9855,10158,676-72-1596-992,25.0,1920,1080,train\ngSIN9Mhm5oQ,10184,10489,394-95-1245-946,25.0,1920,1080,train\ngSIN9Mhm5oQ,10489,10723,387-118-1255-986,25.0,1920,1080,train\ngSIN9Mhm5oQ,10723,10912,306-60-1185-939,25.0,1920,1080,train\ngSIN9Mhm5oQ,11170,11359,410-26-1376-992,25.0,1920,1080,train\ngSIN9Mhm5oQ,11488,11674,264-16-1276-1028,25.0,1920,1080,train\ngSIN9Mhm5oQ,11761,12221,648-85-1604-1041,25.0,1920,1080,train\ngSIN9Mhm5oQ,12221,12349,810-89-1761-1040,25.0,1920,1080,train\nIdnOeLhQWv4,720,1020,108-35-522-449,29.97,640,480,train\nFfvQG67eS7k,198,1222,200-14-894-708,23.97,1280,720,train\nFfvQG67eS7k,1222,2246,162-24-854-716,23.97,1280,720,train\nFfvQG67eS7k,2246,3270,187-15-883-711,23.97,1280,720,train\nFfvQG67eS7k,3270,4294,192-89-821-718,23.97,1280,720,train\nFfvQG67eS7k,4294,5318,197-106-806-715,23.97,1280,720,train\nFfvQG67eS7k,5318,5619,194-125-784-715,23.97,1280,720,train\nFfvQG67eS7k,5619,6483,171-93-797-719,23.97,1280,720,train\nFfvQG67eS7k,8108,8298,517-64-1110-657,23.97,1280,720,train\n_GY8d9rkDh8,272,773,389-136-872-619,29.97,1280,720,train\n_GY8d9rkDh8,1083,1261,295-113-898-716,29.97,1280,720,train\n_GY8d9rkDh8,2291,2428,495-127-1080-712,29.97,1280,720,train\n_GY8d9rkDh8,2863,3046,134-118-730-714,29.97,1280,720,train\n_GY8d9rkDh8,3119,3256,180-179-701-700,29.97,1280,720,train\n_GY8d9rkDh8,3725,3877,460-172-987-699,29.97,1280,720,train\n_GY8d9rkDh8,3975,4104,366-135-940-709,29.97,1280,720,train\n_GY8d9rkDh8,4150,4360,648-161-1160-673,29.97,1280,720,train\n_GY8d9rkDh8,4577,4712,395-176-835-616,29.97,1280,720,train\n_GY8d9rkDh8,4953,5123,479-222-875-618,29.97,1280,720,train\n_GY8d9rkDh8,5370,5773,494-185-903-594,29.97,1280,720,train\n_GY8d9rkDh8,6230,6665,297-40-951-694,29.97,1280,720,train\n0Q914by5A98,10440,10764,261-91-559-389,29.97,854,480,test\n2GX4WZSUVPo,368,1167,299-44-957-702,29.97,1280,720,train\n2GX4WZSUVPo,1274,1657,251-5-963-717,29.97,1280,720,train\n2GX4WZSUVPo,1726,2096,357-62-1007-712,29.97,1280,720,train\n2GX4WZSUVPo,2193,2616,489-54-1130-695,29.97,1280,720,train\n2GX4WZSUVPo,3215,3395,323-52-980-709,29.97,1280,720,train\n2GX4WZSUVPo,3438,3739,303-74-921-692,29.97,1280,720,train\n2GX4WZSUVPo,3739,4082,442-64-1052-674,29.97,1280,720,train\n2GX4WZSUVPo,4082,4318,481-33-1109-661,29.97,1280,720,train\n2GX4WZSUVPo,4361,4619,460-91-1029-660,29.97,1280,720,train\n2GX4WZSUVPo,4619,4912,370-63-971-664,29.97,1280,720,train\n2GX4WZSUVPo,5019,5273,416-81-1011-676,29.97,1280,720,train\n2GX4WZSUVPo,5317,5468,370-71-990-691,29.97,1280,720,train\n2GX4WZSUVPo,5701,5871,296-30-978-712,29.97,1280,720,train\n2GX4WZSUVPo,5990,6343,232-38-873-679,29.97,1280,720,train\n2GX4WZSUVPo,6343,6479,398-54-1038-694,29.97,1280,720,train\n2GX4WZSUVPo,6510,6656,305-83-902-680,29.97,1280,720,train\n2GX4WZSUVPo,6747,7161,324-68-927-671,29.97,1280,720,train\n2GX4WZSUVPo,7161,7295,484-70-1042-628,29.97,1280,720,train\n2GX4WZSUVPo,7399,7587,395-63-975-643,29.97,1280,720,train\n2GX4WZSUVPo,7668,8059,355-53-974-672,29.97,1280,720,train\n2GX4WZSUVPo,8850,9030,444-48-1097-701,29.97,1280,720,train\n2GX4WZSUVPo,9125,9665,227-23-914-710,29.97,1280,720,train\n2GX4WZSUVPo,9812,10048,476-35-1134-693,29.97,1280,720,train\n2GX4WZSUVPo,10357,10532,499-59-1149-709,29.97,1280,720,train\n2GX4WZSUVPo,10555,10919,262-34-921-693,29.97,1280,720,train\n2GX4WZSUVPo,11490,11704,415-33-1088-706,29.97,1280,720,train\n2GX4WZSUVPo,11756,12092,456-37-1129-710,29.97,1280,720,train\n2GX4WZSUVPo,12114,12597,332-59-989-716,29.97,1280,720,train\n2GX4WZSUVPo,12639,12777,468-84-1093-709,29.97,1280,720,train\n2GX4WZSUVPo,12868,13033,400-65-1036-701,29.97,1280,720,train\n2GX4WZSUVPo,13323,13535,480-48-1147-715,29.97,1280,720,train\n2GX4WZSUVPo,13926,14109,547-25-1206-684,29.97,1280,720,train\n2GX4WZSUVPo,14392,14604,397-46-1034-683,29.97,1280,720,train\n2GX4WZSUVPo,14619,14785,426-58-1030-662,29.97,1280,720,train\n2GX4WZSUVPo,14824,15062,341-8-1034-701,29.97,1280,720,train\n2GX4WZSUVPo,15139,15479,309-62-957-710,29.97,1280,720,train\n2GX4WZSUVPo,15507,15705,310-82-926-698,29.97,1280,720,train\n2GX4WZSUVPo,17311,17495,193-43-838-688,29.97,1280,720,train\n2GX4WZSUVPo,17524,18103,301-9-999-707,29.97,1280,720,train\nZOhoUyxIgaU,177,1201,690-370-1331-1011,25.0,1920,1080,train\nZOhoUyxIgaU,1243,1796,730-369-1385-1024,25.0,1920,1080,train\nZOhoUyxIgaU,1974,2113,700-314-1367-981,25.0,1920,1080,train\nZOhoUyxIgaU,2646,2856,628-204-1470-1046,25.0,1920,1080,train\nZOhoUyxIgaU,3003,3225,618-265-1433-1080,25.0,1920,1080,train\nZOhoUyxIgaU,3493,4517,722-308-1473-1059,25.0,1920,1080,train\nZOhoUyxIgaU,4517,4752,744-374-1393-1023,25.0,1920,1080,train\nZOhoUyxIgaU,4818,5005,771-362-1465-1056,25.0,1920,1080,train\nZOhoUyxIgaU,6950,7120,755-354-1468-1067,25.0,1920,1080,train\nZOhoUyxIgaU,7298,7427,891-359-1612-1080,25.0,1920,1080,train\nQCr8cdnal6o,262,1286,195-105-497-407,25.0,640,480,train\nQCr8cdnal6o,1330,1522,142-116-428-402,25.0,640,480,train\nQCr8cdnal6o,1615,2639,147-96-454-403,25.0,640,480,train\nQCr8cdnal6o,3184,3432,151-82-482-413,25.0,640,480,train\nQCr8cdnal6o,3713,3866,241-85-563-407,25.0,640,480,train\nQCr8cdnal6o,4301,4453,205-106-504-405,25.0,640,480,train\nQCr8cdnal6o,4821,5274,162-82-490-410,25.0,640,480,train\nQCr8cdnal6o,5627,5779,206-129-481-404,25.0,640,480,train\nQCr8cdnal6o,5952,6285,199-145-467-413,25.0,640,480,train\nQCr8cdnal6o,6495,6671,188-124-459-395,25.0,640,480,train\nQCr8cdnal6o,6671,6981,151-128-423-400,25.0,640,480,train\noNkBx4CZuEg,0,1024,552-115-1420-983,25.0,1920,1080,test\noNkBx4CZuEg,1024,2048,613-130-1480-997,25.0,1920,1080,test\noNkBx4CZuEg,2070,2311,527-107-1416-996,25.0,1920,1080,test\noNkBx4CZuEg,2312,2605,624-104-1513-993,25.0,1920,1080,test\noNkBx4CZuEg,2605,3529,885-140-1706-961,25.0,1920,1080,test\noNkBx4CZuEg,3647,3919,564-137-1392-965,25.0,1920,1080,test\noNkBx4CZuEg,3919,4109,558-93-1420-955,25.0,1920,1080,test\noNkBx4CZuEg,4110,4634,517-122-1364-969,25.0,1920,1080,test\noNkBx4CZuEg,4634,4861,697-115-1534-952,25.0,1920,1080,test\noNkBx4CZuEg,4861,5171,528-166-1289-927,25.0,1920,1080,test\noNkBx4CZuEg,5172,5811,558-174-1300-916,25.0,1920,1080,test\noNkBx4CZuEg,5811,6053,691-181-1402-892,25.0,1920,1080,test\noNkBx4CZuEg,6170,6468,662-142-1382-862,25.0,1920,1080,test\nXb93PUzUAYA,3,576,118-23-555-460,29.97,640,480,train\nXb93PUzUAYA,576,928,143-0-624-480,29.97,640,480,train\nXb93PUzUAYA,928,1326,106-5-575-474,29.97,640,480,train\nXb93PUzUAYA,2350,2714,134-25-589-480,29.97,640,480,train\nXb93PUzUAYA,2714,2880,164-2-629-467,29.97,640,480,train\nXb93PUzUAYA,4117,4281,130-21-579-470,29.97,640,480,train\nXb93PUzUAYA,5409,5946,98-17-528-447,29.97,640,480,train\nXb93PUzUAYA,5954,6978,139-26-560-447,29.97,640,480,train\nXb93PUzUAYA,7018,7350,158-50-543-435,29.97,640,480,train\nXb93PUzUAYA,7350,7807,110-44-520-454,29.97,640,480,train\nXb93PUzUAYA,7807,8055,106-42-538-474,29.97,640,480,train\nXb93PUzUAYA,8055,8241,92-20-526-454,29.97,640,480,train\nXb93PUzUAYA,8241,8766,110-29-556-475,29.97,640,480,train\nXb93PUzUAYA,8766,9236,101-28-535-462,29.97,640,480,train\nXb93PUzUAYA,9236,9457,151-24-578-451,29.97,640,480,train\nXb93PUzUAYA,9485,10110,143-44-547-448,29.97,640,480,train\nXb93PUzUAYA,10110,10924,165-24-587-446,29.97,640,480,train\nXb93PUzUAYA,10924,11662,86-38-491-443,29.97,640,480,train\nXb93PUzUAYA,11662,12033,127-18-544-435,29.97,640,480,train\nFvQUNJNvrU4,5413,5735,286-213-677-604,29.97,1280,720,train\nFvQUNJNvrU4,10877,11039,523-164-935-576,29.97,1280,720,train\nFvQUNJNvrU4,12496,12740,258-150-696-588,29.97,1280,720,train\nFvQUNJNvrU4,15530,15943,509-79-1075-645,29.97,1280,720,train\n-K57q5o3dn4,50,481,147-47-533-433,25.0,640,480,train\n-K57q5o3dn4,481,633,109-28-499-418,25.0,640,480,train\n-K57q5o3dn4,765,923,139-24-515-400,25.0,640,480,train\n-K57q5o3dn4,1170,1330,102-39-483-420,25.0,640,480,train\n-K57q5o3dn4,1875,2115,145-20-518-393,25.0,640,480,train\n-K57q5o3dn4,2353,2509,135-45-538-448,25.0,640,480,train\n-K57q5o3dn4,6353,6495,119-31-512-424,25.0,640,480,train\n-K57q5o3dn4,8015,8240,128-62-445-379,25.0,640,480,train\n-K57q5o3dn4,9860,9990,186-75-506-395,25.0,640,480,train\nbI1XOdhWVaw,299,879,243-94-745-596,29.97,932,720,train\nbI1XOdhWVaw,969,1132,281-134-763-616,29.97,932,720,train\nbI1XOdhWVaw,1749,1934,295-95-835-635,29.97,932,720,train\nbI1XOdhWVaw,2735,3127,221-141-682-602,29.97,932,720,train\nbI1XOdhWVaw,4512,4668,157-157-581-581,29.97,932,720,train\nIWUTAZF8yVw,1068,1204,686-455-1241-1010,29.97,1920,1080,train\nIWUTAZF8yVw,1317,1497,918-467-1475-1024,29.97,1920,1080,train\nIWUTAZF8yVw,3247,3401,732-441-1308-1017,29.97,1920,1080,train\nIWUTAZF8yVw,3765,3986,535-480-1091-1036,29.97,1920,1080,train\nIWUTAZF8yVw,5489,5628,534-475-1063-1004,29.97,1920,1080,train\nIWUTAZF8yVw,7160,7404,1235-458-1807-1030,29.97,1920,1080,train\nIWUTAZF8yVw,8978,9212,253-439-858-1044,29.97,1920,1080,train\nIWUTAZF8yVw,10436,10652,387-385-1045-1043,29.97,1920,1080,train\nEaEZVfhn07o,3814,4838,84-20-531-467,29.97,640,480,train\nEaEZVfhn07o,4838,5107,90-34-520-464,29.97,640,480,train\nLmHZE5oklag,628,1146,255-145-1130-1020,29.97,1440,1080,train\nLmHZE5oklag,1146,2045,177-102-1106-1031,29.97,1440,1080,train\nLmHZE5oklag,2056,2519,172-157-1030-1015,29.97,1440,1080,train\nLmHZE5oklag,2519,3238,281-187-1149-1055,29.97,1440,1080,train\nLmHZE5oklag,3245,3444,169-145-1022-998,29.97,1440,1080,train\nLmHZE5oklag,3444,3932,224-192-1077-1045,29.97,1440,1080,train\nLmHZE5oklag,3932,4595,238-154-1078-994,29.97,1440,1080,train\nLmHZE5oklag,4812,4951,306-206-1081-981,29.97,1440,1080,train\nLmHZE5oklag,4951,5406,231-179-1073-1021,29.97,1440,1080,train\nLmHZE5oklag,6213,6617,240-189-1107-1056,29.97,1440,1080,train\n7dYtvnHGNxQ,237,390,156-58-544-446,29.97,720,480,train\n7dYtvnHGNxQ,526,672,165-75-545-455,29.97,720,480,train\n7dYtvnHGNxQ,672,802,173-80-554-461,29.97,720,480,train\n7dYtvnHGNxQ,1040,1182,179-67-532-420,29.97,720,480,train\n7dYtvnHGNxQ,1479,1611,197-93-564-460,29.97,720,480,train\n7dYtvnHGNxQ,1644,2294,164-54-560-450,29.97,720,480,train\n7dYtvnHGNxQ,2300,2440,154-76-512-434,29.97,720,480,train\n7dYtvnHGNxQ,2640,2856,130-45-516-431,29.97,720,480,train\n7dYtvnHGNxQ,3750,4079,175-50-556-431,29.97,720,480,train\n7dYtvnHGNxQ,4079,4278,194-15-601-422,29.97,720,480,train\n7dYtvnHGNxQ,4299,4448,218-21-640-443,29.97,720,480,train\n7dYtvnHGNxQ,4545,4732,193-37-585-429,29.97,720,480,train\n7dYtvnHGNxQ,4934,5501,221-55-607-441,29.97,720,480,train\n7dYtvnHGNxQ,5675,5897,142-71-531-460,29.97,720,480,train\n7dYtvnHGNxQ,6009,6169,162-71-545-454,29.97,720,480,train\n7dYtvnHGNxQ,7336,7508,124-82-517-475,29.97,720,480,train\n4rW_9Y1eci8,1215,1409,346-27-922-603,25.0,1280,720,train\n4rW_9Y1eci8,1409,1745,280-26-785-531,25.0,1280,720,train\n4rW_9Y1eci8,1927,2078,310-29-848-567,25.0,1280,720,train\n4rW_9Y1eci8,2272,2460,229-10-778-559,25.0,1280,720,train\n4rW_9Y1eci8,2460,2611,164-30-725-591,25.0,1280,720,train\n4rW_9Y1eci8,2919,3089,234-23-710-499,25.0,1280,720,train\n4rW_9Y1eci8,3420,3556,230-11-740-521,25.0,1280,720,train\n4rW_9Y1eci8,4067,4339,189-4-728-543,25.0,1280,720,train\n4rW_9Y1eci8,4401,4569,125-9-641-525,25.0,1280,720,train\n4rW_9Y1eci8,4569,4710,199-15-727-543,25.0,1280,720,train\n4rW_9Y1eci8,5157,5437,311-14-830-533,25.0,1280,720,train\nmndSqTrxpts,0,175,5-168-496-659,30.0,1280,720,test\nmndSqTrxpts,2234,2406,700-130-1230-660,30.0,1280,720,test\nmndSqTrxpts,2406,2550,565-132-1069-636,30.0,1280,720,test\nmndSqTrxpts,2911,3105,576-116-1123-663,30.0,1280,720,test\nmndSqTrxpts,3600,3794,338-136-879-677,30.0,1280,720,test\nWh3AmDsdQtM,0,1024,149-52-565-468,29.97,640,480,train\nWh3AmDsdQtM,1024,2048,127-55-539-467,29.97,640,480,train\nWh3AmDsdQtM,2048,2187,109-74-506-471,29.97,640,480,train\nWh3AmDsdQtM,2187,3211,122-53-540-471,29.97,640,480,train\nWh3AmDsdQtM,3211,4235,127-64-534-471,29.97,640,480,train\nWh3AmDsdQtM,4235,5227,136-66-538-468,29.97,640,480,train\nWh3AmDsdQtM,5228,5613,124-61-537-474,29.97,640,480,train\nWh3AmDsdQtM,5613,5834,78-56-489-467,29.97,640,480,train\nWh3AmDsdQtM,5834,6097,88-35-524-471,29.97,640,480,train\nHZks-9WmW5s,100,429,120-91-468-439,29.97,640,480,train\nHZks-9WmW5s,473,881,116-84-464-432,29.97,640,480,train\nHZks-9WmW5s,937,1383,113-80-461-428,29.97,640,480,train\nHZks-9WmW5s,1786,2031,159-70-555-466,29.97,640,480,train\nHZks-9WmW5s,2890,3097,169-73-551-455,29.97,640,480,train\nHZks-9WmW5s,3136,3563,157-72-557-472,29.97,640,480,train\ndSIkl9ONOJc,400,1424,245-88-615-458,30.0,854,480,train\ndSIkl9ONOJc,1478,2055,268-76-615-423,30.0,854,480,train\ndSIkl9ONOJc,2133,3039,248-89-620-461,30.0,854,480,train\ndSIkl9ONOJc,3039,3199,254-97-616-459,30.0,854,480,train\ndSIkl9ONOJc,3199,3481,249-88-621-460,30.0,854,480,train\ndSIkl9ONOJc,3481,4328,270-85-612-427,30.0,854,480,train\ndSIkl9ONOJc,4389,4739,244-85-623-464,30.0,854,480,train\ndSIkl9ONOJc,4777,5311,250-92-620-462,30.0,854,480,train\ndSIkl9ONOJc,5311,5762,238-74-627-463,30.0,854,480,train\ndSIkl9ONOJc,6170,6801,241-76-622-457,30.0,854,480,train\ndSIkl9ONOJc,6820,7157,242-75-627-460,30.0,854,480,train\ndSIkl9ONOJc,7536,7964,244-58-613-427,30.0,854,480,train\ndSIkl9ONOJc,7964,8151,240-38-636-434,30.0,854,480,train\ndSIkl9ONOJc,8249,8560,241-72-628-459,30.0,854,480,train\ndSIkl9ONOJc,8573,8721,236-71-626-461,30.0,854,480,train\nOOzyPCkjVmE,250,500,157-91-490-424,30.0,640,480,train\nOOzyPCkjVmE,500,750,177-95-495-413,30.0,640,480,train\nOOzyPCkjVmE,750,893,182-110-493-421,30.0,640,480,train\nOOzyPCkjVmE,1868,2000,130-113-441-424,30.0,640,480,train\nOOzyPCkjVmE,2064,2250,115-98-450-433,30.0,640,480,train\nOOzyPCkjVmE,2327,2500,108-109-419-420,30.0,640,480,train\nOOzyPCkjVmE,2591,2874,93-102-401-410,30.0,640,480,train\nOOzyPCkjVmE,5500,5670,84-92-407-415,30.0,640,480,train\nOOzyPCkjVmE,7316,7454,167-91-485-409,30.0,640,480,train\nOOzyPCkjVmE,7573,7742,128-80-479-431,30.0,640,480,train\nOOzyPCkjVmE,10361,10500,200-98-478-376,30.0,640,480,train\n5ujMzSyHO_8,687,1459,129-124-420-415,25.0,600,480,train\n5ujMzSyHO_8,1459,1690,162-120-453-411,25.0,600,480,train\nskHdRWJ_Zuk,2035,2471,300-175-839-714,29.97,1280,720,train\nskHdRWJ_Zuk,2895,3164,241-154-796-709,29.97,1280,720,train\nskHdRWJ_Zuk,3227,3410,255-145-827-717,29.97,1280,720,train\nskHdRWJ_Zuk,13321,13499,288-164-837-713,29.97,1280,720,train\nskHdRWJ_Zuk,16937,17125,435-198-926-689,29.97,1280,720,train\nskHdRWJ_Zuk,17825,17983,256-153-820-717,29.97,1280,720,train\nskHdRWJ_Zuk,18854,19003,236-136-802-702,29.97,1280,720,train\nskHdRWJ_Zuk,19003,19142,250-108-848-706,29.97,1280,720,train\nskHdRWJ_Zuk,19651,19812,350-159-909-718,29.97,1280,720,train\ngkt8MPv8g1k,4933,5091,234-142-725-633,29.97,1280,720,train\ngkt8MPv8g1k,5143,5440,228-137-731-640,29.97,1280,720,train\ngkt8MPv8g1k,7498,7631,238-124-771-657,29.97,1280,720,train\ngkt8MPv8g1k,7840,8140,253-99-793-639,29.97,1280,720,train\ngkt8MPv8g1k,8470,8648,276-122-730-576,29.97,1280,720,train\ngkt8MPv8g1k,9123,9323,339-150-799-610,29.97,1280,720,train\ngkt8MPv8g1k,10282,10432,291-119-801-629,29.97,1280,720,train\ngkt8MPv8g1k,11308,11465,315-36-916-637,29.97,1280,720,train\ngkt8MPv8g1k,11865,11997,460-81-1025-646,29.97,1280,720,train\ngkt8MPv8g1k,12019,12165,641-103-1201-663,29.97,1280,720,train\ngkt8MPv8g1k,13072,13331,229-108-750-629,29.97,1280,720,train\ngkt8MPv8g1k,13502,13686,351-136-854-639,29.97,1280,720,train\ngkt8MPv8g1k,14795,14974,245-59-782-596,29.97,1280,720,train\nolTSwTofrDM,420,660,278-26-909-657,29.97,1280,720,train\nolTSwTofrDM,800,1163,347-57-944-654,29.97,1280,720,train\nolTSwTofrDM,1163,1410,369-27-1010-668,29.97,1280,720,train\nolTSwTofrDM,1839,2231,367-70-948-651,29.97,1280,720,train\nolTSwTofrDM,2392,2524,463-81-1023-641,29.97,1280,720,train\nolTSwTofrDM,2524,2697,361-84-911-634,29.97,1280,720,train\nolTSwTofrDM,2702,2937,463-70-1035-642,29.97,1280,720,train\nolTSwTofrDM,3263,3403,311-83-871-643,29.97,1280,720,train\nolTSwTofrDM,3861,4063,400-26-1005-631,29.97,1280,720,train\nolTSwTofrDM,4251,4385,180-49-765-634,29.97,1280,720,train\nolTSwTofrDM,4600,4745,307-83-861-637,29.97,1280,720,train\nolTSwTofrDM,4745,5029,211-95-756-640,29.97,1280,720,train\nolTSwTofrDM,5238,5373,251-90-796-635,29.97,1280,720,train\nolTSwTofrDM,6268,6492,284-46-890-652,29.97,1280,720,train\njFuiqvVaESE,450,1050,303-142-717-556,29.97,960,720,train\njFuiqvVaESE,1561,1742,259-85-773-599,29.97,960,720,train\njFuiqvVaESE,2154,2340,249-133-702-586,29.97,960,720,train\njFuiqvVaESE,2661,2850,193-99-664-570,29.97,960,720,train\njFuiqvVaESE,3980,4175,247-94-733-580,29.97,960,720,train\njFuiqvVaESE,4222,4350,170-89-719-638,29.97,960,720,train\njFuiqvVaESE,4873,5021,276-109-742-575,29.97,960,720,train\njFuiqvVaESE,5650,5884,231-93-714-576,29.97,960,720,train\njFuiqvVaESE,6800,6950,269-138-706-575,29.97,960,720,train\nMo87mOAnAio,115,579,498-178-953-633,29.97,1280,720,train\nMo87mOAnAio,658,878,481-169-934-622,29.97,1280,720,train\nMo87mOAnAio,878,1151,518-195-966-643,29.97,1280,720,train\nMo87mOAnAio,1842,2317,470-212-889-631,29.97,1280,720,train\nMo87mOAnAio,2321,2696,497-238-837-578,29.97,1280,720,train\nMo87mOAnAio,5003,5136,340-155-896-711,29.97,1280,720,train\nkt2xwj8xiZI,381,996,241-119-713-591,29.97,1280,720,train\nkt2xwj8xiZI,1022,1224,238-162-683-607,29.97,1280,720,train\nkt2xwj8xiZI,1320,1525,217-147-693-623,29.97,1280,720,train\nkt2xwj8xiZI,1587,1758,222-156-686-620,29.97,1280,720,train\nkt2xwj8xiZI,2167,2447,376-124-870-618,29.97,1280,720,train\nkt2xwj8xiZI,3157,3286,578-133-1063-618,29.97,1280,720,train\nkt2xwj8xiZI,3343,3474,605-150-1074-619,29.97,1280,720,train\nkt2xwj8xiZI,4010,4169,384-118-868-602,29.97,1280,720,train\nkt2xwj8xiZI,4436,4597,301-135-792-626,29.97,1280,720,train\nkt2xwj8xiZI,4637,4868,293-140-779-626,29.97,1280,720,train\nkt2xwj8xiZI,5497,5712,184-159-628-603,29.97,1280,720,train\nkt2xwj8xiZI,5794,6223,199-147-646-594,29.97,1280,720,train\nkt2xwj8xiZI,6267,6404,143-151-605-613,29.97,1280,720,train\nkt2xwj8xiZI,6804,7020,349-148-823-622,29.97,1280,720,train\nkt2xwj8xiZI,8422,8633,646-109-1127-590,29.97,1280,720,train\nkt2xwj8xiZI,9044,9214,404-128-885-609,29.97,1280,720,train\nkt2xwj8xiZI,9316,9571,431-125-934-628,29.97,1280,720,train\nkt2xwj8xiZI,9967,10146,171-125-646-600,29.97,1280,720,train\nkt2xwj8xiZI,10505,10667,331-154-762-585,29.97,1280,720,train\nkt2xwj8xiZI,11308,11484,304-174-713-583,29.97,1280,720,train\nkt2xwj8xiZI,12196,12340,302-137-755-590,29.97,1280,720,train\nkt2xwj8xiZI,12340,12638,284-127-735-578,29.97,1280,720,train\ncB0yZrBOIXQ,362,639,336-89-934-687,25.0,1280,720,test\ncB0yZrBOIXQ,866,1020,310-77-912-679,25.0,1280,720,test\ncB0yZrBOIXQ,1162,1627,291-111-893-713,25.0,1280,720,test\ncB0yZrBOIXQ,4698,4834,325-69-951-695,25.0,1280,720,test\ncB0yZrBOIXQ,4834,5038,253-61-897-705,25.0,1280,720,test\ncB0yZrBOIXQ,5098,5317,383-74-985-676,25.0,1280,720,test\nTtc2stTBRGI,599,850,181-116-696-631,29.97,1280,720,train\nTtc2stTBRGI,922,1054,261-162-723-624,29.97,1280,720,train\nTtc2stTBRGI,1546,1688,388-145-865-622,29.97,1280,720,train\nTtc2stTBRGI,2450,2592,651-148-1113-610,29.97,1280,720,train\nTtc2stTBRGI,2671,2852,560-184-976-600,29.97,1280,720,train\nTtc2stTBRGI,2923,3052,474-139-946-611,29.97,1280,720,train\nTtc2stTBRGI,4145,4274,412-107-951-646,29.97,1280,720,train\nTtc2stTBRGI,4362,4530,279-151-769-641,29.97,1280,720,train\nTtc2stTBRGI,5305,5488,224-160-663-599,29.97,1280,720,train\nTtc2stTBRGI,5600,5796,227-168-659-600,29.97,1280,720,train\nTtc2stTBRGI,5796,5925,230-161-681-612,29.97,1280,720,train\nTtc2stTBRGI,6208,6374,253-173-675-595,29.97,1280,720,train\nTtc2stTBRGI,6484,6627,255-183-660-588,29.97,1280,720,train\nTtc2stTBRGI,6656,6787,237-174-652-589,29.97,1280,720,train\nTtc2stTBRGI,7095,7241,265-137-726-598,29.97,1280,720,train\nTtc2stTBRGI,7243,7466,249-132-706-589,29.97,1280,720,train\nETywBOZ19Y0,606,738,1062-260-1876-1074,29.97,1920,1080,train\nETywBOZ19Y0,865,995,725-147-1561-983,29.97,1920,1080,train\nETywBOZ19Y0,995,1173,687-218-1491-1022,29.97,1920,1080,train\nETywBOZ19Y0,1192,1325,495-238-1258-1001,29.97,1920,1080,train\nETywBOZ19Y0,1447,1668,501-167-1348-1014,29.97,1920,1080,train\nETywBOZ19Y0,1668,1802,580-124-1471-1015,29.97,1920,1080,train\nETywBOZ19Y0,1926,2239,599-191-1477-1069,29.97,1920,1080,train\nETywBOZ19Y0,4796,5567,628-30-1677-1079,29.97,1920,1080,train\nETywBOZ19Y0,5724,6134,594-62-1610-1078,29.97,1920,1080,train\nETywBOZ19Y0,7020,7273,162-83-1159-1080,29.97,1920,1080,train\nETywBOZ19Y0,8463,8654,38-26-1071-1059,29.97,1920,1080,train\nETywBOZ19Y0,9818,10612,764-35-1740-1011,29.97,1920,1080,train\nETywBOZ19Y0,10883,11441,1021-140-1864-983,29.97,1920,1080,train\nETywBOZ19Y0,11614,11766,472-172-1377-1077,29.97,1920,1080,train\nETywBOZ19Y0,11766,12135,537-128-1468-1059,29.97,1920,1080,train\nETywBOZ19Y0,12323,12606,488-63-1472-1047,29.97,1920,1080,train\nETywBOZ19Y0,12639,13004,645-27-1687-1069,29.97,1920,1080,train\nfLYeTpU8b1A,2654,2936,461-10-1525-1074,29.97,1920,1080,train\nfLYeTpU8b1A,4439,4576,50-21-1098-1069,29.97,1920,1080,train\nDMEaUoA8EPE,28,354,560-331-1218-989,25.0,1920,1080,test\nDMEaUoA8EPE,597,810,514-387-1177-1050,25.0,1920,1080,test\niFMbu9-Mejc,75,344,230-45-654-469,25.0,854,480,train\niFMbu9-Mejc,344,520,199-23-642-466,25.0,854,480,train\niFMbu9-Mejc,834,1054,224-39-638-453,25.0,854,480,train\niFMbu9-Mejc,1216,1369,234-56-637-459,25.0,854,480,train\niFMbu9-Mejc,2009,2150,263-77-645-459,25.0,854,480,train\niFMbu9-Mejc,2759,3064,197-54-607-464,25.0,854,480,train\niFMbu9-Mejc,4989,5131,260-56-648-444,25.0,854,480,train\nnHGRRI8otpE,4964,5223,191-103-802-714,29.67,1280,720,train\nnHGRRI8otpE,6556,6821,648-125-1198-675,29.67,1280,720,train\nnHGRRI8otpE,6864,7297,699-93-1270-664,29.67,1280,720,train\nnHGRRI8otpE,7644,7843,597-108-1113-624,29.67,1280,720,train\nnHGRRI8otpE,7843,8091,589-81-1130-622,29.67,1280,720,train\nnHGRRI8otpE,8091,8229,494-55-1056-617,29.67,1280,720,train\nnHGRRI8otpE,8253,8429,574-98-1082-606,29.67,1280,720,train\nnHGRRI8otpE,8429,8701,616-64-1146-594,29.67,1280,720,train\nnHGRRI8otpE,10363,10598,134-13-787-666,29.67,1280,720,train\nnHGRRI8otpE,10965,11173,130-30-757-657,29.67,1280,720,train\nnHGRRI8otpE,11292,11438,9-0-672-662,29.67,1280,720,train\nnHGRRI8otpE,12581,13029,99-84-613-598,29.67,1280,720,train\nnHGRRI8otpE,13241,13424,93-64-607-578,29.67,1280,720,train\nmNtz9Kq4-YU,0,246,295-143-700-548,25.0,1280,720,train\nmNtz9Kq4-YU,1202,1344,513-153-894-534,25.0,1280,720,train\nmNtz9Kq4-YU,3942,4319,345-111-727-493,25.0,1280,720,train\nmNtz9Kq4-YU,8072,8434,347-87-747-487,25.0,1280,720,train\nlCb5w6n8kPs,4451,4631,273-126-535-388,30.0,810,480,test\nlCb5w6n8kPs,10150,10295,292-123-558-389,30.0,810,480,test\nlCb5w6n8kPs,11879,12014,237-88-541-392,30.0,810,480,test\nlCb5w6n8kPs,12081,12216,242-88-547-393,30.0,810,480,test\nS5DkrAAcQP0,368,1392,44-55-674-685,25.0,1280,720,train\nS5DkrAAcQP0,1392,2270,247-132-749-634,25.0,1280,720,train\nS5DkrAAcQP0,2379,2562,372-145-846-619,25.0,1280,720,train\nS5DkrAAcQP0,2597,2795,366-160-847-641,25.0,1280,720,train\nS5DkrAAcQP0,2836,3048,348-136-848-636,25.0,1280,720,train\nS5DkrAAcQP0,3149,3587,506-118-1027-639,25.0,1280,720,train\nS5DkrAAcQP0,3957,4124,535-110-1093-668,25.0,1280,720,train\nS5DkrAAcQP0,4124,4268,553-75-1152-674,25.0,1280,720,train\nZFpTP2fSThw,0,135,826-231-1625-1030,25.0,1920,1080,test\nZFpTP2fSThw,135,270,815-245-1592-1022,25.0,1920,1080,test\nZFpTP2fSThw,405,540,808-256-1609-1057,25.0,1920,1080,test\nZFpTP2fSThw,540,675,816-241-1604-1029,25.0,1920,1080,test\nZFpTP2fSThw,744,945,859-316-1605-1062,25.0,1920,1080,test\nZFpTP2fSThw,1826,1956,806-310-1512-1016,25.0,1920,1080,test\nZFpTP2fSThw,5265,5400,948-173-1767-992,25.0,1920,1080,test\nh8zzn3C5TgU,809,942,407-91-1004-688,29.97,1280,720,train\nh8zzn3C5TgU,942,1167,404-52-1046-694,29.97,1280,720,train\nh8zzn3C5TgU,1167,1519,323-20-1016-713,29.97,1280,720,train\nh8zzn3C5TgU,1942,2314,398-68-1029-699,29.97,1280,720,train\nh8zzn3C5TgU,2894,3238,323-53-979-709,29.97,1280,720,train\nh8zzn3C5TgU,3635,4148,393-44-1044-695,29.97,1280,720,train\nboSXUZ2t7yQ,3034,3220,207-28-625-446,30.0,810,480,train\nboSXUZ2t7yQ,3311,3458,212-31-623-442,30.0,810,480,train\nboSXUZ2t7yQ,3548,3717,230-49-593-412,30.0,810,480,train\nboSXUZ2t7yQ,3717,4456,203-31-587-415,30.0,810,480,train\nboSXUZ2t7yQ,4549,4703,235-46-605-416,30.0,810,480,train\nboSXUZ2t7yQ,4795,5004,240-40-613-413,30.0,810,480,train\nboSXUZ2t7yQ,5058,5189,230-26-626-422,30.0,810,480,train\n6jHyn4z0KLk,1890,2170,165-112-440-387,25.0,640,480,train\n6jHyn4z0KLk,2962,3100,197-120-469-392,25.0,640,480,train\n0l9UlEelXFI,196,737,153-112-474-433,25.0,600,480,train\n0l9UlEelXFI,738,916,187-149-451-413,25.0,600,480,train\n0l9UlEelXFI,945,1236,193-145-459-411,25.0,600,480,train\n0l9UlEelXFI,1443,1623,226-141-514-429,25.0,600,480,train\n0l9UlEelXFI,1744,2138,237-142-528-433,25.0,600,480,train\n0l9UlEelXFI,2148,2364,111-122-424-435,25.0,600,480,train\n0l9UlEelXFI,2373,2545,90-120-407-437,25.0,600,480,train\n0l9UlEelXFI,2545,2699,176-135-476-435,25.0,600,480,train\n0l9UlEelXFI,2985,3443,230-125-539-434,25.0,600,480,train\n0l9UlEelXFI,4050,4310,101-110-463-472,25.0,600,480,train\n0l9UlEelXFI,4991,5173,88-57-507-476,25.0,600,480,train\n0l9UlEelXFI,5201,5380,132-52-556-476,25.0,600,480,train\nkTHsY7fbcgQ,361,762,460-90-995-625,25.0,1280,720,train\nkTHsY7fbcgQ,762,1045,473-54-1060-641,25.0,1280,720,train\nkTHsY7fbcgQ,1045,1235,457-95-1031-669,25.0,1280,720,train\nkTHsY7fbcgQ,1235,2259,350-67-947-664,25.0,1280,720,train\nkTHsY7fbcgQ,2365,2591,508-78-1109-679,25.0,1280,720,train\nkTHsY7fbcgQ,2906,3123,385-95-926-636,25.0,1280,720,train\nkTHsY7fbcgQ,3186,3333,393-113-931-651,25.0,1280,720,train\nkTHsY7fbcgQ,3509,3686,390-120-913-643,25.0,1280,720,train\nkTHsY7fbcgQ,3806,3940,391-113-925-647,25.0,1280,720,train\nkTHsY7fbcgQ,4203,5227,438-26-1092-680,25.0,1280,720,train\nkTHsY7fbcgQ,5275,5758,443-87-1048-692,25.0,1280,720,train\nkTHsY7fbcgQ,5758,5931,473-58-1089-674,25.0,1280,720,train\nPKE4yfDESa0,0,421,92-23-529-460,29.97,640,480,train\nPKE4yfDESa0,421,1445,95-0-558-463,29.97,640,480,train\nPKE4yfDESa0,1445,2469,92-22-533-463,29.97,640,480,train\nPKE4yfDESa0,2469,3493,108-38-532-462,29.97,640,480,train\nPKE4yfDESa0,3493,4517,98-26-537-465,29.97,640,480,train\nPKE4yfDESa0,4598,4818,101-27-533-459,29.97,640,480,train\nPKE4yfDESa0,4818,5657,92-5-551-464,29.97,640,480,train\nvVRBxYkYILo,166,1190,1003-109-1855-961,29.97,1920,1080,train\nvVRBxYkYILo,1242,1499,1034-148-1841-955,29.97,1920,1080,train\nvVRBxYkYILo,2555,2883,191-208-991-1008,29.97,1920,1080,train\nvVRBxYkYILo,3026,3161,71-207-862-998,29.97,1920,1080,train\nvVRBxYkYILo,3218,3387,72-188-836-952,29.97,1920,1080,train\nvVRBxYkYILo,3809,3954,221-128-1080-987,29.97,1920,1080,train\nvVRBxYkYILo,4168,4399,365-94-1313-1042,29.97,1920,1080,train\nvVRBxYkYILo,4399,4529,593-121-1493-1021,29.97,1920,1080,train\nvVRBxYkYILo,4663,5010,714-37-1662-985,29.97,1920,1080,train\nvVRBxYkYILo,6187,6412,353-154-1064-865,29.97,1920,1080,train\nvVRBxYkYILo,6733,6900,313-208-984-879,29.97,1920,1080,train\nvVRBxYkYILo,6919,7085,234-207-926-899,29.97,1920,1080,train\nvVRBxYkYILo,7105,7266,186-152-911-877,29.97,1920,1080,train\nvVRBxYkYILo,7291,7546,506-241-1127-862,29.97,1920,1080,train\nvVRBxYkYILo,8538,8680,1149-271-1747-869,29.97,1920,1080,train\nvVRBxYkYILo,8961,9207,1024-206-1756-938,29.97,1920,1080,train\nvVRBxYkYILo,9314,9833,918-271-1530-883,29.97,1920,1080,train\nvVRBxYkYILo,10043,10645,875-207-1528-860,29.97,1920,1080,train\n-uPGb1vn9Pk,271,520,565-404-822-661,25.0,1280,720,train\n-uPGb1vn9Pk,3527,3903,626-416-882-672,25.0,1280,720,train\n-uPGb1vn9Pk,8686,8949,712-400-974-662,25.0,1280,720,train\n-uPGb1vn9Pk,10632,10827,680-405-962-687,25.0,1280,720,train\n-uPGb1vn9Pk,10837,10965,756-423-1017-684,25.0,1280,720,train\n-uPGb1vn9Pk,11753,11958,785-389-1076-680,25.0,1280,720,train\n-uPGb1vn9Pk,12081,12508,735-387-1033-685,25.0,1280,720,train\n-uPGb1vn9Pk,12508,12793,667-387-970-690,25.0,1280,720,train\n-uPGb1vn9Pk,12818,12996,641-402-924-685,25.0,1280,720,train\n-uPGb1vn9Pk,13134,13484,538-407-812-681,25.0,1280,720,train\n-uPGb1vn9Pk,13484,13618,469-416-730-677,25.0,1280,720,train\n-uPGb1vn9Pk,14669,14909,349-413-610-674,25.0,1280,720,train\n-uPGb1vn9Pk,14915,15536,358-407-627-676,25.0,1280,720,train\n-uPGb1vn9Pk,15849,16074,345-416-604-675,25.0,1280,720,train\n-uPGb1vn9Pk,20707,21076,504-374-792-662,25.0,1280,720,train\nw81Tr0Dp1K8,1120,1378,4-307-484-787,29.97,1920,1080,test\nw81Tr0Dp1K8,1375,1516,1267-268-1793-794,29.97,1920,1080,test\nw81Tr0Dp1K8,2125,2449,541-220-1163-842,29.97,1920,1080,test\nw81Tr0Dp1K8,2947,3160,569-222-1178-831,29.97,1920,1080,test\nw81Tr0Dp1K8,3550,3698,4-314-470-780,29.97,1920,1080,test\nw81Tr0Dp1K8,4036,4218,670-235-1287-852,29.97,1920,1080,test\nw81Tr0Dp1K8,8275,8854,432-149-1199-916,29.97,1920,1080,test\nw81Tr0Dp1K8,8965,9131,409-86-1249-926,29.97,1920,1080,test\nw81Tr0Dp1K8,10513,10662,579-181-1300-902,29.97,1920,1080,test\nw81Tr0Dp1K8,11502,11671,467-136-1241-910,29.97,1920,1080,test\nw81Tr0Dp1K8,12112,12295,22-265-586-829,29.97,1920,1080,test\nw81Tr0Dp1K8,12240,12431,434-87-1264-917,29.97,1920,1080,test\nw81Tr0Dp1K8,12373,12752,1090-190-1719-819,29.97,1920,1080,test\nw81Tr0Dp1K8,12900,13080,382-140-1140-898,29.97,1920,1080,test\nw81Tr0Dp1K8,13602,13783,438-132-1215-909,29.97,1920,1080,test\nw81Tr0Dp1K8,14180,14347,460-140-1240-920,29.97,1920,1080,test\nw81Tr0Dp1K8,14197,14377,12-320-522-830,29.97,1920,1080,test\nw81Tr0Dp1K8,14756,14888,1027-196-1654-823,29.97,1920,1080,test\nw81Tr0Dp1K8,15145,15329,416-85-1235-904,29.97,1920,1080,test\nw81Tr0Dp1K8,15329,15485,6-269-573-836,29.97,1920,1080,test\nw81Tr0Dp1K8,15339,15664,422-120-1193-891,29.97,1920,1080,test\nw81Tr0Dp1K8,15670,15801,6-262-579-835,29.97,1920,1080,test\nA3ZmT97hAWU,95,678,136-86-477-427,29.97,640,480,test\nA3ZmT97hAWU,768,1653,103-66-487-450,29.97,640,480,test\nA3ZmT97hAWU,1737,2033,117-50-500-433,29.97,640,480,test\nA3ZmT97hAWU,2455,2899,49-36-466-453,29.97,640,480,test\nA3ZmT97hAWU,3006,3151,147-77-508-438,29.97,640,480,test\nA3ZmT97hAWU,3169,3528,83-69-453-439,29.97,640,480,test\nA3ZmT97hAWU,3883,4023,128-67-468-407,29.97,640,480,test\nA3ZmT97hAWU,4436,4582,159-92-496-429,29.97,640,480,test\nA3ZmT97hAWU,5410,5643,176-79-515-418,29.97,640,480,test\nA3ZmT97hAWU,6808,7014,148-83-485-420,29.97,640,480,test\nA3ZmT97hAWU,7482,7618,72-58-423-409,29.97,640,480,test\nA3ZmT97hAWU,7778,8125,148-71-481-404,29.97,640,480,test\nA3ZmT97hAWU,8544,8731,58-82-396-420,29.97,640,480,test\nA3ZmT97hAWU,9460,9605,33-69-399-435,29.97,640,480,test\nyZ5l8EJeCMI,165,992,59-94-369-404,25.0,600,480,train\nyZ5l8EJeCMI,2823,3049,116-121-390-395,25.0,600,480,train\neOdr6vu_Y6g,1307,1494,414-194-790-570,29.97,1280,720,train\neOdr6vu_Y6g,1936,2203,431-194-804-567,29.97,1280,720,train\neOdr6vu_Y6g,2203,2348,409-236-738-565,29.97,1280,720,train\neOdr6vu_Y6g,3059,3265,480-225-821-566,29.97,1280,720,train\neOdr6vu_Y6g,3451,3616,444-187-815-558,29.97,1280,720,train\neOdr6vu_Y6g,6837,6992,281-52-944-715,29.97,1280,720,train\neOdr6vu_Y6g,9748,9938,327-139-875-687,29.97,1280,720,train\neOdr6vu_Y6g,11378,11551,183-120-774-711,29.97,1280,720,train\ntN_7bWyIWDU,16,1005,279-39-868-628,30.0,1280,720,train\ntN_7bWyIWDU,1519,1753,632-89-1167-624,30.0,1280,720,train\ntN_7bWyIWDU,2885,3015,381-128-906-653,30.0,1280,720,train\ntN_7bWyIWDU,3015,3177,416-104-950-638,30.0,1280,720,train\ntN_7bWyIWDU,3177,3495,322-97-840-615,30.0,1280,720,train\ntN_7bWyIWDU,3821,3970,371-100-901-630,30.0,1280,720,train\ntN_7bWyIWDU,3970,4160,258-104-778-624,30.0,1280,720,train\ntN_7bWyIWDU,4220,4570,250-79-801-630,30.0,1280,720,train\ntN_7bWyIWDU,4747,5007,261-93-812-644,30.0,1280,720,train\ntN_7bWyIWDU,5007,5280,349-65-903-619,30.0,1280,720,train\ntN_7bWyIWDU,5280,5713,306-97-846-637,30.0,1280,720,train\ntN_7bWyIWDU,5924,6499,311-102-878-669,30.0,1280,720,train\ntN_7bWyIWDU,6581,6750,306-106-865-665,30.0,1280,720,train\ntN_7bWyIWDU,7040,7269,327-63-894-630,30.0,1280,720,train\ntN_7bWyIWDU,7495,7627,299-28-896-625,30.0,1280,720,train\ntN_7bWyIWDU,7691,7943,303-94-829-620,30.0,1280,720,train\ntN_7bWyIWDU,8000,8192,402-74-949-621,30.0,1280,720,train\ntN_7bWyIWDU,8458,8960,233-24-840-631,30.0,1280,720,train\ntN_7bWyIWDU,9007,9377,347-91-901-645,30.0,1280,720,train\ntN_7bWyIWDU,9377,9673,336-61-899-624,30.0,1280,720,train\ntN_7bWyIWDU,10225,10400,441-43-1044-646,30.0,1280,720,train\ntN_7bWyIWDU,10660,10990,498-57-1054-613,30.0,1280,720,train\nkXy-sWk4-jY,170,322,781-196-1407-822,25.0,1920,1080,train\nkXy-sWk4-jY,460,688,990-201-1605-816,25.0,1920,1080,train\nkXy-sWk4-jY,755,1002,801-218-1411-828,25.0,1920,1080,train\nkXy-sWk4-jY,1002,1210,795-228-1426-859,25.0,1920,1080,train\nkXy-sWk4-jY,1287,1454,603-236-1205-838,25.0,1920,1080,train\nkXy-sWk4-jY,1703,1876,762-243-1444-925,25.0,1920,1080,train\nkXy-sWk4-jY,2002,2373,761-320-1279-838,25.0,1920,1080,train\nkXy-sWk4-jY,2468,2693,809-315-1331-837,25.0,1920,1080,train\nkXy-sWk4-jY,2947,3147,909-315-1402-808,25.0,1920,1080,train\nkXy-sWk4-jY,3950,4085,779-296-1234-751,25.0,1920,1080,train\nkXy-sWk4-jY,5417,5586,627-297-1166-836,25.0,1920,1080,train\nUMKGRC2QMFo,0,205,413-209-1200-996,29.97,1920,1080,train\nUMKGRC2QMFo,205,800,408-213-1176-981,29.97,1920,1080,train\nUMKGRC2QMFo,800,1056,592-256-1331-995,29.97,1920,1080,train\nUMKGRC2QMFo,1181,1329,564-301-1262-999,29.97,1920,1080,train\nUMKGRC2QMFo,1379,1519,648-285-1345-982,29.97,1920,1080,train\nUMKGRC2QMFo,1699,2027,493-284-1169-960,29.97,1920,1080,train\nUMKGRC2QMFo,2134,2288,523-307-1159-943,29.97,1920,1080,train\nUMKGRC2QMFo,3352,3491,635-264-1309-938,29.97,1920,1080,train\nUMKGRC2QMFo,4066,4225,503-300-1143-940,29.97,1920,1080,train\nUMKGRC2QMFo,4225,4451,601-344-1197-940,29.97,1920,1080,train\nIw91zmQTMm0,1634,1851,412-53-1079-720,29.97,1280,720,test\nIw91zmQTMm0,2436,2702,360-126-899-665,29.97,1280,720,test\nIw91zmQTMm0,2820,3234,329-96-910-677,29.97,1280,720,test\nIw91zmQTMm0,3234,3387,420-104-991-675,29.97,1280,720,test\nIw91zmQTMm0,3445,3597,345-100-929-684,29.97,1280,720,test\nIw91zmQTMm0,3619,4049,263-86-840-663,29.97,1280,720,test\nIw91zmQTMm0,4049,4465,331-87-916-672,29.97,1280,720,test\n0ye2tnrow_I,1218,1634,315-47-983-715,29.97,1280,720,train\n0ye2tnrow_I,2188,2406,315-68-940-693,29.97,1280,720,train\n0ye2tnrow_I,2976,3112,362-112-909-659,29.97,1280,720,train\n0ye2tnrow_I,3202,3465,445-58-1068-681,29.97,1280,720,train\n0ye2tnrow_I,5782,5922,5-81-643-719,29.97,1280,720,train\n0ye2tnrow_I,6359,6688,1-72-630-701,29.97,1280,720,train\n0ye2tnrow_I,6775,6948,374-82-989-697,29.97,1280,720,train\n0ye2tnrow_I,7035,7216,326-110-910-694,29.97,1280,720,train\n0ye2tnrow_I,7232,7685,347-52-985-690,29.97,1280,720,train\nDfSnNtAcWAs,1390,1581,427-321-1140-1034,29.97,1920,1080,train\nDfSnNtAcWAs,1651,1915,528-306-1252-1030,29.97,1920,1080,train\nDfSnNtAcWAs,1982,2739,493-172-1329-1008,29.97,1920,1080,train\nDfSnNtAcWAs,2743,3767,507-185-1342-1020,29.97,1920,1080,train\nDfSnNtAcWAs,3838,4095,618-286-1314-982,29.97,1920,1080,train\nDfSnNtAcWAs,4232,4472,615-294-1300-979,29.97,1920,1080,train\nDfSnNtAcWAs,5019,5475,723-251-1460-988,29.97,1920,1080,train\nDfSnNtAcWAs,5682,5972,704-328-1380-1004,29.97,1920,1080,train\nDfSnNtAcWAs,6199,6603,462-127-1328-993,29.97,1920,1080,train\nDfSnNtAcWAs,6804,6970,700-329-1355-984,29.97,1920,1080,train\nDfSnNtAcWAs,6980,7343,675-290-1374-989,29.97,1920,1080,train\nDfSnNtAcWAs,7507,7635,495-325-1208-1038,29.97,1920,1080,train\nDfSnNtAcWAs,8344,8515,625-257-1370-1002,29.97,1920,1080,train\nDfSnNtAcWAs,9199,9532,284-111-1185-1012,29.97,1920,1080,train\nDfSnNtAcWAs,10074,10624,321-156-1193-1028,29.97,1920,1080,train\nDfSnNtAcWAs,10773,10917,423-315-1113-1005,29.97,1920,1080,train\nDfSnNtAcWAs,11692,11864,529-346-1235-1052,29.97,1920,1080,train\nDfSnNtAcWAs,12084,12234,458-358-1116-1016,29.97,1920,1080,train\nDfSnNtAcWAs,12272,12416,352-336-1034-1018,29.97,1920,1080,train\nDfSnNtAcWAs,12499,12692,493-265-1254-1026,29.97,1920,1080,train\nDfSnNtAcWAs,12728,12906,390-313-1097-1020,29.97,1920,1080,train\nDfSnNtAcWAs,13001,13131,365-324-1040-999,29.97,1920,1080,train\nDfSnNtAcWAs,13332,13508,385-216-1216-1047,29.97,1920,1080,train\nDfSnNtAcWAs,14200,14383,700-313-1423-1036,29.97,1920,1080,train\nDfSnNtAcWAs,14429,14558,464-158-1317-1011,29.97,1920,1080,train\nDfSnNtAcWAs,14658,14844,578-299-1303-1024,29.97,1920,1080,train\nDfSnNtAcWAs,15250,15769,623-272-1386-1035,29.97,1920,1080,train\nDfSnNtAcWAs,15892,16447,552-133-1455-1036,29.97,1920,1080,train\nDfSnNtAcWAs,16981,17343,470-94-1389-1013,29.97,1920,1080,train\nDfSnNtAcWAs,17370,17527,744-254-1493-1003,29.97,1920,1080,train\nDfSnNtAcWAs,17631,17811,603-273-1390-1060,29.97,1920,1080,train\nDfSnNtAcWAs,18096,18263,305-221-1150-1066,29.97,1920,1080,train\nDfSnNtAcWAs,18546,18683,366-262-1154-1050,29.97,1920,1080,train\nDfSnNtAcWAs,19403,19627,471-257-1242-1028,29.97,1920,1080,train\nDfSnNtAcWAs,19733,20059,626-231-1424-1029,29.97,1920,1080,train\nDfSnNtAcWAs,20333,20603,623-215-1427-1019,29.97,1920,1080,train\nDfSnNtAcWAs,20603,20939,594-175-1438-1019,29.97,1920,1080,train\nDfSnNtAcWAs,21010,21665,423-236-1196-1009,29.97,1920,1080,train\nEDGjhmIMCnw,561,693,181-38-823-680,29.97,1280,720,train\nEDGjhmIMCnw,1349,1647,401-73-1009-681,29.97,1280,720,train\nEDGjhmIMCnw,1956,2120,499-81-1064-646,29.97,1280,720,train\nEDGjhmIMCnw,2241,2535,416-106-986-676,29.97,1280,720,train\nEDGjhmIMCnw,2848,3066,319-106-874-661,29.97,1280,720,train\nEDGjhmIMCnw,3180,3330,387-102-948-663,29.97,1280,720,train\nEDGjhmIMCnw,3397,3614,389-66-1004-681,29.97,1280,720,train\nEDGjhmIMCnw,3831,3982,571-68-1182-679,29.97,1280,720,train\nEDGjhmIMCnw,4092,4223,311-49-938-676,29.97,1280,720,train\nEDGjhmIMCnw,5034,5228,338-88-933-683,29.97,1280,720,train\nEDGjhmIMCnw,5400,5542,426-134-983-691,29.97,1280,720,train\nEDGjhmIMCnw,6330,6497,342-132-897-687,29.97,1280,720,train\nOiblkvkAHWM,2280,2440,256-118-832-694,25.0,1280,720,test\nOiblkvkAHWM,2575,2763,385-63-1018-696,25.0,1280,720,test\nOiblkvkAHWM,3461,3616,315-81-935-701,25.0,1280,720,test\nOiblkvkAHWM,3931,4079,281-124-846-689,25.0,1280,720,test\nOiblkvkAHWM,4079,4212,350-33-1017-700,25.0,1280,720,test\nOiblkvkAHWM,4695,4957,242-80-860-698,25.0,1280,720,test\nOiblkvkAHWM,5484,5794,316-123-903-710,25.0,1280,720,test\nOiblkvkAHWM,5980,6116,256-112-852-708,25.0,1280,720,test\nOiblkvkAHWM,6251,6533,263-10-969-716,25.0,1280,720,test\nOiblkvkAHWM,7654,8070,274-16-965-707,25.0,1280,720,test\nOiblkvkAHWM,8617,8768,597-34-1273-710,25.0,1280,720,test\nOiblkvkAHWM,10080,10217,205-30-877-702,25.0,1280,720,test\nOiblkvkAHWM,10498,10640,305-60-955-710,25.0,1280,720,test\nOiblkvkAHWM,11052,11181,244-65-881-702,25.0,1280,720,test\nOiblkvkAHWM,14186,14331,247-38-917-708,25.0,1280,720,test\nOiblkvkAHWM,14331,14459,264-5-977-718,25.0,1280,720,test\nkfMckLkZz-4,249,430,182-42-604-464,29.97,640,480,train\nkfMckLkZz-4,668,816,22-50-398-426,29.97,640,480,train\nkfMckLkZz-4,2935,3128,86-27-528-469,29.97,640,480,train\nkfMckLkZz-4,4062,4284,204-93-562-451,29.97,640,480,train\nkfMckLkZz-4,4402,4580,230-80-609-459,29.97,640,480,train\nXM-YfeodJq4,909,1087,492-37-1458-1003,29.97,1920,1080,train\nXM-YfeodJq4,1309,1500,405-1-1474-1070,29.97,1920,1080,train\nXM-YfeodJq4,4932,5073,641-4-1569-932,29.97,1920,1080,train\n-kJzyrIM1cg,225,1249,436-135-1332-1031,25.0,1920,1080,train\n-kJzyrIM1cg,1249,2273,518-135-1423-1040,25.0,1920,1080,train\n-kJzyrIM1cg,2273,3297,557-144-1449-1036,25.0,1920,1080,train\n-kJzyrIM1cg,3297,3552,533-135-1411-1013,25.0,1920,1080,train\n-kJzyrIM1cg,3552,4063,534-130-1459-1055,25.0,1920,1080,train\n-kJzyrIM1cg,4063,5087,620-130-1519-1029,25.0,1920,1080,train\n-kJzyrIM1cg,5087,5345,574-155-1458-1039,25.0,1920,1080,train\n-kJzyrIM1cg,5594,5861,504-107-1404-1007,25.0,1920,1080,train\n-kJzyrIM1cg,6067,6227,581-178-1436-1033,25.0,1920,1080,train\n-kJzyrIM1cg,6227,6569,532-137-1399-1004,25.0,1920,1080,train\n-kJzyrIM1cg,6569,6814,684-172-1494-982,25.0,1920,1080,train\n-kJzyrIM1cg,6912,7218,562-171-1385-994,25.0,1920,1080,train\n-kJzyrIM1cg,7363,7547,555-159-1410-1014,25.0,1920,1080,train\n-kJzyrIM1cg,7740,7920,496-133-1366-1003,25.0,1920,1080,train\n-kJzyrIM1cg,7980,8110,492-134-1387-1029,25.0,1920,1080,train\n-kJzyrIM1cg,8345,8658,502-108-1414-1020,25.0,1920,1080,train\n-kJzyrIM1cg,8658,8968,351-65-1288-1002,25.0,1920,1080,train\n-kJzyrIM1cg,8968,9113,370-105-1302-1037,25.0,1920,1080,train\n-kJzyrIM1cg,9132,9313,501-117-1460-1076,25.0,1920,1080,train\n-kJzyrIM1cg,9317,9474,572-194-1414-1036,25.0,1920,1080,train\n-kJzyrIM1cg,9474,9628,527-153-1358-984,25.0,1920,1080,train\n-kJzyrIM1cg,9878,10478,498-171-1326-999,25.0,1920,1080,train\n-kJzyrIM1cg,10527,10752,475-85-1390-1000,25.0,1920,1080,train\n-kJzyrIM1cg,10789,10970,479-126-1362-1009,25.0,1920,1080,train\n-kJzyrIM1cg,10971,11124,601-216-1386-1001,25.0,1920,1080,train\n-kJzyrIM1cg,11282,11482,616-172-1358-914,25.0,1920,1080,train\n-kJzyrIM1cg,11557,11729,271-162-1089-980,25.0,1920,1080,train\n-kJzyrIM1cg,11729,11935,560-193-1332-965,25.0,1920,1080,train\n-kJzyrIM1cg,11935,12166,569-185-1386-1002,25.0,1920,1080,train\n-kJzyrIM1cg,12318,12662,401-131-1311-1041,25.0,1920,1080,train\n-kJzyrIM1cg,12809,13094,495-138-1371-1014,25.0,1920,1080,train\n-kJzyrIM1cg,13350,13779,535-111-1445-1021,25.0,1920,1080,train\n-kJzyrIM1cg,14036,15060,446-122-1403-1079,25.0,1920,1080,train\n-kJzyrIM1cg,15133,15308,548-140-1405-997,25.0,1920,1080,train\n-kJzyrIM1cg,15308,15450,537-185-1391-1039,25.0,1920,1080,train\n-kJzyrIM1cg,15599,16197,466-117-1373-1024,25.0,1920,1080,train\n-kJzyrIM1cg,16197,16435,510-172-1404-1066,25.0,1920,1080,train\n-kJzyrIM1cg,16471,16659,585-174-1486-1075,25.0,1920,1080,train\n-kJzyrIM1cg,16659,17683,412-175-1279-1042,25.0,1920,1080,train\n-kJzyrIM1cg,17703,17993,484-126-1352-994,25.0,1920,1080,train\n-kJzyrIM1cg,18055,19079,415-68-1399-1052,25.0,1920,1080,train\n-kJzyrIM1cg,19105,19403,502-178-1387-1063,25.0,1920,1080,train\n-kJzyrIM1cg,19417,19617,705-128-1656-1079,25.0,1920,1080,train\n-kJzyrIM1cg,19846,20335,625-169-1501-1045,25.0,1920,1080,train\n-kJzyrIM1cg,20963,21092,786-208-1461-883,25.0,1920,1080,train\n0EBa26jUU1g,5,142,137-91-460-414,30.0,640,480,train\n0EBa26jUU1g,142,535,129-105-454-430,30.0,640,480,train\n0EBa26jUU1g,1233,1386,97-127-406-436,30.0,640,480,train\nYVgja2MPa1U,0,406,371-119-1250-998,25.0,1920,1080,train\nYVgja2MPa1U,414,556,520-207-1308-995,25.0,1920,1080,train\nYVgja2MPa1U,748,948,412-122-1347-1057,25.0,1920,1080,train\nYVgja2MPa1U,2280,2470,532-189-1399-1056,25.0,1920,1080,train\nYVgja2MPa1U,2795,2940,613-249-1385-1021,25.0,1920,1080,train\nYVgja2MPa1U,3524,3686,626-265-1432-1071,25.0,1920,1080,train\nYVgja2MPa1U,5360,5588,446-45-1469-1068,25.0,1920,1080,train\nYVgja2MPa1U,8115,8253,431-203-1294-1066,25.0,1920,1080,train\nYVgja2MPa1U,8315,8576,330-118-1280-1068,25.0,1920,1080,train\nPvjYVsRK4Dg,2334,2475,91-32-528-469,29.97,640,480,train\nPvjYVsRK4Dg,8180,8558,80-32-516-468,29.97,640,480,train\nPvjYVsRK4Dg,8559,8768,61-41-488-468,29.97,640,480,train\nPvjYVsRK4Dg,8800,9045,62-41-487-466,29.97,640,480,train\nPvjYVsRK4Dg,9096,9440,59-43-489-473,29.97,640,480,train\nPvjYVsRK4Dg,9451,9738,63-44-480-461,29.97,640,480,train\nPvjYVsRK4Dg,9756,10191,90-31-530-471,29.97,640,480,train\nJoFxJXTe2IM,1167,1349,131-62-483-414,30.0,640,480,train\nJoFxJXTe2IM,1367,1588,143-71-487-415,30.0,640,480,train\nJoFxJXTe2IM,1615,1807,139-52-533-446,30.0,640,480,train\nJoFxJXTe2IM,1821,2164,131-60-496-425,30.0,640,480,train\nJoFxJXTe2IM,2313,2665,162-82-490-410,30.0,640,480,train\nJoFxJXTe2IM,2665,2836,161-78-501-418,30.0,640,480,train\nJoFxJXTe2IM,2902,3073,149-97-491-439,30.0,640,480,train\nJoFxJXTe2IM,3073,3511,156-81-501-426,30.0,640,480,train\nJoFxJXTe2IM,3551,3832,98-72-457-431,30.0,640,480,train\nJoFxJXTe2IM,3832,3973,147-54-511-418,30.0,640,480,train\nJoFxJXTe2IM,4120,4791,116-55-481-420,30.0,640,480,train\nJoFxJXTe2IM,5668,5839,114-111-419-416,30.0,640,480,train\nJoFxJXTe2IM,6019,6170,145-81-466-402,30.0,640,480,train\nJoFxJXTe2IM,7003,7161,153-74-495-416,30.0,640,480,train\nJoFxJXTe2IM,7161,7331,135-54-496-415,30.0,640,480,train\nJoFxJXTe2IM,7990,8253,128-75-462-409,30.0,640,480,train\nJoFxJXTe2IM,8426,8579,161-86-472-397,30.0,640,480,train\nJoFxJXTe2IM,8734,8871,146-90-472-416,30.0,640,480,train\nJoFxJXTe2IM,9077,9362,179-87-497-405,30.0,640,480,train\nJoFxJXTe2IM,9410,9698,172-66-522-416,30.0,640,480,train\nJoFxJXTe2IM,9830,9994,184-92-497-405,30.0,640,480,train\nJoFxJXTe2IM,10574,10759,214-63-566-415,30.0,640,480,train\nJoFxJXTe2IM,11127,11343,130-82-467-419,30.0,640,480,train\nJoFxJXTe2IM,11511,11644,239-99-531-391,30.0,640,480,train\nJoFxJXTe2IM,11893,12027,179-89-501-411,30.0,640,480,train\nJoFxJXTe2IM,12121,12273,203-140-488-425,30.0,640,480,train\nJoFxJXTe2IM,12412,12582,152-104-453-405,30.0,640,480,train\nSdT1S9ZL4L4,1920,2199,247-50-605-408,29.97,854,480,train\nSdT1S9ZL4L4,4818,4971,246-26-601-381,29.97,854,480,train\nSdT1S9ZL4L4,5544,5681,261-10-640-389,29.97,854,480,train\nSdT1S9ZL4L4,6613,6751,241-32-569-360,29.97,854,480,train\nJ4WBg84_30s,5,427,310-62-923-675,25.0,1280,720,train\nJ4WBg84_30s,427,638,415-86-1040-711,25.0,1280,720,train\nTWZGnwNe2jY,920,1078,539-67-1527-1055,29.97,1920,1080,train\nwKkuvbzNt5U,183,477,318-275-699-656,25.0,960,720,train\nwKkuvbzNt5U,514,665,305-299-682-676,25.0,960,720,train\nwKkuvbzNt5U,1114,1245,267-290-676-699,25.0,960,720,train\nwKkuvbzNt5U,4462,4848,243-293-662-712,25.0,960,720,train\nwKkuvbzNt5U,4919,5290,203-269-646-712,25.0,960,720,train\nVidZQ6yA7I4,201,336,820-97-1315-592,29.97,1920,1080,train\nVidZQ6yA7I4,660,802,704-125-1186-607,29.97,1920,1080,train\nVidZQ6yA7I4,835,1014,810-138-1261-589,29.97,1920,1080,train\nVidZQ6yA7I4,1647,1775,990-127-1450-587,29.97,1920,1080,train\nVidZQ6yA7I4,1845,1985,1013-109-1523-619,29.97,1920,1080,train\nVidZQ6yA7I4,2167,2336,670-125-1183-638,29.97,1920,1080,train\nVidZQ6yA7I4,2807,2991,505-137-989-621,29.97,1920,1080,train\nVidZQ6yA7I4,4054,4846,955-0-1776-820,29.97,1920,1080,train\nVidZQ6yA7I4,5086,5478,525-0-1180-655,29.97,1920,1080,train\nVidZQ6yA7I4,5537,5666,778-109-1323-654,29.97,1920,1080,train\nVidZQ6yA7I4,5848,5978,832-98-1366-632,29.97,1920,1080,train\nVidZQ6yA7I4,6617,6750,342-104-867-629,29.97,1920,1080,train\nVidZQ6yA7I4,6750,6888,464-112-988-636,29.97,1920,1080,train\nB2zZOiUBzZc,1201,2225,546-148-1387-989,25.0,1920,1080,train\nB2zZOiUBzZc,2225,2517,661-282-1325-946,25.0,1920,1080,train\nB2zZOiUBzZc,2779,3006,635-217-1372-954,25.0,1920,1080,train\nB2zZOiUBzZc,3066,3355,731-189-1542-1000,25.0,1920,1080,train\nB2zZOiUBzZc,3420,3651,490-181-1278-969,25.0,1920,1080,train\nB2zZOiUBzZc,4284,4439,341-281-996-936,25.0,1920,1080,train\nB2zZOiUBzZc,4512,4653,407-247-1077-917,25.0,1920,1080,train\nB2zZOiUBzZc,4653,4933,432-213-1138-919,25.0,1920,1080,train\nB2zZOiUBzZc,5297,5666,629-188-1432-991,25.0,1920,1080,train\nB2zZOiUBzZc,5963,6091,675-268-1328-921,25.0,1920,1080,train\nB2zZOiUBzZc,6285,6465,461-270-1120-929,25.0,1920,1080,train\nB2zZOiUBzZc,6509,6720,295-290-904-899,25.0,1920,1080,train\nB2zZOiUBzZc,6824,7014,604-262-1235-893,25.0,1920,1080,train\nB2zZOiUBzZc,7097,7262,631-232-1297-898,25.0,1920,1080,train\nB2zZOiUBzZc,9388,9725,676-141-1551-1016,25.0,1920,1080,train\nB2zZOiUBzZc,9725,9859,565-203-1333-971,25.0,1920,1080,train\nB2zZOiUBzZc,10570,10964,547-265-1237-955,25.0,1920,1080,train\nB2zZOiUBzZc,11387,11745,695-250-1408-963,25.0,1920,1080,train\nB2zZOiUBzZc,11826,11963,539-238-1278-977,25.0,1920,1080,train\nB2zZOiUBzZc,11963,12094,707-308-1375-976,25.0,1920,1080,train\nB2zZOiUBzZc,12626,13564,691-52-1641-1002,25.0,1920,1080,train\nB2zZOiUBzZc,13781,13940,450-177-891-618,25.0,1920,1080,train\n1cHighu8eCo,18,253,121-81-492-452,29.97,640,480,train\n1cHighu8eCo,407,973,133-68-519-454,29.97,640,480,train\n1cHighu8eCo,1124,1338,151-92-491-432,29.97,640,480,train\n1cHighu8eCo,2037,2201,235-103-555-423,29.97,640,480,train\n1cHighu8eCo,2472,2757,205-77-548-420,29.97,640,480,train\n1cHighu8eCo,3111,3283,146-77-476-407,29.97,640,480,train\n1cHighu8eCo,3611,3808,100-92-428-420,29.97,640,480,train\n1cHighu8eCo,4953,5197,111-13-570-472,29.97,640,480,train\n1cHighu8eCo,5619,5802,153-77-532-456,29.97,640,480,train\n1cHighu8eCo,7079,7346,89-48-442-401,29.97,640,480,train\n1cHighu8eCo,7394,7587,146-74-500-428,29.97,640,480,train\n1cHighu8eCo,8082,8345,137-88-481-432,29.97,640,480,train\n1cHighu8eCo,8928,9137,221-88-562-429,29.97,640,480,train\n1cHighu8eCo,10401,10703,238-104-554-420,29.97,640,480,train\n1cHighu8eCo,11779,11995,129-73-503-447,29.97,640,480,train\noTmbnz-bRE0,109,942,344-151-787-594,29.97,1280,720,train\noTmbnz-bRE0,1037,1207,290-164-719-593,29.97,1280,720,train\noTmbnz-bRE0,1357,1526,496-210-875-589,29.97,1280,720,train\noTmbnz-bRE0,1760,1922,371-203-746-578,29.97,1280,720,train\noTmbnz-bRE0,1942,2082,448-169-845-566,29.97,1280,720,train\noTmbnz-bRE0,2397,2642,248-168-666-586,29.97,1280,720,train\noTmbnz-bRE0,2758,3011,370-212-741-583,29.97,1280,720,train\noTmbnz-bRE0,3450,3631,429-200-826-597,29.97,1280,720,train\noTmbnz-bRE0,3862,4088,285-173-726-614,29.97,1280,720,train\noTmbnz-bRE0,4243,4384,441-191-857-607,29.97,1280,720,train\noTmbnz-bRE0,4897,5077,278-211-711-644,29.97,1280,720,train\noTmbnz-bRE0,5341,5498,160-181-623-644,29.97,1280,720,train\noTmbnz-bRE0,5666,5820,320-213-754-647,29.97,1280,720,train\noTmbnz-bRE0,6238,6408,302-151-749-598,29.97,1280,720,train\noTmbnz-bRE0,6879,7047,485-175-887-577,29.97,1280,720,train\noTmbnz-bRE0,7061,7229,523-131-983-591,29.97,1280,720,train\noTmbnz-bRE0,8022,8321,292-146-765-619,29.97,1280,720,train\noTmbnz-bRE0,8462,8656,385-184-811-610,29.97,1280,720,train\noTmbnz-bRE0,8656,8877,283-163-737-617,29.97,1280,720,train\noTmbnz-bRE0,9161,9432,385-214-784-613,29.97,1280,720,train\noTmbnz-bRE0,9567,9732,204-189-653-638,29.97,1280,720,train\noTmbnz-bRE0,9806,9956,316-230-747-661,29.97,1280,720,train\noTmbnz-bRE0,9956,10106,370-210-792-632,29.97,1280,720,train\noTmbnz-bRE0,10797,10962,244-145-720-621,29.97,1280,720,train\noTmbnz-bRE0,11147,11276,440-166-892-618,29.97,1280,720,train\noTmbnz-bRE0,11427,11657,290-209-702-621,29.97,1280,720,train\noTmbnz-bRE0,11960,12117,208-163-703-658,29.97,1280,720,train\noTmbnz-bRE0,12637,12858,391-125-905-639,29.97,1280,720,train\noTmbnz-bRE0,12972,13128,149-153-658-662,29.97,1280,720,train\noTmbnz-bRE0,13160,13326,416-165-869-618,29.97,1280,720,train\noTmbnz-bRE0,13328,13691,356-162-808-614,29.97,1280,720,train\noTmbnz-bRE0,13691,14002,369-161-844-636,29.97,1280,720,train\noTmbnz-bRE0,14019,14331,287-83-835-631,29.97,1280,720,train\nwPTaGTzwRDI,82,884,128-72-450-394,25.0,640,480,train\nwPTaGTzwRDI,884,1052,100-114-389-403,25.0,640,480,train\nwPTaGTzwRDI,1052,1399,115-99-418-402,25.0,640,480,train\nwPTaGTzwRDI,1399,1583,92-111-383-402,25.0,640,480,train\nwPTaGTzwRDI,2078,2418,91-110-383-402,25.0,640,480,train\nwPTaGTzwRDI,2504,2670,159-83-475-399,25.0,640,480,train\nwPTaGTzwRDI,2670,3335,140-67-475-402,25.0,640,480,train\nwPTaGTzwRDI,3335,3904,212-105-509-402,25.0,640,480,train\nwPTaGTzwRDI,4476,4872,208-99-515-406,25.0,640,480,train\nwPTaGTzwRDI,4976,5251,110-71-434-395,25.0,640,480,train\nhYZDOpHYgLM,5477,5667,235-233-981-979,29.97,1920,1080,train\nhYZDOpHYgLM,6080,6230,644-274-1337-967,29.97,1920,1080,train\nhYZDOpHYgLM,7337,7502,374-237-1132-995,29.97,1920,1080,train\nhYZDOpHYgLM,7827,8062,297-290-960-953,29.97,1920,1080,train\nLstLDRUBAp4,0,135,423-35-1380-992,25.0,1920,1080,train\nLstLDRUBAp4,270,593,460-30-1471-1041,25.0,1920,1080,train\nLstLDRUBAp4,675,810,494-8-1509-1023,25.0,1920,1080,train\nLstLDRUBAp4,2295,2430,444-16-1463-1035,25.0,1920,1080,train\nLstLDRUBAp4,2430,2565,491-146-1380-1035,25.0,1920,1080,train\nLstLDRUBAp4,2596,2726,613-256-1287-930,25.0,1920,1080,train\n_cIRyxE3Kf8,1983,2675,111-50-515-454,25.0,640,480,train\n_cIRyxE3Kf8,2970,3293,115-5-562-452,25.0,640,480,train\n_cIRyxE3Kf8,4056,4216,46-7-504-465,25.0,640,480,train\n_cIRyxE3Kf8,4946,5763,144-37-550-443,25.0,640,480,train\n_cIRyxE3Kf8,5763,5999,89-52-498-461,25.0,640,480,train\nknidf7i-J3Y,95,323,317-139-824-646,29.97,1280,720,train\nknidf7i-J3Y,534,1558,215-1-879-665,29.97,1280,720,train\nknidf7i-J3Y,2217,2434,300-157-779-636,29.97,1280,720,train\nknidf7i-J3Y,2531,2714,277-150-765-638,29.97,1280,720,train\nknidf7i-J3Y,2743,2975,388-225-805-642,29.97,1280,720,train\nknidf7i-J3Y,3181,3506,402-182-858-638,29.97,1280,720,train\nknidf7i-J3Y,3600,3750,273-162-759-648,29.97,1280,720,train\nknidf7i-J3Y,3766,3995,284-150-760-626,29.97,1280,720,train\nknidf7i-J3Y,3995,4485,283-166-768-651,29.97,1280,720,train\nknidf7i-J3Y,4635,4877,321-147-814-640,29.97,1280,720,train\nknidf7i-J3Y,4951,5132,312-215-753-656,29.97,1280,720,train\nknidf7i-J3Y,5132,5370,324-193-764-633,29.97,1280,720,train\nknidf7i-J3Y,5650,6000,268-25-883-640,29.97,1280,720,train\nsvFggnyI4d8,293,481,1027-268-1829-1070,29.97,1920,1080,train\nsvFggnyI4d8,843,1018,1104-237-1916-1049,29.97,1920,1080,train\nsvFggnyI4d8,1379,1541,867-132-1652-917,29.97,1920,1080,train\nsvFggnyI4d8,3752,3919,604-205-1424-1025,29.97,1920,1080,train\nsvFggnyI4d8,5259,5425,733-184-1588-1039,29.97,1920,1080,train\nsvFggnyI4d8,6260,6412,812-282-1575-1045,29.97,1920,1080,train\nsvFggnyI4d8,7079,7279,459-120-1336-997,29.97,1920,1080,train\n0mpd65lmphU,0,163,330-220-607-497,25.0,1280,720,train\n0mpd65lmphU,0,299,918-216-1214-512,25.0,1280,720,train\n0mpd65lmphU,353,535,905-230-1166-491,25.0,1280,720,train\n0mpd65lmphU,1163,1698,913-219-1184-490,25.0,1280,720,train\n0mpd65lmphU,1799,2003,353-204-637-488,25.0,1280,720,train\n0mpd65lmphU,1932,2262,919-226-1184-491,25.0,1280,720,train\n0mpd65lmphU,2459,2661,244-208-524-488,25.0,1280,720,train\n0mpd65lmphU,2315,2672,829-224-1108-503,25.0,1280,720,train\n0mpd65lmphU,2807,3111,707-210-1001-504,25.0,1280,720,train\n0mpd65lmphU,3180,3433,143-223-416-496,25.0,1280,720,train\n0mpd65lmphU,3433,3608,163-208-448-493,25.0,1280,720,train\n0mpd65lmphU,3176,3745,666-226-964-524,25.0,1280,720,train\n0mpd65lmphU,3745,4129,689-212-994-517,25.0,1280,720,train\n0mpd65lmphU,3825,4216,115-199-420-504,25.0,1280,720,train\n0mpd65lmphU,4140,4436,710-228-993-511,25.0,1280,720,train\nYoABR3mDsIg,1160,1315,355-156-865-666,29.97,1280,720,train\nYoABR3mDsIg,1413,1903,379-183-863-667,29.97,1280,720,train\nYoABR3mDsIg,1979,2139,439-199-910-670,29.97,1280,720,train\nYoABR3mDsIg,2220,2433,423-214-872-663,29.97,1280,720,train\nYoABR3mDsIg,2810,2999,491-183-949-641,29.97,1280,720,train\nYoABR3mDsIg,3080,3250,475-189-929-643,29.97,1280,720,train\nYoABR3mDsIg,9740,9873,357-169-853-665,29.97,1280,720,train\nYoABR3mDsIg,9948,10085,354-195-827-668,29.97,1280,720,train\nYoABR3mDsIg,10085,10331,250-192-723-665,29.97,1280,720,train\nYoABR3mDsIg,10578,10714,257-212-744-699,29.97,1280,720,train\nYoABR3mDsIg,10714,10893,218-189-727-698,29.97,1280,720,train\nYoABR3mDsIg,11261,11456,176-182-705-711,29.97,1280,720,train\nYoABR3mDsIg,11551,11740,208-166-744-702,29.97,1280,720,train\n8eflkNicY-E,945,1125,431-110-961-640,25.0,1280,720,train\n8eflkNicY-E,2011,2153,415-169-915-669,25.0,1280,720,train\n8eflkNicY-E,2398,2580,367-131-868-632,25.0,1280,720,train\n8eflkNicY-E,2713,2843,319-142-858-681,25.0,1280,720,train\n8eflkNicY-E,3587,3734,264-122-815-673,25.0,1280,720,train\nEswKOjV3isk,427,1451,117-36-542-461,29.97,640,480,train\nEswKOjV3isk,1451,2475,127-59-522-454,29.97,640,480,train\nEswKOjV3isk,2475,3499,131-64-521-454,29.97,640,480,train\nEswKOjV3isk,3499,3900,131-66-517-452,29.97,640,480,train\nEswKOjV3isk,3900,4924,132-67-517-452,29.97,640,480,train\nEswKOjV3isk,4924,5948,130-63-521-454,29.97,640,480,train\nEswKOjV3isk,5948,6972,130-64-520-454,29.97,640,480,train\nEswKOjV3isk,6972,7996,128-61-520-453,29.97,640,480,train\nEswKOjV3isk,7996,8832,125-58-522-455,29.97,640,480,train\nEswKOjV3isk,8832,8960,122-37-544-459,29.97,640,480,train\nuggNT3QkTYQ,0,180,310-299-605-594,15.0,960,720,train\nuggNT3QkTYQ,1235,1372,292-243-683-634,15.0,960,720,train\nuggNT3QkTYQ,1386,1536,301-211-743-653,15.0,960,720,train\nuggNT3QkTYQ,2779,2925,314-112-883-681,15.0,960,720,train\nzBJADM80dPQ,420,992,447-127-935-615,29.97,1280,720,train\nzBJADM80dPQ,1906,2109,578-60-1180-662,29.97,1280,720,train\nzBJADM80dPQ,3184,3336,352-148-875-671,29.97,1280,720,train\nzBJADM80dPQ,3393,3711,126-29-732-635,29.97,1280,720,train\nAN62b1UpmcE,342,737,372-186-758-572,25.0,1280,720,train\nAN62b1UpmcE,737,883,383-245-725-587,25.0,1280,720,train\nAN62b1UpmcE,883,1209,367-227-731-591,25.0,1280,720,train\nAN62b1UpmcE,1214,1406,352-210-744-602,25.0,1280,720,train\nAN62b1UpmcE,1406,1736,321-211-736-626,25.0,1280,720,train\nAN62b1UpmcE,3445,3584,22-10-667-655,25.0,1280,720,train\nUU9-XEvF5X4,214,514,350-166-881-697,30.0,1280,720,train\nUU9-XEvF5X4,514,1059,371-137-938-704,30.0,1280,720,train\nUU9-XEvF5X4,1060,1252,378-159-922-703,30.0,1280,720,train\nUU9-XEvF5X4,1252,1498,365-128-938-701,30.0,1280,720,train\nUU9-XEvF5X4,1499,2353,376-158-922-704,30.0,1280,720,train\nUU9-XEvF5X4,2370,3240,275-52-941-718,30.0,1280,720,train\nUU9-XEvF5X4,3811,4835,307-3-1010-706,30.0,1280,720,train\nUU9-XEvF5X4,4924,5948,301-31-984-714,30.0,1280,720,train\nUU9-XEvF5X4,6144,7168,254-90-881-717,30.0,1280,720,train\nUU9-XEvF5X4,7168,8018,340-183-858-701,30.0,1280,720,train\nUU9-XEvF5X4,14225,15249,343-156-906-719,30.0,1280,720,train\nUU9-XEvF5X4,15249,15422,335-154-891-710,30.0,1280,720,train\nUU9-XEvF5X4,16589,16717,314-108-918-712,30.0,1280,720,train\nUU9-XEvF5X4,19207,19770,367-161-903-697,30.0,1280,720,train\nUU9-XEvF5X4,21551,22575,308-21-975-688,30.0,1280,720,train\nUU9-XEvF5X4,22580,23082,382-121-934-673,30.0,1280,720,train\nUU9-XEvF5X4,23082,23377,338-158-881-701,30.0,1280,720,train\nUU9-XEvF5X4,23377,24401,392-131-954-693,30.0,1280,720,train\nUU9-XEvF5X4,24401,24680,397-170-884-657,30.0,1280,720,train\nUU9-XEvF5X4,24765,25094,426-133-960-667,30.0,1280,720,train\nUU9-XEvF5X4,25094,26118,407-137-964-694,30.0,1280,720,train\nUU9-XEvF5X4,26118,27142,389-139-941-691,30.0,1280,720,train\nUU9-XEvF5X4,27290,27965,340-80-952-692,30.0,1280,720,train\nUU9-XEvF5X4,27965,28305,250-36-920-706,30.0,1280,720,train\nUU9-XEvF5X4,29032,29256,281-106-871-696,30.0,1280,720,train\nUU9-XEvF5X4,29265,29501,319-114-891-686,30.0,1280,720,train\nUU9-XEvF5X4,29501,30026,334-90-932-688,30.0,1280,720,train\nUU9-XEvF5X4,30466,30699,282-8-990-716,30.0,1280,720,train\nUU9-XEvF5X4,30755,30925,279-3-993-717,30.0,1280,720,train\nUU9-XEvF5X4,31271,31490,267-39-920-692,30.0,1280,720,train\nUU9-XEvF5X4,31580,32098,289-63-923-697,30.0,1280,720,train\nUU9-XEvF5X4,32098,33122,259-22-947-710,30.0,1280,720,train\nUU9-XEvF5X4,33296,33465,279-128-852-701,30.0,1280,720,train\nUU9-XEvF5X4,33501,33697,275-121-855-701,30.0,1280,720,train\nUU9-XEvF5X4,34758,34954,296-43-957-704,30.0,1280,720,train\nUU9-XEvF5X4,35111,35246,292-58-945-711,30.0,1280,720,train\nUU9-XEvF5X4,35545,35783,271-34-953-716,30.0,1280,720,train\nUU9-XEvF5X4,35899,36032,376-151-918-693,30.0,1280,720,train\nUU9-XEvF5X4,36273,36476,406-152-964-710,30.0,1280,720,train\nUU9-XEvF5X4,38680,39383,369-146-903-680,30.0,1280,720,train\nUU9-XEvF5X4,39383,40407,364-111-931-678,30.0,1280,720,train\nUU9-XEvF5X4,40407,40939,358-122-918-682,30.0,1280,720,train\nUU9-XEvF5X4,49635,49824,263-3-930-670,30.0,1280,720,train\nUU9-XEvF5X4,52401,52598,484-104-1042-662,30.0,1280,720,train\nUU9-XEvF5X4,52983,53208,336-112-899-675,30.0,1280,720,train\nUU9-XEvF5X4,53475,53890,364-100-983-719,30.0,1280,720,train\nUU9-XEvF5X4,54205,54334,69-128-649-708,30.0,1280,720,train\nUU9-XEvF5X4,54522,54706,311-75-949-713,30.0,1280,720,train\nUU9-XEvF5X4,55529,55665,379-27-1060-708,30.0,1280,720,train\nUU9-XEvF5X4,57251,57789,398-45-1069-716,30.0,1280,720,train\nUU9-XEvF5X4,58567,58816,105-59-753-707,30.0,1280,720,train\nUU9-XEvF5X4,60005,60201,25-18-714-707,30.0,1280,720,train\nUU9-XEvF5X4,61363,62161,511-16-1175-680,30.0,1280,720,train\nUU9-XEvF5X4,62431,62894,679-93-1242-656,30.0,1280,720,train\nUU9-XEvF5X4,63139,63682,308-83-943-718,30.0,1280,720,train\nUU9-XEvF5X4,63714,64162,351-11-1042-702,30.0,1280,720,train\nUU9-XEvF5X4,64185,64513,418-10-1126-718,30.0,1280,720,train\nUU9-XEvF5X4,64751,65404,248-101-819-672,30.0,1280,720,train\nUU9-XEvF5X4,67077,67236,621-81-1235-695,30.0,1280,720,train\nUU9-XEvF5X4,67265,67395,370-95-993-718,30.0,1280,720,train\nUU9-XEvF5X4,69598,69942,471-126-962-617,30.0,1280,720,train\nUU9-XEvF5X4,70047,70298,430-129-976-675,30.0,1280,720,train\nUU9-XEvF5X4,70450,70602,472-120-1050-698,30.0,1280,720,train\nUU9-XEvF5X4,70666,71075,371-107-964-700,30.0,1280,720,train\nUU9-XEvF5X4,71344,71656,303-62-953-712,30.0,1280,720,train\nUU9-XEvF5X4,72135,72283,478-87-1105-714,30.0,1280,720,train\nUU9-XEvF5X4,72413,72553,597-68-1228-699,30.0,1280,720,train\nUU9-XEvF5X4,72848,73155,560-4-1267-711,30.0,1280,720,train\nUU9-XEvF5X4,74833,74996,421-106-1028-713,30.0,1280,720,train\nUU9-XEvF5X4,76104,76503,316-77-957-718,30.0,1280,720,train\nUU9-XEvF5X4,76689,77143,460-88-1088-716,30.0,1280,720,train\nUU9-XEvF5X4,77370,77627,355-58-1008-711,30.0,1280,720,train\nUU9-XEvF5X4,77721,78156,201-0-919-718,30.0,1280,720,train\nY6DtgVbcD90,180,512,466-170-1308-1012,30.0,1920,1080,train\nY6DtgVbcD90,2644,2880,449-168-1331-1050,30.0,1920,1080,train\nY6DtgVbcD90,8003,8160,408-71-1324-987,30.0,1920,1080,train\nniFUaaCwYag,706,1500,391-171-1288-1068,29.97,1920,1080,train\nniFUaaCwYag,1500,1660,511-259-1281-1029,29.97,1920,1080,train\nniFUaaCwYag,1882,2162,461-220-1297-1056,29.97,1920,1080,train\nniFUaaCwYag,2162,2451,458-177-1338-1057,29.97,1920,1080,train\nniFUaaCwYag,2549,2880,649-254-1459-1064,29.97,1920,1080,train\nniFUaaCwYag,3010,3198,662-254-1487-1079,29.97,1920,1080,train\nniFUaaCwYag,3382,3572,638-271-1410-1043,29.97,1920,1080,train\nniFUaaCwYag,3986,4160,783-306-1510-1033,29.97,1920,1080,train\nniFUaaCwYag,4545,4835,704-360-1391-1047,29.97,1920,1080,train\nniFUaaCwYag,6741,7039,408-246-1224-1062,29.97,1920,1080,train\nniFUaaCwYag,7313,7459,433-232-1236-1035,29.97,1920,1080,train\nniFUaaCwYag,7459,7724,502-192-1349-1039,29.97,1920,1080,train\nniFUaaCwYag,7724,7912,536-216-1398-1078,29.97,1920,1080,train\nniFUaaCwYag,7948,8273,448-224-1277-1053,29.97,1920,1080,train\nniFUaaCwYag,9440,9618,628-241-1449-1062,29.97,1920,1080,train\nniFUaaCwYag,10391,10575,827-408-1450-1031,29.97,1920,1080,train\nniFUaaCwYag,12164,12342,619-298-1391-1070,29.97,1920,1080,train\nniFUaaCwYag,13057,13262,502-201-1349-1048,29.97,1920,1080,train\nniFUaaCwYag,13382,13631,301-240-1141-1080,29.97,1920,1080,train\nniFUaaCwYag,13753,14084,320-84-1280-1044,29.97,1920,1080,train\nniFUaaCwYag,14451,14704,227-59-1248-1080,29.97,1920,1080,train\nniFUaaCwYag,14993,15127,475-240-1306-1071,29.97,1920,1080,train\nniFUaaCwYag,15365,15581,673-219-1534-1080,29.97,1920,1080,train\nniFUaaCwYag,15765,15984,596-194-1428-1026,29.97,1920,1080,train\nniFUaaCwYag,16246,16429,628-261-1372-1005,29.97,1920,1080,train\nniFUaaCwYag,16454,16678,606-316-1321-1031,29.97,1920,1080,train\nniFUaaCwYag,16698,16880,742-278-1487-1023,29.97,1920,1080,train\nniFUaaCwYag,17027,17171,827-357-1472-1002,29.97,1920,1080,train\nniFUaaCwYag,17171,17387,857-326-1500-969,29.97,1920,1080,train\nniFUaaCwYag,17825,17975,763-314-1450-1001,29.97,1920,1080,train\nniFUaaCwYag,18414,18548,717-222-1569-1074,29.97,1920,1080,train\nniFUaaCwYag,19161,19305,380-128-1330-1078,29.97,1920,1080,train\nniFUaaCwYag,19705,19918,800-201-1647-1048,29.97,1920,1080,train\nniFUaaCwYag,19930,20284,682-203-1529-1050,29.97,1920,1080,train\nniFUaaCwYag,20505,20673,667-283-1452-1068,29.97,1920,1080,train\nniFUaaCwYag,20673,20893,649-244-1472-1067,29.97,1920,1080,train\nniFUaaCwYag,21645,21805,408-231-1248-1071,29.97,1920,1080,train\nab28GAufK8o,261,596,175-63-551-439,29.97,640,480,test\nab28GAufK8o,832,976,122-88-445-411,29.97,640,480,test\nab28GAufK8o,997,1200,139-78-473-412,29.97,640,480,test\nab28GAufK8o,1353,1493,125-100-470-445,29.97,640,480,test\nab28GAufK8o,1591,1826,53-87-398-432,29.97,640,480,test\nab28GAufK8o,2018,2163,56-48-430-422,29.97,640,480,test\nab28GAufK8o,2361,2499,178-110-533-465,29.97,640,480,test\nXYuT0U0K5CA,0,339,417-115-957-655,50.0,1280,720,train\nXYuT0U0K5CA,339,1363,363-117-919-673,50.0,1280,720,train\nXYuT0U0K5CA,1581,2605,297-117-852-672,50.0,1280,720,train\nXYuT0U0K5CA,2605,2993,304-127-851-674,50.0,1280,720,train\nXYuT0U0K5CA,3014,3389,405-154-936-685,50.0,1280,720,train\nXYuT0U0K5CA,3449,3582,323-180-830-687,50.0,1280,720,train\nXYuT0U0K5CA,3582,3924,350-155-881-686,50.0,1280,720,train\nXYuT0U0K5CA,3930,4432,267-154-801-688,50.0,1280,720,train\nXYuT0U0K5CA,4449,5023,267-154-807-694,50.0,1280,720,train\nXYuT0U0K5CA,5147,5416,361-7-1007-653,50.0,1280,720,train\nXYuT0U0K5CA,5416,5612,396-163-912-679,50.0,1280,720,train\nXYuT0U0K5CA,5635,5892,467-148-1009-690,50.0,1280,720,train\nXYuT0U0K5CA,5893,6139,451-137-986-672,50.0,1280,720,train\nXYuT0U0K5CA,6150,6417,478-148-1005-675,50.0,1280,720,train\nXYuT0U0K5CA,6417,6895,439-123-982-666,50.0,1280,720,train\nXYuT0U0K5CA,6902,7148,475-126-1020-671,50.0,1280,720,train\nXYuT0U0K5CA,7151,7341,461-132-999-670,50.0,1280,720,train\nXYuT0U0K5CA,7398,7956,409-17-1089-697,50.0,1280,720,train\nXYuT0U0K5CA,8980,10004,255-6-936-687,50.0,1280,720,train\nXYuT0U0K5CA,10048,10343,242-28-909-695,50.0,1280,720,train\nXYuT0U0K5CA,11554,11740,268-121-843-696,50.0,1280,720,train\nXYuT0U0K5CA,11789,12813,196-32-860-696,50.0,1280,720,train\nXYuT0U0K5CA,12813,13039,173-45-829-701,50.0,1280,720,train\nXYuT0U0K5CA,13066,13227,225-1-930-706,50.0,1280,720,train\nXYuT0U0K5CA,14251,14994,127-58-787-718,50.0,1280,720,train\nXYuT0U0K5CA,15130,15728,260-50-908-698,50.0,1280,720,train\nXYuT0U0K5CA,15736,15989,296-82-926-712,50.0,1280,720,train\nXYuT0U0K5CA,15989,16162,273-48-933-708,50.0,1280,720,train\nXYuT0U0K5CA,16537,16817,304-101-890-687,50.0,1280,720,train\nXYuT0U0K5CA,17383,17539,223-18-907-702,50.0,1280,720,train\nXYuT0U0K5CA,17662,18152,399-48-1019-668,50.0,1280,720,train\nXYuT0U0K5CA,18152,18350,274-74-875-675,50.0,1280,720,train\nXYuT0U0K5CA,18391,18595,250-0-932-682,50.0,1280,720,train\nXYuT0U0K5CA,19497,19666,91-17-768-694,50.0,1280,720,train\nXYuT0U0K5CA,19780,20027,265-54-893-682,50.0,1280,720,train\nXYuT0U0K5CA,20560,20777,81-79-680-678,50.0,1280,720,train\nXYuT0U0K5CA,21021,21174,69-5-748-684,50.0,1280,720,train\nXYuT0U0K5CA,21314,21526,225-57-848-680,50.0,1280,720,train\nXYuT0U0K5CA,21564,21921,82-19-748-685,50.0,1280,720,train\nXYuT0U0K5CA,22051,22192,115-49-746-680,50.0,1280,720,train\nXYuT0U0K5CA,22311,22466,123-67-736-680,50.0,1280,720,train\nXYuT0U0K5CA,22476,23082,185-1-881-697,50.0,1280,720,train\nk1RAdWov7kU,52,465,604-208-1340-944,25.0,1920,1080,train\nk1RAdWov7kU,465,790,615-225-1368-978,25.0,1920,1080,train\nk1RAdWov7kU,790,1168,575-190-1339-954,25.0,1920,1080,train\nk1RAdWov7kU,1168,1508,470-150-1281-961,25.0,1920,1080,train\nk1RAdWov7kU,1707,2152,491-126-1351-986,25.0,1920,1080,train\nk1RAdWov7kU,2152,2288,502-188-1337-1023,25.0,1920,1080,train\nk1RAdWov7kU,2411,3435,487-53-1422-988,25.0,1920,1080,train\nk1RAdWov7kU,3607,3863,528-93-1411-976,25.0,1920,1080,train\nk1RAdWov7kU,4021,4906,523-103-1425-1005,25.0,1920,1080,train\nk1RAdWov7kU,5036,5640,446-101-1377-1032,25.0,1920,1080,train\nk1RAdWov7kU,5757,5927,361-91-1332-1062,25.0,1920,1080,train\nk1RAdWov7kU,5927,6123,471-40-1472-1041,25.0,1920,1080,train\nk1RAdWov7kU,6635,6871,403-77-1341-1015,25.0,1920,1080,train\nk1RAdWov7kU,6880,7647,390-67-1358-1035,25.0,1920,1080,train\nk1RAdWov7kU,8195,8422,464-120-1357-1013,25.0,1920,1080,train\nk1RAdWov7kU,8575,8823,487-45-1442-1000,25.0,1920,1080,train\nk1RAdWov7kU,8946,9302,353-9-1364-1020,25.0,1920,1080,train\nk1RAdWov7kU,9832,10097,493-34-1418-959,25.0,1920,1080,train\nk1RAdWov7kU,10226,10360,503-70-1378-945,25.0,1920,1080,train\nk1RAdWov7kU,10468,11282,597-85-1522-1010,25.0,1920,1080,train\nNXPySOFaBf0,1491,1630,128-45-550-467,29.97,854,480,train\n29FLWPEOCMw,5779,6424,195-15-643-463,29.97,854,480,train\n29FLWPEOCMw,7448,8472,165-3-625-463,29.97,854,480,train\n29FLWPEOCMw,8472,8725,168-34-587-453,29.97,854,480,train\n29FLWPEOCMw,8725,9065,174-12-625-463,29.97,854,480,train\n29FLWPEOCMw,9369,9892,210-0-665-455,29.97,854,480,train\nFzJJ_bWLzcA,315,450,540-216-1386-1062,29.97,1920,1080,train\nFzJJ_bWLzcA,1950,2096,575-123-1466-1014,29.97,1920,1080,train\nFzJJ_bWLzcA,2502,2805,752-95-1647-990,29.97,1920,1080,train\nFzJJ_bWLzcA,3462,3600,452-57-1346-951,29.97,1920,1080,train\nFzJJ_bWLzcA,3829,4122,182-56-1031-905,29.97,1920,1080,train\nd_kA4yIakbs,4185,4886,282-114-608-440,29.97,854,480,train\nd_kA4yIakbs,5023,5303,275-114-579-418,29.97,854,480,train\nd_kA4yIakbs,5445,5583,226-125-517-416,29.97,854,480,train\nd_kA4yIakbs,5599,5775,312-142-598-428,29.97,854,480,train\nd_kA4yIakbs,6152,6282,284-155-560-431,29.97,854,480,train\nd_kA4yIakbs,7188,7406,329-147-630-448,29.97,854,480,train\nd_kA4yIakbs,7502,7726,347-93-696-442,29.97,854,480,train\n7cHsPUybKGg,2452,2582,143-101-429-387,25.0,640,480,train\n7cHsPUybKGg,2621,2814,157-68-480-391,25.0,640,480,train\n7cHsPUybKGg,2852,2980,179-93-474-388,25.0,640,480,train\n7cHsPUybKGg,3235,3386,141-97-429-385,25.0,640,480,train\n7cHsPUybKGg,3411,3568,136-52-475-391,25.0,640,480,train\n7cHsPUybKGg,3640,3782,178-97-474-393,25.0,640,480,train\n7cHsPUybKGg,3827,4164,156-81-470-395,25.0,640,480,train\n7cHsPUybKGg,4512,4664,120-22-503-405,25.0,640,480,train\n7cHsPUybKGg,4700,4874,137-70-472-405,25.0,640,480,train\n7cHsPUybKGg,5587,5721,138-101-478-441,25.0,640,480,train\n7cHsPUybKGg,5940,6115,141-83-476-418,25.0,640,480,train\n7cHsPUybKGg,6159,6437,120-77-453-410,25.0,640,480,train\nLZ2llkUGrsw,3300,3431,58-38-464-444,29.97,640,480,train\nLZ2llkUGrsw,4052,4360,121-6-581-466,29.97,640,480,train\nLZ2llkUGrsw,4522,4687,129-20-566-457,29.97,640,480,train\nLZ2llkUGrsw,4769,4910,128-0-595-467,29.97,640,480,train\nLZ2llkUGrsw,6142,6320,165-44-588-467,29.97,640,480,train\nLZ2llkUGrsw,6509,6865,130-42-543-455,29.97,640,480,train\nLZ2llkUGrsw,7286,7415,89-69-473-453,29.97,640,480,train\nLZ2llkUGrsw,8448,8749,140-100-515-475,29.97,640,480,train\nLZ2llkUGrsw,8751,9081,130-52-551-473,29.97,640,480,train\nLZ2llkUGrsw,9420,10071,84-62-491-469,29.97,640,480,train\nLZ2llkUGrsw,10108,10260,137-27-575-465,29.97,640,480,train\nLZ2llkUGrsw,11207,11425,93-58-504-469,29.97,640,480,train\nLZ2llkUGrsw,11428,11676,100-13-560-473,29.97,640,480,train\nLZ2llkUGrsw,12120,12297,151-37-580-466,29.97,640,480,train\nLZ2llkUGrsw,12382,12553,114-25-569-480,29.97,640,480,train\nLZ2llkUGrsw,12554,12742,126-22-574-470,29.97,640,480,train\nQ52BKOPKOA0,381,1405,43-56-675-688,25.0,1280,720,train\nQ52BKOPKOA0,1405,2281,248-133-752-637,25.0,1280,720,train\nQ52BKOPKOA0,2388,2571,385-154-842-611,25.0,1280,720,train\nQ52BKOPKOA0,2571,2703,384-174-842-632,25.0,1280,720,train\nQ52BKOPKOA0,2845,3063,341-126-856-641,25.0,1280,720,train\nQ52BKOPKOA0,3104,3288,514-144-996-626,25.0,1280,720,train\nQ52BKOPKOA0,3289,3519,458-144-951-637,25.0,1280,720,train\nQ52BKOPKOA0,3631,3762,716-160-1165-609,25.0,1280,720,train\nQ52BKOPKOA0,3972,4138,531-112-1096-677,25.0,1280,720,train\nQ52BKOPKOA0,4138,4281,547-70-1158-681,25.0,1280,720,train\nMEPsADK9Vmk,466,703,170-167-443-440,29.97,640,480,test\nMEPsADK9Vmk,898,1426,191-137-502-448,29.97,640,480,test\nMEPsADK9Vmk,1611,1887,241-115-572-446,29.97,640,480,test\nMEPsADK9Vmk,2049,2189,157-127-491-461,29.97,640,480,test\nMEPsADK9Vmk,2208,2422,198-169-483-454,29.97,640,480,test\nMEPsADK9Vmk,2585,2786,110-119-447-456,29.97,640,480,test\nMEPsADK9Vmk,2786,2966,166-127-491-452,29.97,640,480,test\nMEPsADK9Vmk,4351,4602,204-133-517-446,29.97,640,480,test\nMEPsADK9Vmk,4654,4834,142-144-434-436,29.97,640,480,test\n9b1jcHFhVKg,588,727,147-107-476-436,25.0,600,480,train\n9b1jcHFhVKg,820,1133,129-89-491-451,25.0,600,480,train\n9b1jcHFhVKg,2160,2321,167-85-525-443,25.0,600,480,train\n9b1jcHFhVKg,2322,2488,152-82-522-452,25.0,600,480,train\n9b1jcHFhVKg,2489,2688,145-94-502-451,25.0,600,480,train\n9b1jcHFhVKg,2690,3649,132-93-491-452,25.0,600,480,train\n9b1jcHFhVKg,3655,3919,88-9-529-450,25.0,600,480,train\n9b1jcHFhVKg,4429,4616,180-85-542-447,25.0,600,480,train\n9b1jcHFhVKg,5354,6378,130-96-481-447,25.0,600,480,train\n9b1jcHFhVKg,6378,7402,132-89-491-448,25.0,600,480,train\n9b1jcHFhVKg,7402,7550,129-89-493-453,25.0,600,480,train\n9b1jcHFhVKg,7560,7840,133-90-490-447,25.0,600,480,train\n9b1jcHFhVKg,7938,8115,133-89-501-457,25.0,600,480,train\n9b1jcHFhVKg,8238,8370,134-90-493-449,25.0,600,480,train\n9b1jcHFhVKg,8370,8687,134-90-493-449,25.0,600,480,train\n9b1jcHFhVKg,8688,9213,115-50-517-452,25.0,600,480,train\n9b1jcHFhVKg,9213,9614,91-11-532-452,25.0,600,480,train\noEtFlwUMyvY,2897,3921,118-45-525-452,29.97,640,480,train\noEtFlwUMyvY,3921,4896,113-52-513-452,29.97,640,480,train\noEtFlwUMyvY,5677,5828,113-49-524-460,29.97,640,480,train\noEtFlwUMyvY,5844,6125,108-18-550-460,29.97,640,480,train\nFpLOIJJMXhg,117,652,98-4-561-467,25.0,640,480,train\nFpLOIJJMXhg,665,1505,115-32-561-478,25.0,640,480,train\nFpLOIJJMXhg,1731,2326,81-25-509-453,25.0,640,480,train\nFpLOIJJMXhg,2363,2588,77-21-519-463,25.0,640,480,train\nFpLOIJJMXhg,2661,3274,57-2-523-468,25.0,640,480,train\nFpLOIJJMXhg,3596,3769,177-126-506-455,25.0,640,480,train\nFpLOIJJMXhg,4268,4552,103-85-472-454,25.0,640,480,train\nFpLOIJJMXhg,4939,5673,89-68-478-457,25.0,640,480,train\nFpLOIJJMXhg,6731,7031,94-63-498-467,25.0,640,480,train\nnUDf0Gv_GJ4,530,1554,0-73-334-408,25.0,640,480,train\nnUDf0Gv_GJ4,1638,1808,34-97-343-406,25.0,640,480,train\nnUDf0Gv_GJ4,1914,2285,9-102-312-405,25.0,640,480,train\nnUDf0Gv_GJ4,2424,3169,44-95-356-407,25.0,640,480,train\nnUDf0Gv_GJ4,3461,3816,4-97-320-413,25.0,640,480,train\nnUDf0Gv_GJ4,3909,4148,10-104-315-409,25.0,640,480,train\nnUDf0Gv_GJ4,4148,4625,10-90-330-410,25.0,640,480,train\nnUDf0Gv_GJ4,4724,5514,10-86-339-415,25.0,640,480,train\nnUDf0Gv_GJ4,5648,5900,48-97-369-418,25.0,640,480,train\nnUDf0Gv_GJ4,5947,6692,12-64-373-425,25.0,640,480,train\nnUDf0Gv_GJ4,6786,6960,3-81-347-425,25.0,640,480,train\nnUDf0Gv_GJ4,6960,7198,2-64-371-433,25.0,640,480,train\nnUDf0Gv_GJ4,7290,7475,94-72-450-428,25.0,640,480,train\nnUDf0Gv_GJ4,7689,7890,79-78-436-435,25.0,640,480,train\nnUDf0Gv_GJ4,7890,8044,27-80-373-426,25.0,640,480,train\nnUDf0Gv_GJ4,8044,8310,55-62-418-425,25.0,640,480,train\nQBqpVrjyeYM,3660,3843,146-118-499-471,25.0,640,480,train\nQBqpVrjyeYM,4690,5063,186-181-476-471,25.0,640,480,train\nQBqpVrjyeYM,6048,6213,194-188-481-475,25.0,640,480,train\nQBqpVrjyeYM,6216,6347,194-195-462-463,25.0,640,480,train\nAdEkWqdDlp8,0,216,1072-335-1762-1025,25.0,1920,1080,train\nAdEkWqdDlp8,292,749,1093-301-1807-1015,25.0,1920,1080,train\nAdEkWqdDlp8,1203,2227,234-261-1046-1073,25.0,1920,1080,train\nAdEkWqdDlp8,2227,3251,331-260-1123-1052,25.0,1920,1080,train\nAdEkWqdDlp8,3251,3610,409-307-1107-1005,25.0,1920,1080,train\nAdEkWqdDlp8,3659,3891,553-314-1197-958,25.0,1920,1080,train\nAdEkWqdDlp8,3920,4110,408-302-1107-1001,25.0,1920,1080,train\nAdEkWqdDlp8,4110,4342,631-323-1293-985,25.0,1920,1080,train\nAdEkWqdDlp8,4342,5056,658-290-1350-982,25.0,1920,1080,train\nJdiIQg47Wc4,835,1096,173-195-1000-1022,25.0,1920,1080,train\nJdiIQg47Wc4,2117,2248,63-141-981-1059,25.0,1920,1080,train\nJdiIQg47Wc4,3301,3563,243-73-1183-1013,25.0,1920,1080,train\nJdiIQg47Wc4,3603,3733,329-191-1171-1033,25.0,1920,1080,train\nJdiIQg47Wc4,3801,3959,160-152-1049-1041,25.0,1920,1080,train\naOZmneMZICQ,0,219,257-120-540-403,24.0,854,480,train\naOZmneMZICQ,291,1256,289-139-556-406,24.0,854,480,train\naOZmneMZICQ,1256,1919,292-125-573-406,24.0,854,480,train\naOZmneMZICQ,1919,2496,298-108-598-408,24.0,854,480,train\naOZmneMZICQ,2496,2767,284-116-574-406,24.0,854,480,train\naOZmneMZICQ,3246,3456,288-129-561-402,24.0,854,480,train\naOZmneMZICQ,3480,3677,273-80-593-400,24.0,854,480,train\naOZmneMZICQ,3752,3951,282-122-566-406,24.0,854,480,train\naOZmneMZICQ,3980,4124,251-56-601-406,24.0,854,480,train\naOZmneMZICQ,4257,4452,281-120-564-403,24.0,854,480,train\naOZmneMZICQ,4472,4864,261-71-594-404,24.0,854,480,train\naOZmneMZICQ,4880,5180,284-102-585-403,24.0,854,480,train\naOZmneMZICQ,5180,5334,269-87-585-403,24.0,854,480,train\naOZmneMZICQ,5338,6362,245-49-605-409,24.0,854,480,train\naOZmneMZICQ,6413,6809,303-116-590-403,24.0,854,480,train\nRCiy2FYViEg,382,1051,185-80-511-406,29.97,640,480,train\nRCiy2FYViEg,1740,2161,178-76-502-400,29.97,640,480,train\nRCiy2FYViEg,2238,2446,194-65-506-377,29.97,640,480,train\nRCiy2FYViEg,3171,3310,208-84-510-386,29.97,640,480,train\nRCiy2FYViEg,4437,4805,200-97-477-374,29.97,640,480,train\n67If7DVAWNE,1170,1327,142-51-549-458,30.0,640,480,train\n67If7DVAWNE,1327,1472,136-38-562-464,30.0,640,480,train\n67If7DVAWNE,1472,2005,141-41-564-464,30.0,640,480,train\ngaccfn5JB4Y,1713,1845,169-28-566-425,29.97,640,480,test\ngaccfn5JB4Y,7950,8100,90-20-497-427,29.97,640,480,test\nVBevstnH4Ds,482,738,184-126-459-401,25.0,640,480,train\nVBevstnH4Ds,1057,1578,168-92-475-399,25.0,640,480,train\nVBevstnH4Ds,1700,2163,165-90-475-400,25.0,640,480,train\nVBevstnH4Ds,2269,2688,168-96-473-401,25.0,640,480,train\nVBevstnH4Ds,2702,3267,152-64-491-403,25.0,640,480,train\nVBevstnH4Ds,3390,4414,158-76-483-401,25.0,640,480,train\nVBevstnH4Ds,4414,5438,186-124-456-394,25.0,640,480,train\nVBevstnH4Ds,5438,5759,191-130-459-398,25.0,640,480,train\nVBevstnH4Ds,5759,6783,186-112-476-402,25.0,640,480,train\nVBevstnH4Ds,6783,7807,181-129-454-402,25.0,640,480,train\nVBevstnH4Ds,7807,8583,181-123-455-397,25.0,640,480,train\ngDF0gW-jo9E,635,829,382-105-903-626,29.97,1280,720,train\ngDF0gW-jo9E,830,977,379-102-902-625,29.97,1280,720,train\ngDF0gW-jo9E,1068,1261,365-73-914-622,29.97,1280,720,train\ngDF0gW-jo9E,1497,1685,251-115-812-676,29.97,1280,720,train\ngDF0gW-jo9E,2196,2402,321-115-834-628,29.97,1280,720,train\ngDF0gW-jo9E,2547,2830,335-78-869-612,29.97,1280,720,train\ngDF0gW-jo9E,2830,2963,199-48-750-599,29.97,1280,720,train\ngDF0gW-jo9E,3252,3451,138-49-793-704,29.97,1280,720,train\ngDF0gW-jo9E,3451,3681,109-49-765-705,29.97,1280,720,train\ngDF0gW-jo9E,3681,3879,123-54-768-699,29.97,1280,720,train\ngDF0gW-jo9E,3904,4333,152-74-752-674,29.97,1280,720,train\ngDF0gW-jo9E,4336,4520,241-82-788-629,29.97,1280,720,train\ngDF0gW-jo9E,4520,4706,231-68-790-627,29.97,1280,720,train\ngDF0gW-jo9E,4729,4917,194-97-757-660,29.97,1280,720,train\ngDF0gW-jo9E,5663,5864,274-97-863-686,29.97,1280,720,train\ngDF0gW-jo9E,6151,6473,344-80-941-677,29.97,1280,720,train\nIXMiGVYeTJ4,934,1146,149-124-418-393,29.97,640,480,train\nIXMiGVYeTJ4,1164,1293,131-128-393-390,29.97,640,480,train\nIXMiGVYeTJ4,2749,2926,106-123-381-398,29.97,640,480,train\nIXMiGVYeTJ4,3645,3833,147-130-407-390,29.97,640,480,train\nIXMiGVYeTJ4,4400,4553,204-131-470-397,29.97,640,480,train\nIXMiGVYeTJ4,4557,4727,179-120-456-397,29.97,640,480,train\nIXMiGVYeTJ4,5128,5438,154-101-448-395,29.97,640,480,train\n5Z8D9WwcETQ,124,357,368-103-847-582,25.0,1280,720,train\n5Z8D9WwcETQ,357,500,371-107-846-582,25.0,1280,720,train\n5Z8D9WwcETQ,979,1228,378-79-872-573,25.0,1280,720,train\n5Z8D9WwcETQ,3241,3390,284-86-810-612,25.0,1280,720,train\n5Z8D9WwcETQ,3795,3937,235-22-842-629,25.0,1280,720,train\n5Z8D9WwcETQ,3942,4165,158-15-812-669,25.0,1280,720,train\n5Z8D9WwcETQ,5695,5947,306-0-974-668,25.0,1280,720,train\n5Z8D9WwcETQ,5995,6145,141-6-760-625,25.0,1280,720,train\n5Z8D9WwcETQ,10158,10356,276-20-844-588,25.0,1280,720,train\n5Z8D9WwcETQ,10530,10835,366-34-959-627,25.0,1280,720,train\nq1KCN0rDiAE,0,406,604-254-1172-822,25.0,1920,1080,train\nq1KCN0rDiAE,406,898,658-267-1222-831,25.0,1920,1080,train\nq1KCN0rDiAE,898,1105,535-307-1046-818,25.0,1920,1080,train\nq1KCN0rDiAE,1413,1616,469-320-1002-853,25.0,1920,1080,train\nq1KCN0rDiAE,1616,1772,547-292-1136-881,25.0,1920,1080,train\nq1KCN0rDiAE,1772,2022,577-260-1188-871,25.0,1920,1080,train\nq1KCN0rDiAE,2228,2475,415-304-982-871,25.0,1920,1080,train\nq1KCN0rDiAE,2558,2771,412-310-980-878,25.0,1920,1080,train\nq1KCN0rDiAE,2987,3151,250-177-941-868,25.0,1920,1080,train\nq1KCN0rDiAE,3175,3366,263-293-938-968,25.0,1920,1080,train\nq1KCN0rDiAE,4387,4893,703-292-1274-863,25.0,1920,1080,train\nq1KCN0rDiAE,7136,7376,622-341-1098-817,25.0,1920,1080,train\nq1KCN0rDiAE,7387,7523,671-304-1219-852,25.0,1920,1080,train\nq1KCN0rDiAE,7523,7733,676-272-1241-837,25.0,1920,1080,train\nq1KCN0rDiAE,7733,7876,588-306-1119-837,25.0,1920,1080,train\n4rknb1u9kAQ,513,1091,258-111-788-641,29.97,1280,720,train\n4rknb1u9kAQ,1292,1580,226-163-724-661,29.97,1280,720,train\n4rknb1u9kAQ,2059,2348,310-141-842-673,29.97,1280,720,train\n4rknb1u9kAQ,2607,2789,399-169-877-647,29.97,1280,720,train\n4rknb1u9kAQ,2900,3041,435-146-955-666,29.97,1280,720,train\n4rknb1u9kAQ,3537,3683,384-125-920-661,29.97,1280,720,train\n4rknb1u9kAQ,4230,4481,608-146-1083-621,29.97,1280,720,train\n4rknb1u9kAQ,4505,4661,562-121-1033-592,29.97,1280,720,train\n4rknb1u9kAQ,5879,6017,446-134-938-626,29.97,1280,720,train\n4rknb1u9kAQ,6622,6907,171-58-810-697,29.97,1280,720,train\n4rknb1u9kAQ,8458,8625,220-150-726-656,29.97,1280,720,train\n4rknb1u9kAQ,13070,13211,297-192-714-609,29.97,1280,720,train\n4rknb1u9kAQ,13237,13385,206-164-679-637,29.97,1280,720,train\n4rknb1u9kAQ,13449,13691,276-182-706-612,29.97,1280,720,train\n4rknb1u9kAQ,13887,14183,282-140-753-611,29.97,1280,720,train\ngmSa_wwIhfE,4297,4451,136-10-590-464,29.97,640,480,train\ngmSa_wwIhfE,4734,4885,65-30-513-478,29.97,640,480,train\ngmSa_wwIhfE,4904,5032,139-53-553-467,29.97,640,480,train\ngmSa_wwIhfE,5033,5218,145-49-550-454,29.97,640,480,train\ngmSa_wwIhfE,5550,5727,164-66-563-465,29.97,640,480,train\ngmSa_wwIhfE,9143,9366,214-52-611-449,29.97,640,480,train\ngmSa_wwIhfE,10057,10203,177-37-587-447,29.97,640,480,train\ngmSa_wwIhfE,11205,11372,183-82-546-445,29.97,640,480,train\ngmSa_wwIhfE,11524,11672,184-66-568-450,29.97,640,480,train\nWlDYrq8K6nk,2253,2686,260-18-938-696,29.97,1280,720,test\nWlDYrq8K6nk,2959,3094,353-46-990-683,29.97,1280,720,test\nWlDYrq8K6nk,3247,3381,324-52-980-708,29.97,1280,720,test\nWlDYrq8K6nk,3984,4245,341-116-938-713,29.97,1280,720,test\nWlDYrq8K6nk,4875,5151,389-9-1096-716,29.97,1280,720,test\nWlDYrq8K6nk,5264,5403,297-17-959-679,29.97,1280,720,test\nWlDYrq8K6nk,5943,6135,261-23-942-704,29.97,1280,720,test\nWlDYrq8K6nk,7058,7241,337-4-1009-676,29.97,1280,720,test\nWlDYrq8K6nk,8186,8512,276-7-974-705,29.97,1280,720,test\nWlDYrq8K6nk,8520,8777,326-75-953-702,29.97,1280,720,test\ny4egTMS9H1k,382,640,107-62-963-918,25.0,1920,1080,train\ny4egTMS9H1k,640,917,146-51-1032-937,25.0,1920,1080,train\ny4egTMS9H1k,978,1117,443-111-1272-940,25.0,1920,1080,train\ny4egTMS9H1k,1139,1357,579-120-1453-994,25.0,1920,1080,train\ny4egTMS9H1k,3217,3350,507-24-1464-981,25.0,1920,1080,train\ny4egTMS9H1k,3469,3730,353-37-1308-992,25.0,1920,1080,train\ny4egTMS9H1k,4163,4389,519-45-1426-952,25.0,1920,1080,train\ny4egTMS9H1k,4612,4800,532-60-1428-956,25.0,1920,1080,train\ny4egTMS9H1k,4800,5009,492-16-1437-961,25.0,1920,1080,train\ny4egTMS9H1k,5330,5476,192-123-1038-969,25.0,1920,1080,train\ny4egTMS9H1k,5508,5704,123-167-910-954,25.0,1920,1080,train\ny4egTMS9H1k,5922,6063,322-93-1246-1017,25.0,1920,1080,train\ny4egTMS9H1k,6103,6370,410-87-1372-1049,25.0,1920,1080,train\ny4egTMS9H1k,6370,6514,700-137-1517-954,25.0,1920,1080,train\ny4egTMS9H1k,7018,7169,782-129-1677-1024,25.0,1920,1080,train\ny4egTMS9H1k,7388,7705,874-46-1869-1041,25.0,1920,1080,train\ny4egTMS9H1k,8168,8332,433-46-1357-970,25.0,1920,1080,train\ny4egTMS9H1k,8944,9083,431-95-1295-959,25.0,1920,1080,train\ny4egTMS9H1k,9083,9280,476-52-1369-945,25.0,1920,1080,train\ny4egTMS9H1k,9280,9458,484-138-1335-989,25.0,1920,1080,train\ny4egTMS9H1k,9539,9751,664-141-1434-911,25.0,1920,1080,train\ny4egTMS9H1k,9751,9943,572-104-1363-895,25.0,1920,1080,train\ny4egTMS9H1k,10173,10417,256-80-1165-989,25.0,1920,1080,train\ny4egTMS9H1k,10452,10675,298-104-1181-987,25.0,1920,1080,train\ny4egTMS9H1k,10706,10835,512-109-1449-1046,25.0,1920,1080,train\ny4egTMS9H1k,10859,11061,609-129-1527-1047,25.0,1920,1080,train\ny4egTMS9H1k,11342,11706,595-24-1616-1045,25.0,1920,1080,train\nP9nWs-Haf_I,267,1291,184-140-490-446,25.0,648,480,train\nP9nWs-Haf_I,1599,1740,194-154-489-449,25.0,648,480,train\nP9nWs-Haf_I,1850,2113,199-140-514-455,25.0,648,480,train\n4a0Gro197W4,23,312,64-3-527-466,29.97,640,480,train\n4a0Gro197W4,2755,2910,186-37-530-381,29.97,640,480,train\n4a0Gro197W4,3130,3285,138-13-515-390,29.97,640,480,train\neQqUScz9rLw,76,580,165-101-468-404,25.0,640,480,train\neQqUScz9rLw,580,904,132-123-426-417,25.0,640,480,train\neQqUScz9rLw,2620,2923,124-72-489-437,25.0,640,480,train\neQqUScz9rLw,3587,3735,155-71-526-442,25.0,640,480,train\njVIhp_8EWIE,302,524,115-36-497-418,29.97,640,480,train\njVIhp_8EWIE,4912,5048,215-59-515-359,29.97,640,480,train\nJgx22uN5xzQ,249,600,267-111-558-402,25.0,640,480,train\nJgx22uN5xzQ,951,1200,134-124-415-405,25.0,640,480,train\nJgx22uN5xzQ,1261,1391,133-132-403-402,25.0,640,480,train\nJgx22uN5xzQ,1527,1725,125-134-389-398,25.0,640,480,train\nJgx22uN5xzQ,2151,2387,120-131-379-390,25.0,640,480,train\nJgx22uN5xzQ,2410,2675,175-127-443-395,25.0,640,480,train\nJgx22uN5xzQ,2887,3311,17-28-455-466,25.0,640,480,train\nJgx22uN5xzQ,3436,3605,43-80-423-460,25.0,640,480,train\nJgx22uN5xzQ,4505,4714,105-82-502-479,25.0,640,480,train\nrjfmhJ6GCwM,1218,1634,315-46-983-714,29.97,1280,720,train\nrjfmhJ6GCwM,1801,2000,383-51-1049-717,29.97,1280,720,train\nrjfmhJ6GCwM,2188,2406,316-69-940-693,29.97,1280,720,train\nrjfmhJ6GCwM,2976,3114,360-113-911-664,29.97,1280,720,train\nrjfmhJ6GCwM,3225,3430,406-62-1025-681,29.97,1280,720,train\nrjfmhJ6GCwM,6472,6687,347-92-951-696,29.97,1280,720,train\nrjfmhJ6GCwM,6689,6881,354-104-950-700,29.97,1280,720,train\nrjfmhJ6GCwM,7235,7685,343-43-990-690,29.97,1280,720,train\nP0aQKRrvpt8,1107,1244,117-132-383-398,25.0,640,480,train\nP0aQKRrvpt8,3501,3681,119-87-407-375,25.0,640,480,train\nS_aTWQUxylE,162,566,131-17-573-459,25.0,640,480,train\nqVoJJj13PaY,1167,1486,116-42-518-444,29.97,640,480,train\nqVoJJj13PaY,6070,6213,150-74-523-447,29.97,640,480,train\nqV6PjN55Lb4,785,941,423-68-1345-990,29.97,1920,1080,train\nqV6PjN55Lb4,946,1875,425-73-1343-991,29.97,1920,1080,train\nqV6PjN55Lb4,1949,2088,725-205-1498-978,29.97,1920,1080,train\nqV6PjN55Lb4,2373,2706,582-118-1452-988,29.97,1920,1080,train\nqV6PjN55Lb4,2727,3057,466-21-1443-998,29.97,1920,1080,train\nqV6PjN55Lb4,3251,3419,727-173-1508-954,29.97,1920,1080,train\nqV6PjN55Lb4,3566,3742,721-127-1607-1013,29.97,1920,1080,train\nqV6PjN55Lb4,3905,4135,607-109-1467-969,29.97,1920,1080,train\nqV6PjN55Lb4,4135,4296,387-167-1208-988,29.97,1920,1080,train\nqV6PjN55Lb4,4336,4491,466-162-1289-985,29.97,1920,1080,train\nqV6PjN55Lb4,4491,4876,437-97-1333-993,29.97,1920,1080,train\nqV6PjN55Lb4,6370,6521,497-194-1254-951,29.97,1920,1080,train\nqV6PjN55Lb4,7456,7733,615-179-1389-953,29.97,1920,1080,train\nqV6PjN55Lb4,7944,8378,546-146-1336-936,29.97,1920,1080,train\nqV6PjN55Lb4,8681,8902,708-113-1516-921,29.97,1920,1080,train\nqV6PjN55Lb4,8924,9094,763-107-1572-916,29.97,1920,1080,train\nqV6PjN55Lb4,9582,9794,458-53-1401-996,29.97,1920,1080,train\nqV6PjN55Lb4,10285,10464,653-140-1488-975,29.97,1920,1080,train\nqV6PjN55Lb4,10464,10594,515-175-1337-997,29.97,1920,1080,train\nqV6PjN55Lb4,10769,10965,620-128-1487-995,29.97,1920,1080,train\nqV6PjN55Lb4,11040,11178,438-121-1326-1009,29.97,1920,1080,train\nqV6PjN55Lb4,11350,11534,512-146-1381-1015,29.97,1920,1080,train\nqV6PjN55Lb4,11680,12002,534-65-1495-1026,29.97,1920,1080,train\nmAmvStH5k4g,3132,3284,150-38-554-442,29.97,640,480,train\nmAmvStH5k4g,3765,3971,173-34-592-453,29.97,640,480,train\nmAmvStH5k4g,4096,4426,140-40-555-455,29.97,640,480,train\nmAmvStH5k4g,4471,4866,71-36-507-472,29.97,640,480,train\nmAmvStH5k4g,5670,5820,119-44-539-464,29.97,640,480,train\npbznqs21OvQ,577,1601,311-101-794-584,50.0,1280,720,train\npbznqs21OvQ,1684,2013,418-130-873-585,50.0,1280,720,train\npbznqs21OvQ,2070,2226,259-120-742-603,50.0,1280,720,train\npbznqs21OvQ,2278,2486,284-169-752-637,50.0,1280,720,train\npbznqs21OvQ,2567,3591,302-98-884-680,50.0,1280,720,train\npbznqs21OvQ,3867,4371,181-152-687-658,50.0,1280,720,train\npbznqs21OvQ,4484,4685,295-174-782-661,50.0,1280,720,train\npbznqs21OvQ,4733,5022,164-106-697-639,50.0,1280,720,train\npbznqs21OvQ,5022,5166,184-114-737-667,50.0,1280,720,train\npbznqs21OvQ,5166,5341,101-83-671-653,50.0,1280,720,train\npbznqs21OvQ,5631,5785,305-178-785-658,50.0,1280,720,train\npbznqs21OvQ,5785,5946,302-151-814-663,50.0,1280,720,train\npbznqs21OvQ,6089,6377,342-151-846-655,50.0,1280,720,train\npbznqs21OvQ,6811,6967,487-17-1121-651,50.0,1280,720,train\npbznqs21OvQ,6967,7157,488-110-1057-679,50.0,1280,720,train\npbznqs21OvQ,7540,7724,436-16-1139-719,50.0,1280,720,train\npbznqs21OvQ,8385,9137,220-97-817-694,50.0,1280,720,train\npbznqs21OvQ,9137,10050,123-71-679-627,50.0,1280,720,train\npbznqs21OvQ,10050,10519,253-147-726-620,50.0,1280,720,train\npbznqs21OvQ,10879,11158,451-156-910-615,50.0,1280,720,train\npbznqs21OvQ,11158,11595,445-134-916-605,50.0,1280,720,train\npbznqs21OvQ,11867,12075,287-145-803-661,50.0,1280,720,train\npbznqs21OvQ,12075,12266,267-119-806-658,50.0,1280,720,train\npbznqs21OvQ,12312,13142,267-94-840-667,50.0,1280,720,train\npbznqs21OvQ,13295,13877,286-72-907-693,50.0,1280,720,train\npbznqs21OvQ,13877,14421,253-43-900-690,50.0,1280,720,train\nN8yfhFc25c8,0,1024,454-277-1173-996,29.97,1920,1080,train\nN8yfhFc25c8,1557,1836,668-339-1312-983,29.97,1920,1080,train\nN8yfhFc25c8,1836,1995,558-329-1224-995,29.97,1920,1080,train\nN8yfhFc25c8,2082,2265,497-321-1166-990,29.97,1920,1080,train\nN8yfhFc25c8,2309,2876,669-318-1338-987,29.97,1920,1080,train\nN8yfhFc25c8,3000,3524,653-341-1309-997,29.97,1920,1080,train\nN8yfhFc25c8,3524,4357,528-342-1193-1007,29.97,1920,1080,train\nN8yfhFc25c8,4669,4863,537-350-1180-993,29.97,1920,1080,train\nN8yfhFc25c8,4878,5546,660-287-1347-974,29.97,1920,1080,train\nBm82HLNjkKw,241,830,166-223-422-479,30.0,640,480,train\nBm82HLNjkKw,1528,2552,165-202-443-480,30.0,640,480,train\nBm82HLNjkKw,6236,7260,181-203-457-479,30.0,640,480,train\nBm82HLNjkKw,7338,7690,182-201-461-480,30.0,640,480,train\nMvupxvDqZ9M,155,1104,106-6-563-463,29.97,640,480,train\nMvupxvDqZ9M,1905,2823,137-5-579-447,29.97,640,480,train\nMvupxvDqZ9M,3202,3832,120-13-558-451,29.97,640,480,train\nMvupxvDqZ9M,4250,4436,100-6-535-441,29.97,640,480,train\nMvupxvDqZ9M,4436,5020,95-5-555-465,29.97,640,480,train\nMvupxvDqZ9M,5709,6733,103-26-532-455,29.97,640,480,train\nMvupxvDqZ9M,6972,7811,141-16-580-455,29.97,640,480,train\nMvupxvDqZ9M,8962,9544,165-21-609-465,29.97,640,480,train\nMvupxvDqZ9M,9566,10120,123-24-555-456,29.97,640,480,train\nMvupxvDqZ9M,10463,11410,89-10-536-457,29.97,640,480,train\nMvupxvDqZ9M,11410,11671,94-32-517-455,29.97,640,480,train\nMvupxvDqZ9M,11759,12308,102-10-548-456,29.97,640,480,train\nVhprHat04dk,1321,1459,458-125-1287-954,29.97,1920,1080,train\nVhprHat04dk,4550,4740,426-96-1261-931,29.97,1920,1080,train\nmtXOJ5vBkLw,180,497,215-45-620-450,29.97,854,480,train\nmtXOJ5vBkLw,1302,1449,292-94-660-462,29.97,854,480,train\nmtXOJ5vBkLw,4527,4703,247-70-637-460,29.97,854,480,train\nNjAu1n_-r0A,318,596,635-329-1359-1053,25.0,1920,1080,train\nNjAu1n_-r0A,596,945,625-291-1383-1049,25.0,1920,1080,train\nNjAu1n_-r0A,1043,1176,621-326-1328-1033,25.0,1920,1080,train\nNjAu1n_-r0A,1208,1476,536-166-1419-1049,25.0,1920,1080,train\nNjAu1n_-r0A,1530,1701,638-310-1377-1049,25.0,1920,1080,train\nNjAu1n_-r0A,1736,1943,538-344-1233-1039,25.0,1920,1080,train\nNjAu1n_-r0A,2095,2297,650-283-1407-1040,25.0,1920,1080,train\nNjAu1n_-r0A,2363,2548,602-289-1353-1040,25.0,1920,1080,train\nNjAu1n_-r0A,2800,2953,535-381-1183-1029,25.0,1920,1080,train\nNjAu1n_-r0A,3220,3412,742-288-1481-1027,25.0,1920,1080,train\nNjAu1n_-r0A,3493,3701,640-345-1332-1037,25.0,1920,1080,train\nNjAu1n_-r0A,4925,5081,797-329-1519-1051,25.0,1920,1080,train\nNjAu1n_-r0A,5155,5355,617-196-1481-1060,25.0,1920,1080,train\nNjAu1n_-r0A,5674,6187,594-155-1499-1060,25.0,1920,1080,train\nNjAu1n_-r0A,6817,7302,641-282-1398-1039,25.0,1920,1080,train\nNjAu1n_-r0A,7741,8169,583-260-1355-1032,25.0,1920,1080,train\nNjAu1n_-r0A,8170,8311,595-285-1353-1043,25.0,1920,1080,train\nNjAu1n_-r0A,8355,8749,517-158-1413-1054,25.0,1920,1080,train\nNjAu1n_-r0A,8977,9148,539-182-1406-1049,25.0,1920,1080,train\nNjAu1n_-r0A,9318,9468,487-349-1192-1054,25.0,1920,1080,train\nNjAu1n_-r0A,10494,10665,557-293-1292-1028,25.0,1920,1080,train\nwtFqCHVGA44,2596,2867,199-24-648-473,29.97,854,480,train\nwtFqCHVGA44,3700,3904,304-35-693-424,29.97,854,480,train\nwtFqCHVGA44,3904,4136,302-20-698-416,29.97,854,480,train\nwtFqCHVGA44,4311,4536,352-50-752-450,29.97,854,480,train\nwtFqCHVGA44,4536,4849,325-30-755-460,29.97,854,480,train\nwtFqCHVGA44,4849,5250,334-42-738-446,29.97,854,480,train\nwtFqCHVGA44,5250,5428,333-52-726-445,29.97,854,480,train\nwtFqCHVGA44,5428,5631,339-34-726-421,29.97,854,480,train\nwtFqCHVGA44,5855,6021,290-36-704-450,29.97,854,480,train\nwtFqCHVGA44,6021,6623,279-47-702-470,29.97,854,480,train\nwtFqCHVGA44,6641,6810,241-23-667-449,29.97,854,480,train\nwtFqCHVGA44,8312,8460,222-4-688-470,29.97,854,480,train\nwtFqCHVGA44,8469,9108,189-27-627-465,29.97,854,480,train\nwtFqCHVGA44,9108,9262,181-7-607-433,29.97,854,480,train\nP4vKV-G3hGE,108,351,573-307-1290-1024,29.97,1920,1080,train\nP4vKV-G3hGE,440,991,635-223-1341-929,29.97,1920,1080,train\nP4vKV-G3hGE,1024,1225,553-285-1226-958,29.97,1920,1080,train\nP4vKV-G3hGE,1225,1410,493-325-1156-988,29.97,1920,1080,train\nP4vKV-G3hGE,1410,1616,424-293-1115-984,29.97,1920,1080,train\nP4vKV-G3hGE,1830,2163,415-337-1090-1012,29.97,1920,1080,train\nP4vKV-G3hGE,2805,3003,383-128-1122-867,29.97,1920,1080,train\nP4vKV-G3hGE,3071,3458,394-135-1153-894,29.97,1920,1080,train\nP4vKV-G3hGE,3541,3759,439-121-1186-868,29.97,1920,1080,train\nP4vKV-G3hGE,3814,4012,321-52-1063-794,29.97,1920,1080,train\nP4vKV-G3hGE,4592,4973,503-160-1239-896,29.97,1920,1080,train\nP4vKV-G3hGE,6213,6361,357-138-1198-979,29.97,1920,1080,train\nP4vKV-G3hGE,6381,6654,396-189-1245-1038,29.97,1920,1080,train\nP4vKV-G3hGE,6877,7122,375-180-1215-1020,29.97,1920,1080,train\nP4vKV-G3hGE,7122,7250,238-172-1087-1021,29.97,1920,1080,train\nP4vKV-G3hGE,7251,7541,190-146-1030-986,29.97,1920,1080,train\nP4vKV-G3hGE,7782,8012,208-67-1179-1038,29.97,1920,1080,train\nP4vKV-G3hGE,8735,8939,472-124-1397-1049,29.97,1920,1080,train\nP4vKV-G3hGE,8939,9583,200-172-1071-1043,29.97,1920,1080,train\nP4vKV-G3hGE,9707,9896,331-115-1149-933,29.97,1920,1080,train\nP4vKV-G3hGE,10209,10491,440-116-1296-972,29.97,1920,1080,train\nP4vKV-G3hGE,10529,10754,361-178-1168-985,29.97,1920,1080,train\nP4vKV-G3hGE,10953,11209,23-165-920-1062,29.97,1920,1080,train\nP4vKV-G3hGE,11209,11419,86-122-998-1034,29.97,1920,1080,train\nP4vKV-G3hGE,11505,11735,204-111-1154-1061,29.97,1920,1080,train\nP4vKV-G3hGE,11841,12014,337-119-1256-1038,29.97,1920,1080,train\nP4vKV-G3hGE,12014,12430,272-124-1220-1072,29.97,1920,1080,train\nP4vKV-G3hGE,12871,13029,253-103-1226-1076,29.97,1920,1080,train\nP4vKV-G3hGE,13615,13753,270-91-1256-1077,29.97,1920,1080,train\nP4vKV-G3hGE,13912,14056,199-96-1183-1080,29.97,1920,1080,train\nP4vKV-G3hGE,14659,14813,107-57-1119-1069,29.97,1920,1080,train\nP4vKV-G3hGE,15277,15599,133-17-1142-1026,29.97,1920,1080,train\nP4vKV-G3hGE,15744,15999,254-31-1234-1011,29.97,1920,1080,train\nP4vKV-G3hGE,16759,16906,114-48-955-889,29.97,1920,1080,train\nP4vKV-G3hGE,18069,18488,99-98-969-968,29.97,1920,1080,train\nP4vKV-G3hGE,19055,19352,253-139-1085-971,29.97,1920,1080,train\nP4vKV-G3hGE,19352,19586,177-183-965-971,29.97,1920,1080,train\nP4vKV-G3hGE,19890,20019,106-96-855-845,29.97,1920,1080,train\nP4vKV-G3hGE,20160,20364,422-68-1213-859,29.97,1920,1080,train\nP4vKV-G3hGE,20517,20810,423-165-1203-945,29.97,1920,1080,train\nP4vKV-G3hGE,20851,20984,373-84-1201-912,29.97,1920,1080,train\nP4vKV-G3hGE,21140,21382,117-63-949-895,29.97,1920,1080,train\nP4vKV-G3hGE,21722,21912,174-142-982-950,29.97,1920,1080,train\n8hLvlQrXI6U,7700,7984,132-38-546-452,29.97,640,480,test\n8hLvlQrXI6U,8247,8392,155-43-560-448,29.97,640,480,test\n8hLvlQrXI6U,8872,9001,97-24-536-463,29.97,640,480,test\nRrwo_EH5k30,0,348,524-251-1324-1051,29.97,1920,1080,train\nRrwo_EH5k30,348,1372,556-207-1406-1057,29.97,1920,1080,train\nRrwo_EH5k30,1372,2189,562-217-1388-1043,29.97,1920,1080,train\nRrwo_EH5k30,2203,2561,408-60-1418-1070,29.97,1920,1080,train\nRrwo_EH5k30,2622,3069,463-95-1432-1064,29.97,1920,1080,train\nRrwo_EH5k30,3069,3294,484-36-1510-1062,29.97,1920,1080,train\nRrwo_EH5k30,3423,4447,457-24-1499-1066,29.97,1920,1080,train\nRrwo_EH5k30,4508,5532,441-41-1469-1069,29.97,1920,1080,train\nRrwo_EH5k30,5708,6732,404-128-1343-1067,29.97,1920,1080,train\nRrwo_EH5k30,6732,7756,559-268-1339-1048,29.97,1920,1080,train\nc3ORapk0EH8,101,253,654-322-1241-909,25.0,1920,1080,train\nc3ORapk0EH8,388,747,386-317-1021-952,25.0,1920,1080,train\nc3ORapk0EH8,747,1031,393-262-1091-960,25.0,1920,1080,train\nc3ORapk0EH8,1073,1208,635-307-1293-965,25.0,1920,1080,train\nc3ORapk0EH8,1286,1488,646-234-1440-1028,25.0,1920,1080,train\nc3ORapk0EH8,1538,1784,864-252-1611-999,25.0,1920,1080,train\nc3ORapk0EH8,1869,2027,1152-302-1877-1027,25.0,1920,1080,train\nc3ORapk0EH8,2224,2546,718-300-1368-950,25.0,1920,1080,train\nc3ORapk0EH8,2717,2886,1055-369-1559-873,25.0,1920,1080,train\nc3ORapk0EH8,2886,3031,1132-355-1655-878,25.0,1920,1080,train\nc3ORapk0EH8,3066,3206,1059-371-1534-846,25.0,1920,1080,train\nc3ORapk0EH8,3228,3361,1007-371-1475-839,25.0,1920,1080,train\nc3ORapk0EH8,3565,3709,977-380-1445-848,25.0,1920,1080,train\nc3ORapk0EH8,4362,4568,572-244-1335-1007,25.0,1920,1080,train\nc3ORapk0EH8,4568,4707,416-301-1138-1023,25.0,1920,1080,train\nc3ORapk0EH8,4716,4958,491-196-1336-1041,25.0,1920,1080,train\nc3ORapk0EH8,7026,7156,609-116-1547-1054,25.0,1920,1080,train\nc3ORapk0EH8,10140,10328,258-89-1228-1059,25.0,1920,1080,train\nc3ORapk0EH8,10447,10713,688-237-1468-1017,25.0,1920,1080,train\nc3ORapk0EH8,10713,10856,775-200-1576-1001,25.0,1920,1080,train\nc3ORapk0EH8,10856,11314,617-252-1339-974,25.0,1920,1080,train\nc3ORapk0EH8,11314,11502,641-216-1402-977,25.0,1920,1080,train\nc3ORapk0EH8,11502,11764,802-260-1514-972,25.0,1920,1080,train\nc3ORapk0EH8,12636,12805,361-6-1424-1069,25.0,1920,1080,train\nc3ORapk0EH8,20720,20904,347-110-1183-946,25.0,1920,1080,train\nc3ORapk0EH8,20904,21110,606-159-1291-844,25.0,1920,1080,train\n5HNVxg4Vwzc,1629,1825,318-19-1013-714,29.97,1280,720,train\n5HNVxg4Vwzc,2312,2467,339-69-975-705,29.97,1280,720,train\n5HNVxg4Vwzc,3628,3817,314-49-978-713,29.97,1280,720,train\n5HNVxg4Vwzc,4936,5141,298-26-963-691,29.97,1280,720,train\n5HNVxg4Vwzc,7606,7739,417-95-944-622,29.97,1280,720,train\n5HNVxg4Vwzc,8400,8540,467-82-1022-637,29.97,1280,720,train\n5HNVxg4Vwzc,13192,13408,450-112-989-651,29.97,1280,720,train\n5HNVxg4Vwzc,13902,14081,428-95-1016-683,29.97,1280,720,train\n5HNVxg4Vwzc,14081,14349,453-66-1024-637,29.97,1280,720,train\n5HNVxg4Vwzc,17828,18041,388-41-1061-714,29.97,1280,720,train\n5HNVxg4Vwzc,18320,18615,261-11-955-705,29.97,1280,720,train\nPjpHBRjIjpo,359,1026,569-167-1419-1017,29.97,1920,1080,train\nPjpHBRjIjpo,1500,1679,853-180-1739-1066,29.97,1920,1080,train\nPjpHBRjIjpo,1730,2519,856-151-1783-1078,29.97,1920,1080,train\nPjpHBRjIjpo,2759,3318,851-216-1652-1017,29.97,1920,1080,train\nPjpHBRjIjpo,3318,3981,655-174-1467-986,29.97,1920,1080,train\nPjpHBRjIjpo,4199,4439,590-203-1406-1019,29.97,1920,1080,train\nPjpHBRjIjpo,5039,5212,574-153-1417-996,29.97,1920,1080,train\n4rv26XZJJsc,947,1131,80-64-447-431,25.0,640,480,train\n7KzG5fmhdRE,208,655,195-23-613-441,30.0,854,480,train\n7KzG5fmhdRE,655,1255,157-3-603-449,30.0,854,480,train\n7KzG5fmhdRE,1255,2075,135-29-579-473,30.0,854,480,train\n7KzG5fmhdRE,2075,2370,116-5-568-457,30.0,854,480,train\n7KzG5fmhdRE,2370,2781,84-27-534-477,30.0,854,480,train\n7KzG5fmhdRE,2781,2972,217-35-623-441,30.0,854,480,train\n7KzG5fmhdRE,2972,3461,214-16-635-437,30.0,854,480,train\n7KzG5fmhdRE,3461,4485,201-25-633-457,30.0,854,480,train\n7KzG5fmhdRE,4485,4898,204-37-612-445,30.0,854,480,train\n7KzG5fmhdRE,4898,5559,321-45-719-443,30.0,854,480,train\n7KzG5fmhdRE,5559,6212,367-26-789-448,30.0,854,480,train\n7KzG5fmhdRE,7236,7375,468-41-850-423,30.0,854,480,train\neR67awnEM2Q,0,551,941-315-1695-1069,30.0,1920,1080,train\neR67awnEM2Q,552,1125,996-339-1700-1043,30.0,1920,1080,train\neR67awnEM2Q,1125,1455,833-339-1547-1053,30.0,1920,1080,train\neR67awnEM2Q,1455,1768,1004-325-1717-1038,30.0,1920,1080,train\neR67awnEM2Q,1768,1964,800-352-1468-1020,30.0,1920,1080,train\neR67awnEM2Q,1964,2219,621-333-1319-1031,30.0,1920,1080,train\neR67awnEM2Q,2220,2390,530-343-1194-1007,30.0,1920,1080,train\neR67awnEM2Q,2390,2738,420-304-1135-1019,30.0,1920,1080,train\neR67awnEM2Q,2861,3017,444-288-1204-1048,30.0,1920,1080,train\neR67awnEM2Q,3017,3308,438-249-1234-1045,30.0,1920,1080,train\neR67awnEM2Q,3362,3659,523-317-1251-1045,30.0,1920,1080,train\neR67awnEM2Q,3713,3853,618-382-1277-1041,30.0,1920,1080,train\neR67awnEM2Q,3918,4070,555-262-1343-1050,30.0,1920,1080,train\neR67awnEM2Q,4281,4518,620-312-1370-1062,30.0,1920,1080,train\neR67awnEM2Q,4664,5329,330-290-1071-1031,30.0,1920,1080,train\neR67awnEM2Q,5466,5627,293-309-1014-1030,30.0,1920,1080,train\neR67awnEM2Q,5724,5872,319-295-1042-1018,30.0,1920,1080,train\neR67awnEM2Q,5985,6233,557-313-1290-1046,30.0,1920,1080,train\neR67awnEM2Q,6233,6436,729-323-1450-1044,30.0,1920,1080,train\neR67awnEM2Q,6497,6657,875-317-1614-1056,30.0,1920,1080,train\neR67awnEM2Q,6731,6923,690-309-1427-1046,30.0,1920,1080,train\neR67awnEM2Q,7368,7703,600-314-1320-1034,30.0,1920,1080,train\neR67awnEM2Q,7711,8132,551-189-1372-1010,30.0,1920,1080,train\neR67awnEM2Q,8144,8800,554-188-1374-1008,30.0,1920,1080,train\neR67awnEM2Q,8866,9143,946-335-1649-1038,30.0,1920,1080,train\neR67awnEM2Q,9245,9457,804-326-1521-1043,30.0,1920,1080,train\neR67awnEM2Q,9781,9973,963-306-1702-1045,30.0,1920,1080,train\neR67awnEM2Q,10377,10642,512-190-1387-1065,30.0,1920,1080,train\neR67awnEM2Q,10642,10838,830-328-1573-1071,30.0,1920,1080,train\neR67awnEM2Q,10838,11058,823-291-1600-1068,30.0,1920,1080,train\neR67awnEM2Q,11064,11557,760-190-1643-1073,30.0,1920,1080,train\nagjeMK0otQA,1570,2233,330-57-744-471,29.97,854,480,train\nagjeMK0otQA,2843,3867,298-46-726-474,29.97,854,480,train\nagjeMK0otQA,3867,4891,272-47-699-474,29.97,854,480,train\nagjeMK0otQA,4891,5341,282-45-696-459,29.97,854,480,train\nagjeMK0otQA,5381,5681,256-43-640-427,29.97,854,480,train\nagjeMK0otQA,5681,6235,295-25-702-432,29.97,854,480,train\nagjeMK0otQA,6235,6425,354-37-770-453,29.97,854,480,train\nagjeMK0otQA,6425,6654,351-60-764-473,29.97,854,480,train\nagjeMK0otQA,6654,7658,254-39-695-480,29.97,854,480,train\nagjeMK0otQA,7660,7885,261-56-634-429,29.97,854,480,train\nagjeMK0otQA,7885,8133,274-36-686-448,29.97,854,480,train\nagjeMK0otQA,8133,8350,339-60-746-467,29.97,854,480,train\nagjeMK0otQA,9042,9256,230-59-598-427,29.97,854,480,train\nagjeMK0otQA,9300,9576,210-40-607-437,29.97,854,480,train\nagjeMK0otQA,9576,9761,251-37-671-457,29.97,854,480,train\nagjeMK0otQA,9761,9961,277-57-697-477,29.97,854,480,train\nagjeMK0otQA,10698,10877,204-53-580-429,29.97,854,480,train\nagjeMK0otQA,10877,11400,166-33-566-433,29.97,854,480,train\nYqt573H689c,26,451,552-103-1389-940,29.97,1920,1080,train\nYqt573H689c,451,1475,527-120-1388-981,29.97,1920,1080,train\nYqt573H689c,1475,2499,558-114-1416-972,29.97,1920,1080,train\nYqt573H689c,2499,2748,390-118-1263-991,29.97,1920,1080,train\nYqt573H689c,2748,3053,632-127-1486-981,29.97,1920,1080,train\nYqt573H689c,3053,3505,510-181-1305-976,29.97,1920,1080,train\nYqt573H689c,3632,4437,368-93-1305-1030,29.97,1920,1080,train\nYqt573H689c,4437,4955,593-157-1422-986,29.97,1920,1080,train\nYqt573H689c,5076,5278,368-178-1213-1023,29.97,1920,1080,train\nYqt573H689c,5280,6000,441-139-1294-992,29.97,1920,1080,train\nYqt573H689c,6316,6655,569-139-1452-1022,29.97,1920,1080,train\nYqt573H689c,6655,7166,502-143-1378-1019,29.97,1920,1080,train\nYqt573H689c,7216,7770,295-143-1154-1002,29.97,1920,1080,train\nYqt573H689c,7770,8169,170-141-1037-1008,29.97,1920,1080,train\nYqt573H689c,8169,8931,285-99-1197-1011,29.97,1920,1080,train\nYqt573H689c,8932,9127,366-99-1253-986,29.97,1920,1080,train\nYqt573H689c,9249,9501,207-74-1166-1033,29.97,1920,1080,train\nYqt573H689c,9872,10034,635-107-1471-943,29.97,1920,1080,train\nYqt573H689c,10190,10701,454-92-1392-1030,29.97,1920,1080,train\nYqt573H689c,10809,10959,329-119-1262-1052,29.97,1920,1080,train\nYqt573H689c,10987,11199,369-37-1388-1056,29.97,1920,1080,train\nYqt573H689c,11954,12168,544-64-1528-1048,29.97,1920,1080,train\nYqt573H689c,12291,12578,317-59-1270-1012,29.97,1920,1080,train\nYqt573H689c,12651,12823,517-108-1442-1033,29.97,1920,1080,train\nYqt573H689c,12860,13884,745-81-1715-1051,29.97,1920,1080,train\nYqt573H689c,13884,14560,613-142-1474-1003,29.97,1920,1080,train\nYqt573H689c,14560,14973,470-90-1397-1017,29.97,1920,1080,train\nYqt573H689c,14973,15474,547-44-1549-1046,29.97,1920,1080,train\nYqt573H689c,15475,15624,845-72-1755-982,29.97,1920,1080,train\nYqt573H689c,15624,16648,759-77-1707-1025,29.97,1920,1080,train\nYqt573H689c,16720,17044,777-134-1595-952,29.97,1920,1080,train\nYqt573H689c,17044,17241,871-93-1714-936,29.97,1920,1080,train\nYqt573H689c,17241,17782,675-101-1488-914,29.97,1920,1080,train\nYqt573H689c,17827,17967,902-146-1624-868,29.97,1920,1080,train\nYqt573H689c,18096,18306,718-77-1563-922,29.97,1920,1080,train\nYqt573H689c,18306,18617,516-109-1358-951,29.97,1920,1080,train\nYqt573H689c,18617,19217,678-104-1565-991,29.97,1920,1080,train\nYqt573H689c,19217,19855,638-47-1581-990,29.97,1920,1080,train\nYqt573H689c,19865,20797,802-73-1701-972,29.97,1920,1080,train\n-p3QMYa_buo,150,938,81-5-537-461,29.97,640,480,train\n-p3QMYa_buo,1203,1654,110-18-539-447,29.97,640,480,train\n-p3QMYa_buo,1912,2095,120-24-547-451,29.97,640,480,train\n-p3QMYa_buo,2100,2289,141-30-567-456,29.97,640,480,train\n-p3QMYa_buo,2479,2808,127-14-568-455,29.97,640,480,train\n-p3QMYa_buo,3029,3329,129-18-569-458,29.97,640,480,train\n-p3QMYa_buo,3482,3819,120-33-537-450,29.97,640,480,train\n-p3QMYa_buo,4004,4138,106-30-530-454,29.97,640,480,train\n-p3QMYa_buo,4148,4302,134-26-569-461,29.97,640,480,train\n-p3QMYa_buo,4503,4832,119-30-544-455,29.97,640,480,train\n-p3QMYa_buo,5060,6084,110-27-538-455,29.97,640,480,train\n-p3QMYa_buo,6084,6735,85-40-503-458,29.97,640,480,train\n-p3QMYa_buo,6960,7340,135-25-563-453,29.97,640,480,train\n-p3QMYa_buo,7522,7686,142-34-558-450,29.97,640,480,train\n-p3QMYa_buo,7686,8423,114-41-543-470,29.97,640,480,train\n-p3QMYa_buo,9274,9472,146-38-574-466,29.97,640,480,train\n-p3QMYa_buo,9656,9945,137-25-569-457,29.97,640,480,train\n-p3QMYa_buo,10107,10466,111-39-532-460,29.97,640,480,train\n-p3QMYa_buo,10648,10799,96-0-530-434,29.97,640,480,train\n-p3QMYa_buo,10799,11285,95-12-537-454,29.97,640,480,train\n-p3QMYa_buo,11285,11772,78-27-526-475,29.97,640,480,train\nE93J3Gtrxhs,122,445,933-277-1711-1055,29.97,1920,1080,train\nE93J3Gtrxhs,593,744,917-283-1623-989,29.97,1920,1080,train\nE93J3Gtrxhs,1344,1780,935-236-1742-1043,29.97,1920,1080,train\nE93J3Gtrxhs,1979,2334,752-188-1622-1058,29.97,1920,1080,train\nE93J3Gtrxhs,2334,2594,944-247-1724-1027,29.97,1920,1080,train\nE93J3Gtrxhs,3390,3530,646-21-1585-960,29.97,1920,1080,train\nE93J3Gtrxhs,5189,5360,332-34-1310-1012,29.97,1920,1080,train\nE93J3Gtrxhs,5360,5537,324-141-1238-1055,29.97,1920,1080,train\nytT4iU7h-A8,1778,2049,93-28-1078-1013,29.97,1920,1080,train\nytT4iU7h-A8,2049,2389,309-80-1286-1057,29.97,1920,1080,train\nytT4iU7h-A8,2563,2880,70-43-1049-1022,29.97,1920,1080,train\nytT4iU7h-A8,2880,3044,71-116-891-936,29.97,1920,1080,train\nytT4iU7h-A8,3439,3635,206-70-1172-1036,29.97,1920,1080,train\nytT4iU7h-A8,3664,3887,245-24-1282-1061,29.97,1920,1080,train\nytT4iU7h-A8,3990,4119,383-21-1422-1060,29.97,1920,1080,train\nytT4iU7h-A8,4127,4291,215-78-1212-1075,29.97,1920,1080,train\nytT4iU7h-A8,4865,5048,397-27-1440-1070,29.97,1920,1080,train\nytT4iU7h-A8,6173,6517,424-8-1491-1075,29.97,1920,1080,train\nytT4iU7h-A8,6884,7149,407-125-1346-1064,29.97,1920,1080,train\nytT4iU7h-A8,10804,11024,262-47-1287-1072,29.97,1920,1080,train\nsjzfA4dYMfg,1769,2003,310-10-1014-714,25.0,1280,720,train\nsjzfA4dYMfg,2303,2447,283-15-982-714,25.0,1280,720,train\nMHWHMZ1N8rk,0,1024,133-50-470-387,30.0,640,480,train\nMHWHMZ1N8rk,1024,1191,140-48-475-383,30.0,640,480,train\nMHWHMZ1N8rk,1914,2938,138-48-474-384,30.0,640,480,train\nMHWHMZ1N8rk,2938,3962,133-42-475-384,30.0,640,480,train\nMHWHMZ1N8rk,3962,4666,142-49-475-382,30.0,640,480,train\nMHWHMZ1N8rk,4759,5246,149-54-477-382,30.0,640,480,train\nMHWHMZ1N8rk,5246,6153,124-37-473-386,30.0,640,480,train\nMHWHMZ1N8rk,6293,6513,131-47-467-383,30.0,640,480,train\nMHWHMZ1N8rk,7196,7434,131-36-480-385,30.0,640,480,train\nMHWHMZ1N8rk,7445,8469,133-42-475-384,30.0,640,480,train\nMHWHMZ1N8rk,8469,8848,137-40-476-379,30.0,640,480,train\nMHWHMZ1N8rk,8857,9562,138-33-487-382,30.0,640,480,train\ncEOS2zoyQw4,2285,2500,276-24-949-697,25.0,1280,720,train\ncEOS2zoyQw4,2587,2818,276-28-957-709,25.0,1280,720,train\ncEOS2zoyQw4,2831,2976,298-42-955-699,25.0,1280,720,train\ncEOS2zoyQw4,3492,3670,322-37-1000-715,25.0,1280,720,train\ncEOS2zoyQw4,3724,4006,327-17-1001-691,25.0,1280,720,train\ncEOS2zoyQw4,5678,6155,423-54-1087-718,25.0,1280,720,train\ncEOS2zoyQw4,7372,7525,320-42-978-700,25.0,1280,720,train\ncEOS2zoyQw4,7536,7742,308-21-1006-719,25.0,1280,720,train\ncEOS2zoyQw4,8918,9068,269-25-921-677,25.0,1280,720,train\ncEOS2zoyQw4,9648,10267,299-15-977-693,25.0,1280,720,train\ncEOS2zoyQw4,10820,11648,298-4-977-683,25.0,1280,720,train\ncEOS2zoyQw4,12796,13029,194-58-856-720,25.0,1280,720,train\ncEOS2zoyQw4,13575,13853,284-12-986-714,25.0,1280,720,train\ncEOS2zoyQw4,13965,14104,285-19-977-711,25.0,1280,720,train\ncEOS2zoyQw4,15149,15819,300-15-989-704,25.0,1280,720,train\ncEOS2zoyQw4,16021,16153,259-14-954-709,25.0,1280,720,train\njxAD7rOqDZs,323,483,320-80-817-577,29.97,1280,720,train\njxAD7rOqDZs,483,743,316-96-821-601,29.97,1280,720,train\njxAD7rOqDZs,961,1178,191-71-743-623,29.97,1280,720,train\njxAD7rOqDZs,1376,1661,121-152-598-629,29.97,1280,720,train\njxAD7rOqDZs,1705,1862,2-117-505-620,29.97,1280,720,train\njxAD7rOqDZs,2057,2234,253-128-748-623,29.97,1280,720,train\n58m6HTXpBz8,1172,1382,576-137-1364-925,25.0,1920,1080,train\n58m6HTXpBz8,1552,1772,508-128-1331-951,25.0,1920,1080,train\n58m6HTXpBz8,2203,2352,873-37-1721-885,25.0,1920,1080,train\naOk2Diz9C9g,3328,3464,139-48-486-395,25.0,640,480,train\nZBVzUnF9eXU,31,658,157-99-505-447,30.0,640,480,train\nZBVzUnF9eXU,678,889,161-125-496-460,30.0,640,480,train\nZBVzUnF9eXU,955,1200,114-69-517-472,30.0,640,480,train\nZBVzUnF9eXU,1397,1610,104-156-396-448,30.0,640,480,train\nZBVzUnF9eXU,1803,2097,68-120-399-451,30.0,640,480,train\nbXz9ZSVlSKo,149,484,160-96-514-450,25.0,600,480,train\nbXz9ZSVlSKo,789,1596,149-82-519-452,25.0,600,480,train\nbXz9ZSVlSKo,1607,1761,140-44-552-456,25.0,600,480,train\nbXz9ZSVlSKo,2458,2612,165-107-508-450,25.0,600,480,train\nbXz9ZSVlSKo,2824,2986,168-113-506-451,25.0,600,480,train\nbXz9ZSVlSKo,2986,3118,159-96-513-450,25.0,600,480,train\nbXz9ZSVlSKo,3268,3578,157-93-516-452,25.0,600,480,train\nbXz9ZSVlSKo,3793,4046,158-93-516-451,25.0,600,480,train\nbXz9ZSVlSKo,4169,5047,141-58-538-455,25.0,600,480,train\nbXz9ZSVlSKo,5047,5254,137-35-561-459,25.0,600,480,train\nbXz9ZSVlSKo,5322,5477,155-85-521-451,25.0,600,480,train\nbXz9ZSVlSKo,5995,6214,155-89-518-452,25.0,600,480,train\nbXz9ZSVlSKo,6315,6591,166-110-509-453,25.0,600,480,train\nbXz9ZSVlSKo,6819,7523,159-95-516-452,25.0,600,480,train\nbXz9ZSVlSKo,7530,8444,139-55-540-456,25.0,600,480,train\nbXz9ZSVlSKo,8444,8973,127-30-561-464,25.0,600,480,train\nbXz9ZSVlSKo,9083,9241,167-110-504-447,25.0,600,480,train\nbXz9ZSVlSKo,9241,10265,150-87-521-458,25.0,600,480,train\nbXz9ZSVlSKo,10265,10536,161-95-515-449,25.0,600,480,train\n5dsMA7KF_b0,150,1095,510-144-1245-879,29.97,1920,1080,train\n5dsMA7KF_b0,1297,1490,922-217-1549-844,29.97,1920,1080,train\n5dsMA7KF_b0,1758,2065,832-212-1476-856,29.97,1920,1080,train\n5dsMA7KF_b0,2479,2648,987-324-1525-862,29.97,1920,1080,train\n5dsMA7KF_b0,2712,2928,944-305-1504-865,29.97,1920,1080,train\n5dsMA7KF_b0,3152,3338,706-298-1295-887,29.97,1920,1080,train\n5dsMA7KF_b0,3890,4052,779-236-1385-842,29.97,1920,1080,train\n5dsMA7KF_b0,4646,4972,773-221-1368-816,29.97,1920,1080,train\n5dsMA7KF_b0,5095,5246,796-235-1372-811,29.97,1920,1080,train\n5dsMA7KF_b0,5306,5472,793-207-1405-819,29.97,1920,1080,train\n5dsMA7KF_b0,6092,6255,978-316-1535-873,29.97,1920,1080,train\n5dsMA7KF_b0,6368,6561,1026-306-1587-867,29.97,1920,1080,train\n5dsMA7KF_b0,6561,6739,1101-359-1634-892,29.97,1920,1080,train\n5dsMA7KF_b0,7949,8091,278-176-951-849,29.97,1920,1080,train\n5dsMA7KF_b0,8632,8819,531-178-1231-878,29.97,1920,1080,train\n5dsMA7KF_b0,8920,9234,836-194-1513-871,29.97,1920,1080,train\n5dsMA7KF_b0,9347,9648,782-175-1489-882,29.97,1920,1080,train\n5dsMA7KF_b0,9648,9940,736-139-1479-882,29.97,1920,1080,train\n8xSkbMUpegs,1680,1920,322-89-923-690,29.97,1280,720,train\n8xSkbMUpegs,2185,2400,221-75-866-720,29.97,1280,720,train\n8xSkbMUpegs,2926,3144,294-14-946-666,29.97,1280,720,train\n8xSkbMUpegs,3160,3323,414-78-998-662,29.97,1280,720,train\n8xSkbMUpegs,3476,3697,330-56-946-672,29.97,1280,720,train\n8xSkbMUpegs,3840,4000,475-90-1015-630,29.97,1280,720,train\n8xSkbMUpegs,4406,4565,671-106-1149-584,29.97,1280,720,train\n8xSkbMUpegs,4665,4800,620-10-1151-541,29.97,1280,720,train\n8xSkbMUpegs,5365,5640,516-89-1017-590,29.97,1280,720,train\n8xSkbMUpegs,8569,8907,254-32-868-646,29.97,1280,720,train\n8xSkbMUpegs,9625,9880,393-65-983-655,29.97,1280,720,train\n8xSkbMUpegs,11849,12000,383-70-988-675,29.97,1280,720,train\naJjr_OD8M4A,17249,18273,487-168-1397-1078,29.97,1920,1080,train\nA-0smsWdrog,0,480,569-143-1343-917,30.0,1920,1080,train\nA-0smsWdrog,1500,1679,857-45-1658-846,30.0,1920,1080,train\nA-0smsWdrog,2998,3130,706-107-1468-869,30.0,1920,1080,train\nA-0smsWdrog,4667,4854,485-97-1399-1011,30.0,1920,1080,train\nA-0smsWdrog,5370,5700,370-106-1287-1023,30.0,1920,1080,train\nA-0smsWdrog,6405,6555,266-162-1023-919,30.0,1920,1080,train\nA-0smsWdrog,6922,7079,646-135-1439-928,30.0,1920,1080,train\nA-0smsWdrog,7980,8162,448-31-1443-1026,30.0,1920,1080,train\nA-0smsWdrog,10538,10674,172-129-960-917,30.0,1920,1080,train\nA-0smsWdrog,11346,11477,595-223-1293-921,30.0,1920,1080,train\nw2awOCDRtrc,1729,2009,120-40-509-429,25.0,640,480,test\nw2awOCDRtrc,3059,3190,139-32-540-433,25.0,640,480,test\nsSNvvVqnd_8,46,262,75-79-458-462,25.0,640,480,train\nsSNvvVqnd_8,1286,2310,130-77-518-465,25.0,640,480,train\nsSNvvVqnd_8,2397,3014,195-71-587-463,25.0,640,480,train\nsSNvvVqnd_8,3099,3708,102-79-491-468,25.0,640,480,train\nsSNvvVqnd_8,3708,4423,202-96-565-459,25.0,640,480,train\nsSNvvVqnd_8,4423,5042,144-72-527-455,25.0,640,480,train\nsSNvvVqnd_8,5208,5376,194-91-548-445,25.0,640,480,train\nsSNvvVqnd_8,5376,5577,182-89-547-454,25.0,640,480,train\nsSNvvVqnd_8,5700,6078,139-84-501-446,25.0,640,480,train\nsSNvvVqnd_8,6188,6990,119-87-494-462,25.0,640,480,train\nsSNvvVqnd_8,7131,7297,99-49-527-477,25.0,640,480,train\nsSNvvVqnd_8,7297,8321,93-78-488-473,25.0,640,480,train\nsSNvvVqnd_8,8321,8851,95-93-461-459,25.0,640,480,train\nsSNvvVqnd_8,8863,9145,165-89-543-467,25.0,640,480,train\nsSNvvVqnd_8,9704,9982,194-70-599-475,25.0,640,480,train\nsSNvvVqnd_8,9982,10197,105-105-461-461,25.0,640,480,train\nsSNvvVqnd_8,10197,10363,63-87-431-455,25.0,640,480,train\nsSNvvVqnd_8,10363,10503,164-96-537-469,25.0,640,480,train\nsSNvvVqnd_8,10503,10878,185-95-552-462,25.0,640,480,train\nAYrUqlwE6n8,0,1024,372-66-999-693,29.97,1280,720,train\nAYrUqlwE6n8,1024,2048,354-71-981-698,29.97,1280,720,train\nAYrUqlwE6n8,2069,3093,458-125-901-568,29.97,1280,720,train\nAYrUqlwE6n8,3093,4117,464-126-903-565,29.97,1280,720,train\nAYrUqlwE6n8,4117,5141,375-136-801-562,29.97,1280,720,train\nAYrUqlwE6n8,5141,6165,439-138-869-568,29.97,1280,720,train\nAYrUqlwE6n8,6165,6328,459-144-898-583,29.97,1280,720,train\nAYrUqlwE6n8,6328,6814,510-149-965-604,29.97,1280,720,train\nAYrUqlwE6n8,6814,7800,423-138-908-623,29.97,1280,720,train\nAYrUqlwE6n8,7800,7965,285-132-800-647,29.97,1280,720,train\nAYrUqlwE6n8,7965,8449,366-130-900-664,29.97,1280,720,train\nAYrUqlwE6n8,8662,8951,352-94-919-661,29.97,1280,720,train\nAYrUqlwE6n8,8985,9166,424-110-892-578,29.97,1280,720,train\nAYrUqlwE6n8,9166,10190,443-111-933-601,29.97,1280,720,train\nAYrUqlwE6n8,10190,10622,499-144-961-606,29.97,1280,720,train\nAYrUqlwE6n8,10677,11366,285-104-836-655,29.97,1280,720,train\nAYrUqlwE6n8,11573,12431,401-113-934-646,29.97,1280,720,train\nAYrUqlwE6n8,12487,13329,423-112-925-614,29.97,1280,720,train\nAYrUqlwE6n8,13329,13960,433-123-947-637,29.97,1280,720,train\nAYrUqlwE6n8,14060,14200,278-124-803-649,29.97,1280,720,train\nAYrUqlwE6n8,14200,14467,384-139-886-641,29.97,1280,720,train\nAYrUqlwE6n8,14531,15555,331-99-893-661,29.97,1280,720,train\nAYrUqlwE6n8,15555,16177,433-134-963-664,29.97,1280,720,train\nAYrUqlwE6n8,16218,16904,409-124-946-661,29.97,1280,720,train\nAYrUqlwE6n8,16904,17928,411-97-981-667,29.97,1280,720,train\nAYrUqlwE6n8,17928,18468,371-102-910-641,29.97,1280,720,train\nAYrUqlwE6n8,18470,19494,466-118-915-567,29.97,1280,720,train\nAYrUqlwE6n8,19494,20243,386-146-817-577,29.97,1280,720,train\nAYrUqlwE6n8,20243,20397,436-158-875-597,29.97,1280,720,train\nAYrUqlwE6n8,20425,20884,496-100-1004-608,29.97,1280,720,train\nAYrUqlwE6n8,20936,21373,444-133-953-642,29.97,1280,720,train\nAYrUqlwE6n8,21564,22588,386-115-959-688,29.97,1280,720,train\nAYrUqlwE6n8,22667,23691,372-137-875-640,29.97,1280,720,train\nAYrUqlwE6n8,23691,23952,344-128-871-655,29.97,1280,720,train\nAYrUqlwE6n8,23952,24976,360-96-906-642,29.97,1280,720,train\nAYrUqlwE6n8,24976,25214,398-146-872-620,29.97,1280,720,train\nAYrUqlwE6n8,25405,25694,388-126-936-674,29.97,1280,720,train\nAYrUqlwE6n8,26008,26995,355-70-971-686,29.97,1280,720,train\nKrsQLNWK9Jc,1022,1224,508-135-1074-701,22.0,1280,720,train\nKrsQLNWK9Jc,1422,1572,582-140-1132-690,22.0,1280,720,train\nKrsQLNWK9Jc,1572,1747,504-146-1045-687,22.0,1280,720,train\nKrsQLNWK9Jc,1747,1963,353-151-906-704,22.0,1280,720,train\nKrsQLNWK9Jc,1963,2106,232-156-775-699,22.0,1280,720,train\nKrsQLNWK9Jc,2243,2493,208-144-765-701,22.0,1280,720,train\nKrsQLNWK9Jc,2864,3057,362-128-927-693,22.0,1280,720,train\nKrsQLNWK9Jc,3057,3240,482-138-1025-681,22.0,1280,720,train\nKrsQLNWK9Jc,3258,3455,329-109-903-683,22.0,1280,720,train\nKrsQLNWK9Jc,4401,4669,379-153-939-713,22.0,1280,720,train\nKrsQLNWK9Jc,4769,5021,321-103-918-700,22.0,1280,720,train\nItJsAxi-vME,5870,6028,239-172-636-569,29.97,1280,720,train\nItJsAxi-vME,7041,7281,375-161-769-555,29.97,1280,720,train\nItJsAxi-vME,8469,8631,703-135-1002-434,29.97,1280,720,train\nItJsAxi-vME,9463,9608,352-41-814-503,29.97,1280,720,train\nItJsAxi-vME,9764,9911,228-64-637-473,29.97,1280,720,train\nItJsAxi-vME,10068,10212,149-91-661-603,29.97,1280,720,train\nItJsAxi-vME,10709,10923,90-161-585-656,29.97,1280,720,train\nItJsAxi-vME,11152,11322,159-157-613-611,29.97,1280,720,train\nItJsAxi-vME,11975,12127,261-126-728-593,29.97,1280,720,train\nItJsAxi-vME,13625,13900,38-72-592-626,29.97,1280,720,train\nItJsAxi-vME,14683,14828,137-133-557-553,29.97,1280,720,train\nItJsAxi-vME,15953,16769,638-139-1160-661,29.97,1280,720,train\nItJsAxi-vME,17286,17440,616-147-1049-580,29.97,1280,720,train\nItJsAxi-vME,18233,18396,178-162-657-641,29.97,1280,720,train\nItJsAxi-vME,19329,19556,315-180-806-671,29.97,1280,720,train\nItJsAxi-vME,19847,20146,370-144-910-684,29.97,1280,720,train\nItJsAxi-vME,20251,20435,571-124-1094-647,29.97,1280,720,train\nItJsAxi-vME,21527,21664,634-153-1036-555,29.97,1280,720,train\nItJsAxi-vME,24016,24192,386-138-888-640,29.97,1280,720,train\nItJsAxi-vME,25569,25723,569-200-894-525,29.97,1280,720,train\nItJsAxi-vME,25924,26119,670-182-1021-533,29.97,1280,720,train\nItJsAxi-vME,26119,26272,605-163-986-544,29.97,1280,720,train\nDdscFyAZurI,20,380,125-127-400-402,25.0,640,480,train\nDdscFyAZurI,500,648,152-142-459-449,25.0,640,480,train\nDdscFyAZurI,648,864,175-175-452-452,25.0,640,480,train\nDdscFyAZurI,1999,2159,144-59-550-465,25.0,640,480,train\nDdscFyAZurI,4384,4536,196-71-582-457,25.0,640,480,train\nDdscFyAZurI,4627,5001,280-106-600-426,25.0,640,480,train\nDdscFyAZurI,5004,5184,262-99-581-418,25.0,640,480,train\nDdscFyAZurI,5499,5663,153-88-534-469,25.0,640,480,train\nO3aNcFLu-98,6102,6322,244-25-770-551,29.97,1280,720,train\nO3aNcFLu-98,8088,8228,169-98-696-625,29.97,1280,720,train\nO3aNcFLu-98,9710,9877,159-115-616-572,29.97,1280,720,train\nO3aNcFLu-98,10465,10632,607-45-1173-611,29.97,1280,720,train\nO3aNcFLu-98,11283,11453,127-71-652-596,29.97,1280,720,train\nO3aNcFLu-98,11654,11905,161-102-662-603,29.97,1280,720,train\nO3aNcFLu-98,12747,12888,349-44-904-599,29.97,1280,720,train\nWvpZGirYxi0,299,894,394-217-1161-984,24.0,1920,1080,train\nWvpZGirYxi0,957,1087,120-208-897-985,24.0,1920,1080,train\nWvpZGirYxi0,1122,1589,285-222-1139-1076,24.0,1920,1080,train\nWvpZGirYxi0,1615,2185,94-199-886-991,24.0,1920,1080,train\nWvpZGirYxi0,2258,2808,289-166-1152-1029,24.0,1920,1080,train\nWvpZGirYxi0,2869,3043,633-231-1402-1000,24.0,1920,1080,train\nWvpZGirYxi0,3273,3460,1047-180-1862-995,24.0,1920,1080,train\nWvpZGirYxi0,3607,3803,1034-126-1889-981,24.0,1920,1080,train\nzHsLRAPJkMM,0,200,826-534-1324-1032,29.97,1920,1080,train\nzHsLRAPJkMM,322,617,832-543-1326-1037,29.97,1920,1080,train\nzHsLRAPJkMM,5037,5166,992-497-1573-1078,29.97,1920,1080,train\nzHsLRAPJkMM,5442,5645,1008-477-1609-1078,29.97,1920,1080,train\nzHsLRAPJkMM,6089,6218,959-466-1490-997,29.97,1920,1080,train\nzHsLRAPJkMM,8064,8382,696-172-1569-1045,29.97,1920,1080,train\nzHsLRAPJkMM,8638,8853,601-337-1199-935,29.97,1920,1080,train\nzHsLRAPJkMM,10071,10220,826-496-1377-1047,29.97,1920,1080,train\nzHsLRAPJkMM,10896,11027,905-511-1417-1023,29.97,1920,1080,train\nzHsLRAPJkMM,12402,12685,939-445-1509-1015,29.97,1920,1080,train\nzHsLRAPJkMM,14839,14978,603-468-1081-946,29.97,1920,1080,train\nzHsLRAPJkMM,17023,17198,471-536-997-1062,29.97,1920,1080,train\nzHsLRAPJkMM,17754,17912,158-463-723-1028,29.97,1920,1080,train\nzHsLRAPJkMM,19418,19631,486-520-1003-1037,29.97,1920,1080,train\nzHsLRAPJkMM,20948,21279,664-371-1366-1073,29.97,1920,1080,train\nzHsLRAPJkMM,22932,23113,1082-460-1673-1051,29.97,1920,1080,train\nzHsLRAPJkMM,23113,23307,1032-518-1559-1045,29.97,1920,1080,train\nzHsLRAPJkMM,23519,23658,617-451-1243-1077,29.97,1920,1080,train\nzHsLRAPJkMM,25274,25419,847-466-1411-1030,29.97,1920,1080,train\nzHsLRAPJkMM,25581,25755,708-512-1236-1040,29.97,1920,1080,train\nzHsLRAPJkMM,25880,26011,870-474-1476-1080,29.97,1920,1080,train\nzHsLRAPJkMM,26291,26430,787-546-1258-1017,29.97,1920,1080,train\nzHsLRAPJkMM,26438,26583,832-506-1317-991,29.97,1920,1080,train\nzHsLRAPJkMM,26846,27055,1108-477-1544-913,29.97,1920,1080,train\nl_faFvmpDrM,366,725,377-35-1044-702,30.0,1280,720,train\nxMYVjC4Ip3I,433,1457,156-84-484-412,25.0,640,480,train\nxMYVjC4Ip3I,1476,2500,163-89-480-406,25.0,640,480,train\nxMYVjC4Ip3I,4829,5142,190-121-469-400,25.0,640,480,train\nxMYVjC4Ip3I,5208,5373,182-97-487-402,25.0,640,480,train\nxMYVjC4Ip3I,5477,6501,153-65-493-405,25.0,640,480,train\nxMYVjC4Ip3I,6501,6931,180-109-474-403,25.0,640,480,train\nxMYVjC4Ip3I,6931,7125,184-95-492-403,25.0,640,480,train\nxMYVjC4Ip3I,7125,7294,158-78-490-410,25.0,640,480,train\nxMYVjC4Ip3I,7294,8318,156-62-496-402,25.0,640,480,train\nxMYVjC4Ip3I,8318,8973,168-78-493-403,25.0,640,480,train\n42P58QDIgno,87,603,310-119-827-636,25.0,1280,720,train\n42P58QDIgno,908,1041,244-153-778-687,25.0,1280,720,train\n42P58QDIgno,1042,1187,231-87-826-682,25.0,1280,720,train\n42P58QDIgno,1614,1758,330-111-896-677,25.0,1280,720,train\n42P58QDIgno,1808,2164,395-94-950-649,25.0,1280,720,train\n42P58QDIgno,2364,2529,442-142-912-612,25.0,1280,720,train\n42P58QDIgno,2529,2772,468-198-903-633,25.0,1280,720,train\n42P58QDIgno,3174,3372,409-145-942-678,25.0,1280,720,train\n42P58QDIgno,3372,3564,469-115-1038-684,25.0,1280,720,train\n42P58QDIgno,4120,4262,186-74-817-705,25.0,1280,720,train\n42P58QDIgno,5174,5345,341-112-905-676,25.0,1280,720,train\n42P58QDIgno,5791,5925,330-92-923-685,25.0,1280,720,train\n42P58QDIgno,6079,6215,436-108-986-658,25.0,1280,720,train\n42P58QDIgno,8471,8646,390-79-1017-706,25.0,1280,720,train\n42P58QDIgno,8690,9030,220-15-919-714,25.0,1280,720,train\nuCR05ckHiFE,72,1096,719-202-1367-850,29.97,1920,1080,train\nuCR05ckHiFE,1275,1916,790-238-1328-776,29.97,1920,1080,train\nuCR05ckHiFE,2238,2734,699-216-1274-791,29.97,1920,1080,train\nuCR05ckHiFE,2897,3045,673-208-1290-825,29.97,1920,1080,train\nuCR05ckHiFE,3267,3428,796-213-1355-772,29.97,1920,1080,train\nuCR05ckHiFE,4254,4432,616-209-1198-791,29.97,1920,1080,train\nuCR05ckHiFE,4432,4651,638-223-1233-818,29.97,1920,1080,train\nuCR05ckHiFE,4659,4842,669-152-1371-854,29.97,1920,1080,train\nuCR05ckHiFE,5001,5163,703-207-1380-884,29.97,1920,1080,train\nuCR05ckHiFE,5204,5333,681-186-1330-835,29.97,1920,1080,train\nuCR05ckHiFE,5606,5751,687-251-1307-871,29.97,1920,1080,train\nuCR05ckHiFE,5828,5990,784-227-1365-808,29.97,1920,1080,train\nuCR05ckHiFE,6206,6474,768-318-1327-877,29.97,1920,1080,train\nuCR05ckHiFE,6906,7176,614-267-1301-954,29.97,1920,1080,train\n_64NZbqcISg,0,199,141-101-426-386,25.0,640,480,train\ncgcuo2lfdEc,0,163,270-151-780-661,29.97,1280,720,train\ncgcuo2lfdEc,163,328,282-123-823-664,29.97,1280,720,train\ncgcuo2lfdEc,360,500,236-65-822-651,29.97,1280,720,train\ncgcuo2lfdEc,500,733,215-32-818-635,29.97,1280,720,train\ncgcuo2lfdEc,774,1020,185-138-733-686,29.97,1280,720,train\ncgcuo2lfdEc,1103,1363,295-141-833-679,29.97,1280,720,train\ncgcuo2lfdEc,1363,1888,292-115-833-656,29.97,1280,720,train\ncgcuo2lfdEc,1978,2250,225-22-876-673,29.97,1280,720,train\ncgcuo2lfdEc,2501,2672,407-171-911-675,29.97,1280,720,train\ncgcuo2lfdEc,2738,2890,354-114-924-684,29.97,1280,720,train\nqBdCNti65Wc,1422,1929,97-43-528-474,29.97,640,480,train\nqBdCNti65Wc,1929,2250,122-22-568-468,29.97,640,480,train\nqBdCNti65Wc,2432,2700,70-15-527-472,29.97,640,480,train\nqBdCNti65Wc,3119,3358,104-34-541-471,29.97,640,480,train\nqBdCNti65Wc,3360,3536,108-68-511-471,29.97,640,480,train\nqBdCNti65Wc,3895,4063,108-79-497-468,29.97,640,480,train\nqBdCNti65Wc,5096,5385,104-57-512-465,29.97,640,480,train\nqBdCNti65Wc,5385,6409,93-36-519-462,29.97,640,480,train\nqBdCNti65Wc,6409,6778,111-85-489-463,29.97,640,480,train\nqBdCNti65Wc,6877,7363,103-77-485-459,29.97,640,480,train\nqBdCNti65Wc,7521,8545,110-48-528-466,29.97,640,480,train\nqBdCNti65Wc,8667,9016,76-12-524-460,29.97,640,480,train\nn1ic2Kxv0lo,600,750,115-71-522-478,30.0,640,480,train\nn1ic2Kxv0lo,1650,1800,162-80-528-446,30.0,640,480,train\nn1ic2Kxv0lo,1950,2100,178-82-548-452,30.0,640,480,train\nn1ic2Kxv0lo,2400,2550,155-89-541-475,30.0,640,480,train\nn1ic2Kxv0lo,2700,2850,155-85-534-464,30.0,640,480,train\nn1ic2Kxv0lo,3450,3600,145-26-560-441,30.0,640,480,train\nn1ic2Kxv0lo,3794,4050,131-37-560-466,30.0,640,480,train\nn1ic2Kxv0lo,4502,4650,129-35-571-477,30.0,640,480,train\nn1ic2Kxv0lo,4650,4800,103-28-537-462,30.0,640,480,train\nn1ic2Kxv0lo,4848,5019,91-1-555-465,30.0,640,480,train\nn1ic2Kxv0lo,5400,5597,121-27-569-475,30.0,640,480,train\nn1ic2Kxv0lo,7820,7972,122-36-544-458,30.0,640,480,train\nn1ic2Kxv0lo,8408,8550,131-66-536-471,30.0,640,480,train\nn1ic2Kxv0lo,8700,9150,97-23-546-472,30.0,640,480,train\nLfBbfOEVV3c,29,282,626-411-1153-938,25.0,1920,1080,train\nLfBbfOEVV3c,593,746,530-399-1121-990,25.0,1920,1080,train\nLfBbfOEVV3c,841,1175,616-431-1162-977,25.0,1920,1080,train\nLfBbfOEVV3c,3916,4071,618-474-1138-994,25.0,1920,1080,train\nLfBbfOEVV3c,4275,4429,624-482-1106-964,25.0,1920,1080,train\nHOsiZya4deQ,3227,3396,98-1-559-462,25.0,640,480,train\nHOsiZya4deQ,8561,8691,84-1-562-479,25.0,640,480,train\nHOsiZya4deQ,8796,8924,96-5-543-452,25.0,640,480,train\ne4VIw41R-PU,274,680,364-50-972-658,29.97,1280,720,train\ne4VIw41R-PU,905,1121,330-93-946-709,29.97,1280,720,train\ne4VIw41R-PU,1121,1433,267-57-887-677,29.97,1280,720,train\ne4VIw41R-PU,1819,1969,225-64-867-706,29.97,1280,720,train\ne4VIw41R-PU,2127,2262,155-78-794-717,29.97,1280,720,train\ne4VIw41R-PU,2262,2508,282-49-897-664,29.97,1280,720,train\ne4VIw41R-PU,2508,2701,209-101-807-699,29.97,1280,720,train\ne4VIw41R-PU,2987,3140,203-55-834-686,29.97,1280,720,train\ne4VIw41R-PU,5155,5286,364-69-962-667,29.97,1280,720,train\ne4VIw41R-PU,5499,6211,355-50-1000-695,29.97,1280,720,train\ne4VIw41R-PU,6225,6474,239-79-815-655,29.97,1280,720,train\ne4VIw41R-PU,6602,7020,11-20-632-641,29.97,1280,720,train\ne4VIw41R-PU,7194,7385,40-17-625-602,29.97,1280,720,train\ne4VIw41R-PU,8660,8877,348-47-1004-703,29.97,1280,720,train\ne4VIw41R-PU,9338,9537,302-102-854-654,29.97,1280,720,train\ne4VIw41R-PU,9537,9785,390-127-921-658,29.97,1280,720,train\ne4VIw41R-PU,9785,10060,477-118-1017-658,29.97,1280,720,train\ne4VIw41R-PU,10085,10243,347-63-935-651,29.97,1280,720,train\nj_UJ-M6KnLA,576,762,115-41-521-447,30.0,640,480,train\nj_UJ-M6KnLA,1602,1755,85-56-481-452,30.0,640,480,train\nj_UJ-M6KnLA,1779,1995,143-58-530-445,30.0,640,480,train\nj_UJ-M6KnLA,2897,3026,183-40-590-447,30.0,640,480,train\nj_UJ-M6KnLA,3273,3434,118-56-505-443,30.0,640,480,train\nj_UJ-M6KnLA,3994,4201,149-84-500-435,30.0,640,480,train\nj_UJ-M6KnLA,4647,4805,189-96-538-445,30.0,640,480,train\nj_UJ-M6KnLA,9125,9276,122-90-455-423,30.0,640,480,train\nj_UJ-M6KnLA,12123,12348,192-80-529-417,30.0,640,480,train\nj_UJ-M6KnLA,12706,12892,167-87-507-427,30.0,640,480,train\nuXjfq4otSPg,108,318,102-59-492-449,29.97,640,480,train\nZ3pAsUWV5d8,669,1049,137-64-520-447,29.97,720,480,train\nZ3pAsUWV5d8,1049,1215,86-54-473-441,29.97,720,480,train\nZ3pAsUWV5d8,1215,1400,178-69-565-456,29.97,720,480,train\nZ3pAsUWV5d8,1400,1738,129-48-536-455,29.97,720,480,train\nZ3pAsUWV5d8,1738,2240,126-25-568-467,29.97,720,480,train\nZ3pAsUWV5d8,2240,2403,180-68-571-459,29.97,720,480,train\nZ3pAsUWV5d8,2403,2790,202-46-605-449,29.97,720,480,train\nZ3pAsUWV5d8,3118,4142,115-50-528-463,29.97,720,480,train\nZ3pAsUWV5d8,4142,4281,178-56-570-448,29.97,720,480,train\nZ3pAsUWV5d8,4281,4414,185-35-607-457,29.97,720,480,train\nkgx5w20u0k4,385,957,362-96-983-717,25.0,1280,720,train\nkgx5w20u0k4,957,1204,324-99-943-718,25.0,1280,720,train\nkgx5w20u0k4,1803,2117,338-92-962-716,25.0,1280,720,train\nkgx5w20u0k4,3594,3778,346-95-954-703,25.0,1280,720,train\nZAycgaoKipI,107,496,152-9-623-480,30.0,640,480,train\nZAycgaoKipI,3778,3967,206-41-637-472,30.0,640,480,train\nZAycgaoKipI,5284,5413,62-63-478-479,30.0,640,480,train\nm4ccN_yYKlA,3039,3220,396-112-990-706,29.97,1280,720,train\nm4ccN_yYKlA,6281,7305,338-30-1021-713,29.97,1280,720,train\nm4ccN_yYKlA,7393,8417,339-22-1027-710,29.97,1280,720,train\nm4ccN_yYKlA,8417,9143,347-18-1041-712,29.97,1280,720,train\nm4ccN_yYKlA,9143,9753,416-25-1107-716,29.97,1280,720,train\nm4ccN_yYKlA,12409,13433,326-16-1028-718,29.97,1280,720,train\nm4ccN_yYKlA,13433,13814,316-13-1015-712,29.97,1280,720,train\nm4ccN_yYKlA,13860,14884,316-31-999-714,29.97,1280,720,train\nm4ccN_yYKlA,15047,15483,246-30-932-716,29.97,1280,720,train\nm4ccN_yYKlA,15528,16552,331-29-1010-708,29.97,1280,720,train\nm4ccN_yYKlA,16552,17524,375-57-1016-698,29.97,1280,720,train\nm4ccN_yYKlA,17524,18548,328-24-1013-709,29.97,1280,720,train\nm4ccN_yYKlA,18548,18718,376-98-980-702,29.97,1280,720,train\nm4ccN_yYKlA,18743,19202,353-32-1030-709,29.97,1280,720,train\nKYdyIdusD0g,426,876,150-70-541-461,25.0,640,480,train\nKYdyIdusD0g,876,1641,143-69-535-461,25.0,640,480,train\nKYdyIdusD0g,2665,3001,77-56-497-476,25.0,640,480,train\nKYdyIdusD0g,3126,3282,145-83-518-456,25.0,640,480,train\nKYdyIdusD0g,3322,3841,109-64-509-464,25.0,640,480,train\nKYdyIdusD0g,3925,4124,213-65-618-470,25.0,640,480,train\nKYdyIdusD0g,4124,4626,109-53-523-467,25.0,640,480,train\nKYdyIdusD0g,4728,4931,223-45-629-451,25.0,640,480,train\nKYdyIdusD0g,4931,5402,224-49-610-435,25.0,640,480,train\nKYdyIdusD0g,5530,5676,172-35-567-430,25.0,640,480,train\nkgFEyCiX1To,0,1024,76-41-505-470,29.97,640,480,train\nkgFEyCiX1To,1094,1238,59-45-494-480,29.97,640,480,train\nkgFEyCiX1To,6720,7041,86-11-523-448,29.97,640,480,train\nkgFEyCiX1To,8330,8458,107-0-574-467,29.97,640,480,train\nkgFEyCiX1To,9911,10056,134-51-548-465,29.97,640,480,train\n-nRYJnnnTuk,523,688,744-292-1364-912,29.97,1440,1080,train\n-nRYJnnnTuk,3891,4024,743-423-1239-919,29.97,1440,1080,train\n-nRYJnnnTuk,4025,4229,726-408-1230-912,29.97,1440,1080,train\n-nRYJnnnTuk,5368,5543,566-340-1140-914,29.97,1440,1080,train\n-nRYJnnnTuk,6217,6377,702-438-1191-927,29.97,1440,1080,train\n-nRYJnnnTuk,6411,6621,678-421-1196-939,29.97,1440,1080,train\n-nRYJnnnTuk,6957,7093,723-315-1328-920,29.97,1440,1080,train\nKtVCCLlkcKg,72,1096,587-93-1444-950,23.97,1920,1080,train\nKtVCCLlkcKg,1096,2120,577-90-1412-925,23.97,1920,1080,train\nKtVCCLlkcKg,2120,2393,570-83-1419-932,23.97,1920,1080,train\nKtVCCLlkcKg,2399,3423,566-80-1413-927,23.97,1920,1080,train\nKtVCCLlkcKg,3423,4115,576-110-1395-929,23.97,1920,1080,train\nKtVCCLlkcKg,4115,4472,564-49-1469-954,23.97,1920,1080,train\nKtVCCLlkcKg,4472,5496,550-3-1510-963,23.97,1920,1080,train\nKtVCCLlkcKg,5496,5754,610-123-1434-947,23.97,1920,1080,train\na6qZnwdir0c,60,502,141-363-788-1010,30.0,1920,1080,train\na6qZnwdir0c,502,875,192-332-854-994,30.0,1920,1080,train\na6qZnwdir0c,1106,1280,186-239-832-885,30.0,1920,1080,train\na6qZnwdir0c,1572,1709,288-248-851-811,30.0,1920,1080,train\na6qZnwdir0c,2559,2892,85-299-785-999,30.0,1920,1080,train\na6qZnwdir0c,2892,3074,207-351-844-988,30.0,1920,1080,train\na6qZnwdir0c,3468,3731,471-292-1175-996,30.0,1920,1080,train\na6qZnwdir0c,4830,5021,790-369-1472-1051,30.0,1920,1080,train\na6qZnwdir0c,5326,5472,877-292-1638-1053,30.0,1920,1080,train\nkgvcI9oe3NI,386,520,160-35-592-467,25.0,640,480,test\nkgvcI9oe3NI,1578,1763,133-29-556-452,25.0,640,480,test\nkgvcI9oe3NI,1818,2842,102-5-571-474,25.0,640,480,test\nkgvcI9oe3NI,2890,3413,60-27-507-474,25.0,640,480,test\nPpk7BAngN_A,141,315,219-53-616-450,29.97,640,480,train\nPpk7BAngN_A,4433,4569,150-93-481-424,29.97,640,480,train\nPpk7BAngN_A,9338,9492,194-56-559-421,29.97,640,480,train\nOgChhgaq8Zw,1441,1695,288-26-952-690,29.97,1280,720,train\nOgChhgaq8Zw,2192,2648,251-15-913-677,29.97,1280,720,train\nOgChhgaq8Zw,3125,3308,116-71-736-691,29.97,1280,720,train\nOgChhgaq8Zw,5529,6019,299-9-990-700,29.97,1280,720,train\nOgChhgaq8Zw,6019,6162,3-8-687-692,29.97,1280,720,train\nOgChhgaq8Zw,6749,6960,60-38-732-710,29.97,1280,720,train\nOgChhgaq8Zw,7304,8328,288-1-988-701,29.97,1280,720,train\n2aDZU_WgtoY,0,395,126-143-401-418,25.0,640,480,train\n2aDZU_WgtoY,6225,6498,175-98-462-385,25.0,640,480,train\nMEtdtJwdfwg,127,704,350-86-976-712,25.0,1280,720,train\nMEtdtJwdfwg,2795,3497,430-104-1041-715,25.0,1280,720,train\n4h845uDRDR8,481,1205,620-113-1570-1063,29.97,1920,1080,train\n4h845uDRDR8,1205,2229,887-174-1792-1079,29.97,1920,1080,train\n4h845uDRDR8,2229,2362,831-202-1669-1040,29.97,1920,1080,train\n4h845uDRDR8,2362,2579,949-183-1811-1045,29.97,1920,1080,train\n4h845uDRDR8,2579,2809,746-183-1578-1015,29.97,1920,1080,train\n4h845uDRDR8,3913,4552,507-152-1431-1076,29.97,1920,1080,train\n4h845uDRDR8,6488,6831,528-141-1444-1057,29.97,1920,1080,train\n4h845uDRDR8,7549,8104,409-77-1400-1068,29.97,1920,1080,train\n4h845uDRDR8,8105,8313,354-121-1245-1012,29.97,1920,1080,train\n4h845uDRDR8,8418,8720,608-126-1542-1060,29.97,1920,1080,train\n4h845uDRDR8,8800,9824,457-124-1413-1080,29.97,1920,1080,train\n4h845uDRDR8,9857,10554,541-178-1404-1041,29.97,1920,1080,train\n4h845uDRDR8,10743,11552,180-38-1209-1067,29.97,1920,1080,train\n4h845uDRDR8,11659,12669,480-106-1443-1069,29.97,1920,1080,train\n4h845uDRDR8,12669,12942,245-124-1153-1032,29.97,1920,1080,train\n4h845uDRDR8,13287,13586,440-9-1485-1054,29.97,1920,1080,train\nqgWnTgmgi0Q,274,630,126-48-510-432,25.0,640,480,train\nqgWnTgmgi0Q,630,818,155-90-496-431,25.0,640,480,train\nqgWnTgmgi0Q,829,1006,98-77-448-427,25.0,640,480,train\nqgWnTgmgi0Q,2700,2988,119-89-451-421,25.0,640,480,train\nqgWnTgmgi0Q,2988,3132,133-96-451-414,25.0,640,480,train\nqgWnTgmgi0Q,3923,4080,195-91-531-427,25.0,640,480,train\nqgWnTgmgi0Q,4889,5039,178-79-517-418,25.0,640,480,train\nqgWnTgmgi0Q,6132,6427,231-87-574-430,25.0,640,480,train\nqgWnTgmgi0Q,6562,6706,165-65-530-430,25.0,640,480,train\nqgWnTgmgi0Q,10358,10496,132-78-458-404,25.0,640,480,train\nVMSqvTE90hk,165,530,100-85-454-439,29.97,640,480,test\nVMSqvTE90hk,743,887,114-89-467-442,29.97,640,480,test\nVMSqvTE90hk,2955,3097,181-71-559-449,29.97,640,480,test\nVMSqvTE90hk,3198,3327,200-76-552-428,29.97,640,480,test\nVMSqvTE90hk,3327,3476,157-54-524-421,29.97,640,480,test\nVMSqvTE90hk,4248,4621,150-66-533-449,29.97,640,480,test\nVMSqvTE90hk,6598,6749,78-91-414-427,29.97,640,480,test\nVMSqvTE90hk,7168,7312,77-46-482-451,29.97,640,480,test\nLHoIPFDYBCc,3922,4349,230-106-834-710,29.97,1280,720,train\nLHoIPFDYBCc,7529,7681,458-51-1110-703,29.97,1280,720,train\nLHoIPFDYBCc,7681,7892,424-17-1107-700,29.97,1280,720,train\nLHoIPFDYBCc,7893,8187,343-62-985-704,29.97,1280,720,train\nLHoIPFDYBCc,11054,11260,535-11-1244-720,29.97,1280,720,train\nLHoIPFDYBCc,19928,20078,372-27-1014-669,29.97,1280,720,train\nTlou0HOrOE4,227,1042,179-77-507-405,29.97,640,480,train\nTlou0HOrOE4,1306,1504,191-52-562-423,29.97,640,480,train\nTlou0HOrOE4,2613,2755,193-124-457-388,29.97,640,480,train\nTlou0HOrOE4,4709,4862,214-105-501-392,29.97,640,480,train\nTlou0HOrOE4,5273,5506,213-104-480-371,29.97,640,480,train\nTlou0HOrOE4,5554,5700,243-82-525-364,29.97,640,480,train\nTlou0HOrOE4,6157,6335,218-122-486-390,29.97,640,480,train\nTlou0HOrOE4,6423,6603,182-102-470-390,29.97,640,480,train\nTlou0HOrOE4,6905,7118,190-62-524-396,29.97,640,480,train\nTlou0HOrOE4,8654,8811,224-122-491-389,29.97,640,480,train\nTlou0HOrOE4,9114,9252,117-107-431-421,29.97,640,480,train\nrfXnvX5eTAM,2,621,469-28-1374-933,25.0,1920,1080,train\nrfXnvX5eTAM,809,1162,484-75-1481-1072,25.0,1920,1080,train\nrfXnvX5eTAM,1285,1440,584-68-1532-1016,25.0,1920,1080,train\nrfXnvX5eTAM,1622,1853,512-48-1505-1041,25.0,1920,1080,train\nrfXnvX5eTAM,1882,2027,621-130-1523-1032,25.0,1920,1080,train\nrfXnvX5eTAM,3124,3336,319-62-1292-1035,25.0,1920,1080,train\nrfXnvX5eTAM,3946,4085,325-68-1336-1079,25.0,1920,1080,train\neD0O4ZrSjjQ,199,1223,270-60-597-387,25.0,854,480,train\neD0O4ZrSjjQ,1223,1418,319-73-628-382,25.0,854,480,train\neD0O4ZrSjjQ,1418,1797,294-70-622-398,25.0,854,480,train\neD0O4ZrSjjQ,1802,1940,343-71-647-375,25.0,854,480,train\neD0O4ZrSjjQ,1942,2315,303-85-595-377,25.0,854,480,train\neD0O4ZrSjjQ,2315,3140,302-70-613-381,25.0,854,480,train\neD0O4ZrSjjQ,3140,3830,220-76-523-379,25.0,854,480,train\neD0O4ZrSjjQ,3870,4469,143-76-457-390,25.0,854,480,train\neD0O4ZrSjjQ,4628,4758,295-83-602-390,25.0,854,480,train\neD0O4ZrSjjQ,4935,5125,255-82-578-405,25.0,854,480,train\neD0O4ZrSjjQ,5125,5779,308-66-647-405,25.0,854,480,train\neD0O4ZrSjjQ,5877,6901,201-65-528-392,25.0,854,480,train\neD0O4ZrSjjQ,6901,7386,234-80-529-375,25.0,854,480,train\neD0O4ZrSjjQ,7387,7548,278-84-574-380,25.0,854,480,train\neD0O4ZrSjjQ,7548,7696,201-83-490-372,25.0,854,480,train\neD0O4ZrSjjQ,7702,7917,240-94-522-376,25.0,854,480,train\neD0O4ZrSjjQ,7943,8180,265-93-542-370,25.0,854,480,train\neD0O4ZrSjjQ,8240,8451,311-86-610-385,25.0,854,480,train\neD0O4ZrSjjQ,8451,9475,294-69-614-389,25.0,854,480,train\neD0O4ZrSjjQ,9560,9988,315-79-601-365,25.0,854,480,train\neD0O4ZrSjjQ,10002,10312,257-48-579-370,25.0,854,480,train\neD0O4ZrSjjQ,10313,10553,287-95-559-367,25.0,854,480,train\nX7Q04MoQxXo,51,272,273-162-535-424,29.97,854,480,train\nX7Q04MoQxXo,440,577,268-170-553-455,29.97,854,480,train\nX7Q04MoQxXo,661,791,211-183-485-457,29.97,854,480,train\nX7Q04MoQxXo,834,985,217-174-496-453,29.97,854,480,train\nX7Q04MoQxXo,1379,1606,287-132-563-408,29.97,854,480,train\nX7Q04MoQxXo,4037,4187,327-161-590-424,29.97,854,480,train\nX7Q04MoQxXo,4480,4689,298-152-568-422,29.97,854,480,train\nX7Q04MoQxXo,6739,6869,276-110-552-386,29.97,854,480,train\nJHaOu5Z2ScI,1302,1530,344-103-714-473,29.97,854,480,train\nJHaOu5Z2ScI,4591,4752,263-62-680-479,29.97,854,480,train\nJHaOu5Z2ScI,5431,5562,280-70-677-467,29.97,854,480,train\nJHaOu5Z2ScI,6634,6769,212-70-617-475,29.97,854,480,train\nR108l6J4N1o,634,767,381-189-1108-916,30.0,1920,1080,train\nR108l6J4N1o,1547,1727,378-41-1183-846,30.0,1920,1080,train\nR108l6J4N1o,3244,3387,398-23-1192-817,30.0,1920,1080,train\nR108l6J4N1o,9079,9210,1484-138-1904-558,30.0,1920,1080,train\nR108l6J4N1o,9666,10014,510-105-1314-909,30.0,1920,1080,train\nR108l6J4N1o,10596,10732,1333-82-1760-509,30.0,1920,1080,train\nR108l6J4N1o,10742,10968,1422-121-1851-550,30.0,1920,1080,train\nwbwUCsr9SR8,183,347,316-91-887-662,29.97,1280,720,train\nwbwUCsr9SR8,3634,3857,432-97-976-641,29.97,1280,720,train\nwbwUCsr9SR8,3896,4104,424-188-840-604,29.97,1280,720,train\nKjMxdYJOwqI,0,470,31-19-652-640,25.0,1280,720,train\nKjMxdYJOwqI,543,747,121-28-695-602,25.0,1280,720,train\nKjMxdYJOwqI,1240,1599,307-1-962-656,25.0,1280,720,train\nKjMxdYJOwqI,1599,2068,391-13-1070-692,25.0,1280,720,train\nKjMxdYJOwqI,2687,2970,239-23-902-686,25.0,1280,720,train\nKjMxdYJOwqI,3782,4050,57-38-662-643,25.0,1280,720,train\nKjMxdYJOwqI,4050,4644,16-10-624-618,25.0,1280,720,train\nKjMxdYJOwqI,4866,5084,272-36-832-596,25.0,1280,720,train\ns3b6B6Vw2ZQ,494,858,184-64-661-541,29.97,1280,720,train\ns3b6B6Vw2ZQ,2285,2468,438-93-888-543,29.97,1280,720,train\ns3b6B6Vw2ZQ,3262,3440,379-77-851-549,29.97,1280,720,train\ns3b6B6Vw2ZQ,3498,3808,292-96-749-553,29.97,1280,720,train\ns3b6B6Vw2ZQ,3876,4009,202-82-672-552,29.97,1280,720,train\ns3b6B6Vw2ZQ,4146,4371,292-110-726-544,29.97,1280,720,train\ns3b6B6Vw2ZQ,4407,4562,275-98-715-538,29.97,1280,720,train\ns3b6B6Vw2ZQ,4635,4943,286-108-723-545,29.97,1280,720,train\ns3b6B6Vw2ZQ,4943,5075,357-88-796-527,29.97,1280,720,train\ns3b6B6Vw2ZQ,5320,5573,290-79-751-540,29.97,1280,720,train\ns3b6B6Vw2ZQ,6256,6458,410-95-851-536,29.97,1280,720,train\ns3b6B6Vw2ZQ,6458,6604,498-88-938-528,29.97,1280,720,train\ns3b6B6Vw2ZQ,7023,7281,497-87-939-529,29.97,1280,720,train\ns3b6B6Vw2ZQ,7731,7916,551-79-1006-534,29.97,1280,720,train\ns3b6B6Vw2ZQ,7943,8160,612-57-1077-522,29.97,1280,720,train\ns3b6B6Vw2ZQ,8459,8640,278-31-827-580,29.97,1280,720,train\ns3b6B6Vw2ZQ,9087,9262,86-62-628-604,29.97,1280,720,train\ns3b6B6Vw2ZQ,9364,9500,185-99-664-578,29.97,1280,720,train\ns3b6B6Vw2ZQ,9846,9982,134-110-592-568,29.97,1280,720,train\ns3b6B6Vw2ZQ,10339,10639,327-113-791-577,29.97,1280,720,train\ns3b6B6Vw2ZQ,10913,11278,287-67-791-571,29.97,1280,720,train\n36SpweR9O3s,8618,8748,98-139-380-421,25.0,600,480,train\nnAQEOC1Z10M,7750,7956,569-105-1130-666,59.94,1280,720,test\nnAQEOC1Z10M,7999,8438,414-89-997-672,59.94,1280,720,test\nnAQEOC1Z10M,8438,8572,339-61-925-647,59.94,1280,720,test\nnAQEOC1Z10M,8572,8848,411-64-998-651,59.94,1280,720,test\nnAQEOC1Z10M,8848,9055,445-36-1052-643,59.94,1280,720,test\nnAQEOC1Z10M,9055,9434,370-96-919-645,59.94,1280,720,test\nnAQEOC1Z10M,9434,9587,251-92-805-646,59.94,1280,720,test\nnAQEOC1Z10M,10446,10614,309-92-868-651,59.94,1280,720,test\nnAQEOC1Z10M,10776,10955,542-102-1085-645,59.94,1280,720,test\nnAQEOC1Z10M,11006,11200,712-115-1258-661,59.94,1280,720,test\nnAQEOC1Z10M,11244,11869,363-118-916-671,59.94,1280,720,test\nnAQEOC1Z10M,11869,12265,259-123-784-648,59.94,1280,720,test\nnAQEOC1Z10M,12265,12835,330-101-905-676,59.94,1280,720,test\nnAQEOC1Z10M,12926,13159,315-112-852-649,59.94,1280,720,test\nnAQEOC1Z10M,13257,13665,359-102-921-664,59.94,1280,720,test\nnAQEOC1Z10M,13665,13832,215-102-770-657,59.94,1280,720,test\nnAQEOC1Z10M,13891,14101,151-95-714-658,59.94,1280,720,test\nnAQEOC1Z10M,14101,14461,48-104-605-661,59.94,1280,720,test\nnAQEOC1Z10M,14730,15436,88-98-631-641,59.94,1280,720,test\nnAQEOC1Z10M,15442,15583,19-108-522-611,59.94,1280,720,test\nnAQEOC1Z10M,15624,15783,94-120-570-596,59.94,1280,720,test\nnAQEOC1Z10M,16313,16524,266-151-761-646,59.94,1280,720,test\nnAQEOC1Z10M,16558,16877,370-104-882-616,59.94,1280,720,test\nnAQEOC1Z10M,17094,17364,594-177-1029-612,59.94,1280,720,test\nnAQEOC1Z10M,17670,18082,419-131-931-643,59.94,1280,720,test\nnAQEOC1Z10M,18236,18704,655-125-1192-662,59.94,1280,720,test\nnAQEOC1Z10M,18798,19102,610-130-1136-656,59.94,1280,720,test\nnAQEOC1Z10M,19102,19658,513-135-1050-672,59.94,1280,720,test\nnAQEOC1Z10M,19658,19817,411-133-930-652,59.94,1280,720,test\nnAQEOC1Z10M,19858,20177,556-141-1073-658,59.94,1280,720,test\nnAQEOC1Z10M,20177,20600,492-115-1038-661,59.94,1280,720,test\nnAQEOC1Z10M,20600,20777,557-116-1128-687,59.94,1280,720,test\n5SRTl6JcQ8g,42,808,229-101-787-659,30.0,960,720,train\n5SRTl6JcQ8g,927,1081,307-156-750-599,30.0,960,720,train\n5SRTl6JcQ8g,2322,2464,180-143-679-642,30.0,960,720,train\n5SRTl6JcQ8g,2730,2859,301-139-793-631,30.0,960,720,train\n5SRTl6JcQ8g,5958,6251,219-80-785-646,30.0,960,720,train\n5SRTl6JcQ8g,8002,8158,205-112-768-675,30.0,960,720,train\n5SRTl6JcQ8g,9419,9551,227-117-768-658,30.0,960,720,train\n5SRTl6JcQ8g,9661,9828,176-46-779-649,30.0,960,720,train\nvNfhp02w9s0,0,275,92-30-521-459,25.0,640,480,train\nvNfhp02w9s0,275,473,99-9-558-468,25.0,640,480,train\nvNfhp02w9s0,526,957,136-16-580-460,25.0,640,480,train\nvNfhp02w9s0,1115,1296,149-21-586-458,25.0,640,480,train\nvNfhp02w9s0,1303,1586,165-13-626-474,25.0,640,480,train\nvNfhp02w9s0,1676,1905,129-10-586-467,25.0,640,480,train\nvNfhp02w9s0,2087,2349,113-9-571-467,25.0,640,480,train\nvNfhp02w9s0,2452,2825,128-23-559-454,25.0,640,480,train\nvNfhp02w9s0,3382,3925,54-49-454-449,25.0,640,480,train\nvNfhp02w9s0,4066,4442,70-67-462-459,25.0,640,480,train\nvNfhp02w9s0,4648,5130,87-29-514-456,25.0,640,480,train\nvNfhp02w9s0,5130,5331,115-61-510-456,25.0,640,480,train\nvNfhp02w9s0,5415,5670,121-11-579-469,25.0,640,480,train\nvNfhp02w9s0,5670,5852,89-16-528-455,25.0,640,480,train\nvNfhp02w9s0,5965,6412,137-17-585-465,25.0,640,480,train\nvNfhp02w9s0,6732,6866,88-38-512-462,25.0,640,480,train\nvNfhp02w9s0,6866,7091,138-14-578-454,25.0,640,480,train\nvNfhp02w9s0,7133,7426,127-0-597-469,25.0,640,480,train\nEaPwYQC-5pE,989,1191,377-57-985-665,29.97,1280,720,train\nEaPwYQC-5pE,1191,1328,357-62-990-695,29.97,1280,720,train\nEaPwYQC-5pE,1328,2300,497-86-1105-694,29.97,1280,720,train\nEaPwYQC-5pE,2322,3346,370-117-874-621,29.97,1280,720,train\nEaPwYQC-5pE,3677,3928,333-63-939-669,29.97,1280,720,train\nEaPwYQC-5pE,3939,4526,292-58-887-653,29.97,1280,720,train\nEaPwYQC-5pE,4562,4692,282-73-875-666,29.97,1280,720,train\nEaPwYQC-5pE,4692,4849,445-75-1029-659,29.97,1280,720,train\nEaPwYQC-5pE,4870,5075,385-77-968-660,29.97,1280,720,train\nEaPwYQC-5pE,5282,5592,489-135-1014-660,29.97,1280,720,train\nEaPwYQC-5pE,5602,6151,420-71-1017-668,29.97,1280,720,train\nEaPwYQC-5pE,6238,6601,447-126-970-649,29.97,1280,720,train\nEaPwYQC-5pE,6631,7182,479-107-1039-667,29.97,1280,720,train\nEaPwYQC-5pE,7251,7407,398-60-996-658,29.97,1280,720,train\nirQNFGmGRQQ,1350,1533,376-105-657-386,25.0,854,480,train\nirQNFGmGRQQ,1559,1918,345-106-639-400,25.0,854,480,train\nirQNFGmGRQQ,1918,2100,359-91-665-397,25.0,854,480,train\nirQNFGmGRQQ,2184,2348,315-95-623-403,25.0,854,480,train\nirQNFGmGRQQ,2379,2525,376-105-662-391,25.0,854,480,train\nirQNFGmGRQQ,2662,2790,365-108-623-366,25.0,854,480,train\nirQNFGmGRQQ,2819,2956,418-84-707-373,25.0,854,480,train\nirQNFGmGRQQ,3122,3324,434-88-709-363,25.0,854,480,train\nirQNFGmGRQQ,3818,4112,195-78-495-378,25.0,854,480,train\nirQNFGmGRQQ,4422,4633,343-127-600-384,25.0,854,480,train\nirQNFGmGRQQ,4667,5691,299-87-600-388,25.0,854,480,train\nirQNFGmGRQQ,5990,6150,338-114-603-379,25.0,854,480,train\nirQNFGmGRQQ,6986,7123,403-105-669-371,25.0,854,480,train\nirQNFGmGRQQ,8158,8325,422-40-744-362,25.0,854,480,train\nirQNFGmGRQQ,8536,8757,478-88-749-359,25.0,854,480,train\nirQNFGmGRQQ,8776,8913,495-53-794-352,25.0,854,480,train\nirQNFGmGRQQ,8916,9099,497-74-771-348,25.0,854,480,train\nirQNFGmGRQQ,9320,9546,332-53-658-379,25.0,854,480,train\nirQNFGmGRQQ,10512,10767,168-73-515-420,25.0,854,480,train\nirQNFGmGRQQ,10877,11167,114-53-470-409,25.0,854,480,train\nirQNFGmGRQQ,11405,11767,274-90-603-419,25.0,854,480,train\nirQNFGmGRQQ,11887,12038,301-96-614-409,25.0,854,480,train\nirQNFGmGRQQ,12068,12345,253-64-597-408,25.0,854,480,train\nMGYF1aDwUKg,90,294,142-122-459-439,25.0,640,480,train\nxlHGjYHyjmM,3102,3428,244-12-901-669,30.0,1280,720,train\nxlHGjYHyjmM,3430,3580,389-58-1037-706,30.0,1280,720,train\nxlHGjYHyjmM,3638,3771,328-42-972-686,30.0,1280,720,train\nxlHGjYHyjmM,3771,4079,309-9-977-677,30.0,1280,720,train\nxlHGjYHyjmM,4103,4242,403-9-1081-687,30.0,1280,720,train\nxlHGjYHyjmM,4279,4496,326-33-974-681,30.0,1280,720,train\nxlHGjYHyjmM,4719,5353,330-36-980-686,30.0,1280,720,train\nxlHGjYHyjmM,5640,6064,295-17-966-688,30.0,1280,720,train\nxlHGjYHyjmM,6321,6456,298-35-959-696,30.0,1280,720,train\nxlHGjYHyjmM,7579,7762,317-23-983-689,30.0,1280,720,train\nxlHGjYHyjmM,7762,7956,268-30-958-720,30.0,1280,720,train\nxlHGjYHyjmM,8604,9595,339-15-1008-684,30.0,1280,720,train\nxlHGjYHyjmM,11581,11725,321-26-999-704,30.0,1280,720,train\nlybYf6hakUs,2593,2722,227-27-897-697,25.0,1280,720,train\nlybYf6hakUs,4230,4438,250-8-932-690,25.0,1280,720,train\naAwbJ9MO91I,1200,2224,400-177-830-607,29.97,1280,720,train\naAwbJ9MO91I,2224,2711,402-178-826-602,29.97,1280,720,train\naAwbJ9MO91I,2804,2953,387-179-823-615,29.97,1280,720,train\naAwbJ9MO91I,3061,3208,391-182-821-612,29.97,1280,720,train\naAwbJ9MO91I,3318,3486,392-185-822-615,29.97,1280,720,train\naAwbJ9MO91I,3569,4029,385-180-826-621,29.97,1280,720,train\naAwbJ9MO91I,4770,4990,398-178-822-602,29.97,1280,720,train\naAwbJ9MO91I,5137,5465,384-173-824-613,29.97,1280,720,train\naAwbJ9MO91I,5508,5662,390-172-831-613,29.97,1280,720,train\naAwbJ9MO91I,5920,6137,405-188-818-601,29.97,1280,720,train\naAwbJ9MO91I,6240,6400,498-256-826-584,29.97,1280,720,train\naAwbJ9MO91I,6453,6812,473-213-849-589,29.97,1280,720,train\naAwbJ9MO91I,6812,6974,461-234-841-614,29.97,1280,720,train\naAwbJ9MO91I,7044,7230,473-242-817-586,29.97,1280,720,train\naAwbJ9MO91I,7287,7466,469-231-834-596,29.97,1280,720,train\naAwbJ9MO91I,7529,7674,476-241-822-587,29.97,1280,720,train\naAwbJ9MO91I,7790,8065,477-233-833-589,29.97,1280,720,train\naAwbJ9MO91I,8440,8607,480-261-808-589,29.97,1280,720,train\naAwbJ9MO91I,8899,9160,471-234-828-591,29.97,1280,720,train\naAwbJ9MO91I,9201,9423,453-230-830-607,29.97,1280,720,train\naAwbJ9MO91I,9458,10482,380-133-850-603,29.97,1280,720,train\naAwbJ9MO91I,10482,10993,400-184-824-608,29.97,1280,720,train\naAwbJ9MO91I,11043,11203,386-181-812-607,29.97,1280,720,train\naAwbJ9MO91I,11253,11381,397-180-818-601,29.97,1280,720,train\naAwbJ9MO91I,11443,11941,375-127-855-607,29.97,1280,720,train\naAwbJ9MO91I,11943,12093,361-127-834-600,29.97,1280,720,train\naAwbJ9MO91I,12147,12279,368-124-860-616,29.97,1280,720,train\naAwbJ9MO91I,13619,13771,452-238-802-588,29.97,1280,720,train\naAwbJ9MO91I,13785,13917,429-251-764-586,29.97,1280,720,train\naAwbJ9MO91I,14197,14338,415-237-767-589,29.97,1280,720,train\naAwbJ9MO91I,14498,14720,456-260-784-588,29.97,1280,720,train\naAwbJ9MO91I,14720,14925,494-257-826-589,29.97,1280,720,train\naAwbJ9MO91I,15040,15199,457-260-781-584,29.97,1280,720,train\naAwbJ9MO91I,15574,15767,500-263-822-585,29.97,1280,720,train\naAwbJ9MO91I,15795,16046,455-256-785-586,29.97,1280,720,train\naAwbJ9MO91I,16195,16490,491-260-818-587,29.97,1280,720,train\naAwbJ9MO91I,16490,16679,490-256-821-587,29.97,1280,720,train\naAwbJ9MO91I,16740,16950,460-256-787-583,29.97,1280,720,train\naAwbJ9MO91I,16951,17234,471-255-801-585,29.97,1280,720,train\naAwbJ9MO91I,18514,18665,401-163-835-597,29.97,1280,720,train\naAwbJ9MO91I,20234,20480,409-174-874-639,29.97,1280,720,train\naAwbJ9MO91I,21511,21660,481-255-833-607,29.97,1280,720,train\naAwbJ9MO91I,21788,21958,507-259-837-589,29.97,1280,720,train\naAwbJ9MO91I,23001,23143,482-255-834-607,29.97,1280,720,train\naAwbJ9MO91I,24614,24768,401-190-812-601,29.97,1280,720,train\naAwbJ9MO91I,24768,25270,388-169-818-599,29.97,1280,720,train\naAwbJ9MO91I,25271,25439,405-177-827-599,29.97,1280,720,train\naAwbJ9MO91I,28293,28430,478-257-803-582,29.97,1280,720,train\naAwbJ9MO91I,29027,29482,493-255-826-588,29.97,1280,720,train\naAwbJ9MO91I,29640,29779,460-248-810-598,29.97,1280,720,train\naAwbJ9MO91I,30757,30967,473-249-811-587,29.97,1280,720,train\naAwbJ9MO91I,31022,31562,476-251-810-585,29.97,1280,720,train\naAwbJ9MO91I,31613,31879,395-188-804-597,29.97,1280,720,train\naAwbJ9MO91I,32005,32251,397-183-809-595,29.97,1280,720,train\naAwbJ9MO91I,32252,33024,396-190-804-598,29.97,1280,720,train\naAwbJ9MO91I,33215,33410,401-183-812-594,29.97,1280,720,train\naAwbJ9MO91I,33432,34082,401-183-808-590,29.97,1280,720,train\naAwbJ9MO91I,34083,34548,402-182-807-587,29.97,1280,720,train\naAwbJ9MO91I,35071,35261,402-187-811-596,29.97,1280,720,train\naAwbJ9MO91I,35327,36351,405-182-822-599,29.97,1280,720,train\naAwbJ9MO91I,36351,36772,400-177-820-597,29.97,1280,720,train\naAwbJ9MO91I,39234,39398,407-180-816-589,29.97,1280,720,train\naAwbJ9MO91I,39966,40163,404-178-817-591,29.97,1280,720,train\naAwbJ9MO91I,40340,40640,406-179-817-590,29.97,1280,720,train\naAwbJ9MO91I,40664,40934,404-178-819-593,29.97,1280,720,train\naAwbJ9MO91I,40972,41876,403-178-820-595,29.97,1280,720,train\n3M5VGsUtw_Q,1600,1750,244-55-896-707,29.97,1280,720,train\n3M5VGsUtw_Q,2100,2250,354-54-1002-702,29.97,1280,720,train\n3M5VGsUtw_Q,2522,2650,415-58-1075-718,29.97,1280,720,train\n3M5VGsUtw_Q,2650,2841,328-55-988-715,29.97,1280,720,train\n3M5VGsUtw_Q,8100,8240,420-135-996-711,29.97,1280,720,train\n3M5VGsUtw_Q,11044,11220,484-191-1009-716,29.97,1280,720,train\n3M5VGsUtw_Q,12038,12175,556-177-1083-704,29.97,1280,720,train\n3M5VGsUtw_Q,12625,12784,308-193-831-716,29.97,1280,720,train\nw8YcIAuUIys,613,844,363-112-899-648,25.0,1280,720,train\nw8YcIAuUIys,844,1234,298-113-860-675,25.0,1280,720,train\n4SgduoCb2_8,151,1175,491-117-1220-846,29.97,1920,1080,train\n4SgduoCb2_8,1426,1565,532-186-1190-844,29.97,1920,1080,train\n4SgduoCb2_8,1734,1894,553-181-1269-897,29.97,1920,1080,train\n4SgduoCb2_8,2110,2466,515-204-1144-833,29.97,1920,1080,train\n4SgduoCb2_8,2986,3737,519-156-1235-872,29.97,1920,1080,train\n4SgduoCb2_8,4154,4302,508-190-1208-890,29.97,1920,1080,train\n4SgduoCb2_8,4302,4480,564-148-1256-840,29.97,1920,1080,train\n4SgduoCb2_8,4481,4916,513-191-1154-832,29.97,1920,1080,train\n4SgduoCb2_8,5530,5834,518-145-1226-853,29.97,1920,1080,train\n4SgduoCb2_8,5834,6016,439-135-1156-852,29.97,1920,1080,train\nyKYjtfmyVGU,228,360,556-135-1425-1004,30.0,1920,1080,train\nyKYjtfmyVGU,360,625,544-131-1413-1000,30.0,1920,1080,train\nyKYjtfmyVGU,817,961,522-135-1405-1018,30.0,1920,1080,train\nyKYjtfmyVGU,973,1105,463-118-1334-989,30.0,1920,1080,train\nyKYjtfmyVGU,1429,1982,478-125-1377-1024,30.0,1920,1080,train\nyKYjtfmyVGU,2097,2246,496-100-1412-1016,30.0,1920,1080,train\nyKYjtfmyVGU,2258,2423,508-131-1374-997,30.0,1920,1080,train\nyKYjtfmyVGU,2423,2943,614-107-1497-990,30.0,1920,1080,train\nyKYjtfmyVGU,3063,3229,561-120-1466-1025,30.0,1920,1080,train\nyKYjtfmyVGU,3351,3603,561-105-1441-985,30.0,1920,1080,train\nyKYjtfmyVGU,3603,3749,493-138-1358-1003,30.0,1920,1080,train\nyKYjtfmyVGU,3798,4072,653-80-1556-983,30.0,1920,1080,train\nyKYjtfmyVGU,4264,4655,708-132-1522-946,30.0,1920,1080,train\nyKYjtfmyVGU,4685,4865,638-107-1489-958,30.0,1920,1080,train\nyKYjtfmyVGU,4973,5946,546-118-1382-954,30.0,1920,1080,train\nyKYjtfmyVGU,6466,6606,658-108-1474-924,30.0,1920,1080,train\nyKYjtfmyVGU,6727,6915,468-149-1257-938,30.0,1920,1080,train\nyKYjtfmyVGU,6915,7327,628-100-1461-933,30.0,1920,1080,train\nyKYjtfmyVGU,7447,7695,572-133-1375-936,30.0,1920,1080,train\nyKYjtfmyVGU,7808,7988,635-131-1419-915,30.0,1920,1080,train\nyKYjtfmyVGU,7988,8156,613-134-1419-940,30.0,1920,1080,train\nyKYjtfmyVGU,8156,8348,574-107-1419-952,30.0,1920,1080,train\nyKYjtfmyVGU,8468,8695,539-117-1364-942,30.0,1920,1080,train\nyKYjtfmyVGU,8695,9033,716-111-1554-949,30.0,1920,1080,train\nyKYjtfmyVGU,9405,9630,610-111-1419-920,30.0,1920,1080,train\nyKYjtfmyVGU,9638,9790,485-123-1296-934,30.0,1920,1080,train\nyKYjtfmyVGU,9790,9970,510-134-1298-922,30.0,1920,1080,train\nyKYjtfmyVGU,10270,10450,568-121-1376-929,30.0,1920,1080,train\nyKYjtfmyVGU,11167,11331,523-158-1338-973,30.0,1920,1080,train\nyKYjtfmyVGU,11471,11712,504-140-1325-961,30.0,1920,1080,train\nyKYjtfmyVGU,11789,12012,436-144-1268-976,30.0,1920,1080,train\nyKYjtfmyVGU,12012,12142,617-152-1431-966,30.0,1920,1080,train\nyKYjtfmyVGU,12145,12560,635-171-1413-949,30.0,1920,1080,train\nyKYjtfmyVGU,12560,12718,739-132-1558-951,30.0,1920,1080,train\nyKYjtfmyVGU,12979,13144,537-126-1352-941,30.0,1920,1080,train\nyKYjtfmyVGU,13861,14510,647-87-1590-1030,30.0,1920,1080,train\nyKYjtfmyVGU,14522,14943,648-142-1480-974,30.0,1920,1080,train\nyKYjtfmyVGU,14955,15123,685-131-1524-970,30.0,1920,1080,train\nyKYjtfmyVGU,15171,15314,666-114-1512-960,30.0,1920,1080,train\nyKYjtfmyVGU,15533,15706,640-152-1439-951,30.0,1920,1080,train\nyKYjtfmyVGU,16577,16745,628-128-1485-985,30.0,1920,1080,train\nyKYjtfmyVGU,16997,17360,648-155-1436-943,30.0,1920,1080,train\nyKYjtfmyVGU,17537,17838,545-117-1380-952,30.0,1920,1080,train\nxmwGBXYofEE,705,960,259-114-859-714,29.97,1280,720,train\nxmwGBXYofEE,960,1120,294-123-884-713,29.97,1280,720,train\nxmwGBXYofEE,1180,1384,294-136-858-700,29.97,1280,720,train\nxmwGBXYofEE,1920,2080,342-136-904-698,29.97,1280,720,train\nxmwGBXYofEE,2162,2400,305-128-892-715,29.97,1280,720,train\nxmwGBXYofEE,2560,2720,424-168-963-707,29.97,1280,720,train\nxmwGBXYofEE,2720,2867,419-194-905-680,29.97,1280,720,train\nxmwGBXYofEE,3040,3198,421-187-938-704,29.97,1280,720,train\nxmwGBXYofEE,3384,3520,422-182-939-699,29.97,1280,720,train\nxmwGBXYofEE,4640,4791,441-225-908-692,29.97,1280,720,train\nxmwGBXYofEE,6497,6715,213-161-758-706,29.97,1280,720,train\nxmwGBXYofEE,7313,7459,282-154-826-698,29.97,1280,720,train\nxmwGBXYofEE,7459,7680,333-127-897-691,29.97,1280,720,train\nxmwGBXYofEE,7680,8160,302-132-879-709,29.97,1280,720,train\nxmwGBXYofEE,9445,9618,411-157-967-713,29.97,1280,720,train\nxmwGBXYofEE,10405,10575,544-265-966-687,29.97,1280,720,train\nxmwGBXYofEE,12164,12341,415-200-928-713,29.97,1280,720,train\nxmwGBXYofEE,12820,12960,445-159-1002-716,29.97,1280,720,train\nxmwGBXYofEE,13096,13264,334-140-895-701,29.97,1280,720,train\nxmwGBXYofEE,13381,13631,214-163-761-710,29.97,1280,720,train\nxmwGBXYofEE,13760,13920,231-66-856-691,29.97,1280,720,train\nxmwGBXYofEE,13920,14056,228-105-816-693,29.97,1280,720,train\nxmwGBXYofEE,14992,15188,316-159-870-713,29.97,1280,720,train\nxmwGBXYofEE,15761,15942,392-136-942-686,29.97,1280,720,train\nxmwGBXYofEE,15942,16144,421-162-938-679,29.97,1280,720,train\nxmwGBXYofEE,16455,16676,400-209-877-686,29.97,1280,720,train\nxmwGBXYofEE,16703,16880,498-185-998-685,29.97,1280,720,train\nxmwGBXYofEE,17034,17280,541-231-982-672,29.97,1280,720,train\nxmwGBXYofEE,17280,17423,591-212-1037-658,29.97,1280,720,train\nxmwGBXYofEE,19640,19840,446-115-1025-694,29.97,1280,720,train\nxmwGBXYofEE,20042,20205,501-201-973-673,29.97,1280,720,train\nxmwGBXYofEE,20507,20674,445-189-969-713,29.97,1280,720,train\nxmwGBXYofEE,20986,21170,446-168-998-720,29.97,1280,720,train\nxmwGBXYofEE,21646,21806,271-153-832-714,29.97,1280,720,train\nxmwGBXYofEE,21806,21945,306-125-885-704,29.97,1280,720,train\n0JKfDKo-3DM,0,1024,376-188-861-673,29.97,1280,720,train\n0JKfDKo-3DM,1024,2048,373-203-840-670,29.97,1280,720,train\n0JKfDKo-3DM,2048,3072,332-194-807-669,29.97,1280,720,train\n0JKfDKo-3DM,3072,4096,352-211-819-678,29.97,1280,720,train\n0JKfDKo-3DM,4096,5120,357-209-823-675,29.97,1280,720,train\n0JKfDKo-3DM,5120,6144,353-206-820-673,29.97,1280,720,train\n0JKfDKo-3DM,6144,6500,359-205-823-669,29.97,1280,720,train\n0JKfDKo-3DM,6500,7028,265-217-729-681,29.97,1280,720,train\n0JKfDKo-3DM,7028,7522,351-202-826-677,29.97,1280,720,train\n0JKfDKo-3DM,7522,8546,241-200-724-683,29.97,1280,720,train\n0JKfDKo-3DM,8608,8862,236-206-710-680,29.97,1280,720,train\n0JKfDKo-3DM,8862,9089,318-214-789-685,29.97,1280,720,train\n0JKfDKo-3DM,9089,9631,186-221-647-682,29.97,1280,720,train\n0JKfDKo-3DM,9631,10567,68-222-543-697,29.97,1280,720,train\n0JKfDKo-3DM,10567,10874,202-228-655-681,29.97,1280,720,train\n0JKfDKo-3DM,10874,11515,316-206-780-670,29.97,1280,720,train\n0JKfDKo-3DM,11537,12300,349-211-812-674,29.97,1280,720,train\n0JKfDKo-3DM,12302,12473,362-211-819-668,29.97,1280,720,train\n0JKfDKo-3DM,12473,13497,222-217-680-675,29.97,1280,720,train\n0JKfDKo-3DM,13654,14029,337-218-786-667,29.97,1280,720,train\n0JKfDKo-3DM,14143,14588,208-224-650-666,29.97,1280,720,train\n0JKfDKo-3DM,14627,15338,352-233-779-660,29.97,1280,720,train\n0JKfDKo-3DM,15338,15549,276-236-705-665,29.97,1280,720,train\n0JKfDKo-3DM,15682,16706,350-227-781-658,29.97,1280,720,train\n0JKfDKo-3DM,16782,17147,300-232-745-677,29.97,1280,720,train\n0JKfDKo-3DM,17147,18170,225-239-661-675,29.97,1280,720,train\n0JKfDKo-3DM,18170,19101,291-223-744-676,29.97,1280,720,train\n0JKfDKo-3DM,19101,20125,204-232-649-677,29.97,1280,720,train\n0JKfDKo-3DM,20125,20374,225-229-665-669,29.97,1280,720,train\nrKilyW_awUo,1458,1774,435-162-1349-1076,29.97,1920,1080,train\nrKilyW_awUo,1780,1949,515-163-1395-1043,29.97,1920,1080,train\nrKilyW_awUo,2228,2389,439-93-1314-968,29.97,1920,1080,train\nrKilyW_awUo,2440,2823,585-108-1547-1070,29.97,1920,1080,train\nrKilyW_awUo,2823,3063,421-149-1294-1022,29.97,1920,1080,train\nrKilyW_awUo,3121,3381,422-134-1341-1053,29.97,1920,1080,train\nrKilyW_awUo,3802,4043,464-132-1368-1036,29.97,1920,1080,train\nrKilyW_awUo,4302,4673,471-127-1417-1073,29.97,1920,1080,train\nrKilyW_awUo,6925,7605,467-4-1539-1076,29.97,1920,1080,train\nrKilyW_awUo,7622,7778,467-85-1458-1076,29.97,1920,1080,train\nrKilyW_awUo,7849,8024,513-126-1455-1068,29.97,1920,1080,train\nrKilyW_awUo,8024,8209,350-157-1229-1036,29.97,1920,1080,train\nrKilyW_awUo,8483,8795,475-135-1390-1050,29.97,1920,1080,train\nrKilyW_awUo,9031,9180,370-80-1319-1029,29.97,1920,1080,train\nrKilyW_awUo,9832,9968,524-167-1393-1036,29.97,1920,1080,train\nrKilyW_awUo,10043,10191,359-157-1263-1061,29.97,1920,1080,train\nrKilyW_awUo,10853,11314,596-122-1548-1074,29.97,1920,1080,train\njvwHcYbcyEU,16862,17082,458-107-1417-1066,29.97,1920,1080,train\nZjN0kL_SVJw,484,1026,486-99-1448-1061,29.97,1920,1080,train\nZjN0kL_SVJw,1430,1791,499-105-1453-1059,29.97,1920,1080,train\nZjN0kL_SVJw,1854,2092,496-87-1441-1032,29.97,1920,1080,train\nZjN0kL_SVJw,2608,2902,483-138-1423-1078,29.97,1920,1080,train\nZjN0kL_SVJw,4107,4453,501-116-1428-1043,29.97,1920,1080,train\nZjN0kL_SVJw,4640,4787,592-132-1446-986,29.97,1920,1080,train\nZjN0kL_SVJw,5007,5400,580-104-1516-1040,29.97,1920,1080,train\nZjN0kL_SVJw,5504,5765,625-139-1489-1003,29.97,1920,1080,train\nZjN0kL_SVJw,6068,6560,555-110-1460-1015,29.97,1920,1080,train\nZjN0kL_SVJw,6560,6708,557-64-1496-1003,29.97,1920,1080,train\nZjN0kL_SVJw,6978,7219,409-64-1398-1053,29.97,1920,1080,train\nZjN0kL_SVJw,7726,7867,428-169-1252-993,29.97,1920,1080,train\nZjN0kL_SVJw,8080,8216,521-166-1345-990,29.97,1920,1080,train\nZjN0kL_SVJw,8216,8506,586-123-1450-987,29.97,1920,1080,train\nZjN0kL_SVJw,9341,10027,523-128-1419-1024,29.97,1920,1080,train\nZjN0kL_SVJw,10645,10851,653-132-1555-1034,29.97,1920,1080,train\nZjN0kL_SVJw,11510,11645,406-135-1307-1036,29.97,1920,1080,train\nZjN0kL_SVJw,11818,12033,498-108-1365-975,29.97,1920,1080,train\nZjN0kL_SVJw,12558,12813,618-121-1502-1005,29.97,1920,1080,train\nZjN0kL_SVJw,13887,14539,466-102-1400-1036,29.97,1920,1080,train\nZjN0kL_SVJw,14632,14877,509-69-1478-1038,29.97,1920,1080,train\nZjN0kL_SVJw,15009,15188,467-112-1329-974,29.97,1920,1080,train\nZjN0kL_SVJw,15790,16165,488-52-1488-1052,29.97,1920,1080,train\nZjN0kL_SVJw,16515,16797,575-88-1481-994,29.97,1920,1080,train\nZjN0kL_SVJw,16918,17090,481-109-1382-1010,29.97,1920,1080,train\nZjN0kL_SVJw,17706,18370,477-109-1388-1020,29.97,1920,1080,train\nZjN0kL_SVJw,18864,19106,628-182-1450-1004,29.97,1920,1080,train\nZjN0kL_SVJw,19248,19483,626-187-1431-992,29.97,1920,1080,train\nZjN0kL_SVJw,19574,19705,700-154-1523-977,29.97,1920,1080,train\nZjN0kL_SVJw,19995,20148,613-200-1412-999,29.97,1920,1080,train\nZjN0kL_SVJw,20148,20438,596-214-1423-1041,29.97,1920,1080,train\nZjN0kL_SVJw,20754,21251,526-182-1375-1031,29.97,1920,1080,train\nZjN0kL_SVJw,21463,21675,575-203-1396-1024,29.97,1920,1080,train\nZjN0kL_SVJw,21978,22118,565-206-1431-1072,29.97,1920,1080,train\nZjN0kL_SVJw,22364,22549,564-144-1419-999,29.97,1920,1080,train\nZjN0kL_SVJw,22627,22805,430-123-1344-1037,29.97,1920,1080,train\nZjN0kL_SVJw,23025,23480,440-94-1351-1005,29.97,1920,1080,train\nZjN0kL_SVJw,23672,24011,490-60-1457-1027,29.97,1920,1080,train\nZjN0kL_SVJw,24369,24544,500-150-1382-1032,29.97,1920,1080,train\nZjN0kL_SVJw,25051,25218,498-149-1376-1027,29.97,1920,1080,train\nZjN0kL_SVJw,26621,26807,473-111-1367-1005,29.97,1920,1080,train\nZjN0kL_SVJw,27127,27435,347-60-1277-990,29.97,1920,1080,train\nZjN0kL_SVJw,27740,28028,574-84-1531-1041,29.97,1920,1080,train\nZjN0kL_SVJw,28375,28601,423-77-1311-965,29.97,1920,1080,train\nZjN0kL_SVJw,28832,28963,319-64-1310-1055,29.97,1920,1080,train\nZjN0kL_SVJw,29329,29545,371-83-1337-1049,29.97,1920,1080,train\nZjN0kL_SVJw,29652,29809,543-75-1518-1050,29.97,1920,1080,train\nZjN0kL_SVJw,30249,30753,469-75-1428-1034,29.97,1920,1080,train\nZjN0kL_SVJw,31021,31151,551-84-1470-1003,29.97,1920,1080,train\nZjN0kL_SVJw,31176,31444,449-60-1400-1011,29.97,1920,1080,train\nZjN0kL_SVJw,31616,31947,386-94-1339-1047,29.97,1920,1080,train\nZjN0kL_SVJw,31977,32248,671-75-1618-1022,29.97,1920,1080,train\nZjN0kL_SVJw,32391,32575,485-140-1359-1014,29.97,1920,1080,train\nZjN0kL_SVJw,32575,32830,468-142-1383-1057,29.97,1920,1080,train\nZjN0kL_SVJw,32830,33120,480-99-1405-1024,29.97,1920,1080,train\nZjN0kL_SVJw,33497,33680,414-102-1315-1003,29.97,1920,1080,train\nZjN0kL_SVJw,33975,34175,571-177-1418-1024,29.97,1920,1080,train\nZjN0kL_SVJw,34260,34450,461-172-1345-1056,29.97,1920,1080,train\nZjN0kL_SVJw,34592,35099,470-96-1401-1027,29.97,1920,1080,train\nZjN0kL_SVJw,35586,35735,436-93-1387-1044,29.97,1920,1080,train\nZjN0kL_SVJw,35735,35919,655-156-1533-1034,29.97,1920,1080,train\nZjN0kL_SVJw,36098,36243,569-177-1425-1033,29.97,1920,1080,train\nZjN0kL_SVJw,36631,36898,426-109-1392-1075,29.97,1920,1080,train\nZjN0kL_SVJw,37391,37543,407-86-1373-1052,29.97,1920,1080,train\nZjN0kL_SVJw,37842,38109,464-103-1420-1059,29.97,1920,1080,train\nZjN0kL_SVJw,38109,38345,416-59-1369-1012,29.97,1920,1080,train\nZjN0kL_SVJw,39026,39156,540-174-1410-1044,29.97,1920,1080,train\nZjN0kL_SVJw,39519,39951,511-160-1351-1000,29.97,1920,1080,train\nZjN0kL_SVJw,40298,40634,500-155-1339-994,29.97,1920,1080,train\nZjN0kL_SVJw,40681,40819,525-129-1408-1012,29.97,1920,1080,train\nZjN0kL_SVJw,41084,41399,600-69-1536-1005,29.97,1920,1080,train\nZjN0kL_SVJw,42242,42392,550-143-1439-1032,29.97,1920,1080,train\nZjN0kL_SVJw,42392,42947,437-101-1348-1012,29.97,1920,1080,train\nZjN0kL_SVJw,42947,43160,464-122-1405-1063,29.97,1920,1080,train\nZjN0kL_SVJw,43560,43764,499-131-1394-1026,29.97,1920,1080,train\nZjN0kL_SVJw,44320,44604,446-65-1420-1039,29.97,1920,1080,train\nZjN0kL_SVJw,44822,44998,441-106-1380-1045,29.97,1920,1080,train\nZjN0kL_SVJw,45217,45352,474-25-1468-1019,29.97,1920,1080,train\nZjN0kL_SVJw,45463,45647,470-74-1425-1029,29.97,1920,1080,train\nZjN0kL_SVJw,45647,46118,516-27-1507-1018,29.97,1920,1080,train\nZjN0kL_SVJw,47084,47212,459-116-1422-1079,29.97,1920,1080,train\nZjN0kL_SVJw,47552,47970,411-59-1408-1056,29.97,1920,1080,train\nZjN0kL_SVJw,48147,48725,436-30-1445-1039,29.97,1920,1080,train\nZjN0kL_SVJw,48725,49050,682-81-1606-1005,29.97,1920,1080,train\nZjN0kL_SVJw,49753,49894,488-103-1403-1018,29.97,1920,1080,train\nZjN0kL_SVJw,49910,50138,467-56-1464-1053,29.97,1920,1080,train\nZjN0kL_SVJw,50507,50801,579-253-1280-954,29.97,1920,1080,train\nZjN0kL_SVJw,51795,52079,489-79-1412-1002,29.97,1920,1080,train\nZjN0kL_SVJw,52313,52812,478-177-1317-1016,29.97,1920,1080,train\nZjN0kL_SVJw,52968,53141,496-127-1334-965,29.97,1920,1080,train\nZjN0kL_SVJw,54177,54583,440-51-1442-1053,29.97,1920,1080,train\nZjN0kL_SVJw,54984,55128,543-97-1415-969,29.97,1920,1080,train\nZjN0kL_SVJw,55256,55425,520-190-1311-981,29.97,1920,1080,train\nZjN0kL_SVJw,56476,57029,471-56-1425-1010,29.97,1920,1080,train\nZjN0kL_SVJw,57533,57678,667-70-1622-1025,29.97,1920,1080,train\nZjN0kL_SVJw,57794,58094,500-63-1455-1018,29.97,1920,1080,train\nZjN0kL_SVJw,59433,59619,473-90-1394-1011,29.97,1920,1080,train\nZjN0kL_SVJw,60005,60236,445-41-1407-1003,29.97,1920,1080,train\nZjN0kL_SVJw,60236,60964,477-116-1411-1050,29.97,1920,1080,train\nZjN0kL_SVJw,61106,61308,558-107-1459-1008,29.97,1920,1080,train\nZjN0kL_SVJw,62100,62696,440-35-1476-1071,29.97,1920,1080,train\nZjN0kL_SVJw,63604,63847,534-125-1319-910,29.97,1920,1080,train\nZjN0kL_SVJw,64809,65833,483-70-1452-1039,29.97,1920,1080,train\nZjN0kL_SVJw,66046,66329,551-136-1383-968,29.97,1920,1080,train\nZjN0kL_SVJw,66965,67124,595-118-1481-1004,29.97,1920,1080,train\nZjN0kL_SVJw,67155,68081,526-117-1420-1011,29.97,1920,1080,train\nZjN0kL_SVJw,68179,68369,525-112-1376-963,29.97,1920,1080,train\nZjN0kL_SVJw,68494,68671,446-39-1445-1038,29.97,1920,1080,train\nZjN0kL_SVJw,68930,69343,434-46-1436-1048,29.97,1920,1080,train\nZjN0kL_SVJw,69642,69859,535-127-1446-1038,29.97,1920,1080,train\nZjN0kL_SVJw,70223,70396,640-199-1425-984,29.97,1920,1080,train\nZjN0kL_SVJw,72195,72374,598-186-1369-957,29.97,1920,1080,train\nZjN0kL_SVJw,72374,72640,589-146-1409-966,29.97,1920,1080,train\nZjN0kL_SVJw,73008,73137,526-212-1273-959,29.97,1920,1080,train\nZjN0kL_SVJw,73240,73380,673-267-1359-953,29.97,1920,1080,train\nZjN0kL_SVJw,73644,73779,556-164-1354-962,29.97,1920,1080,train\nZjN0kL_SVJw,74163,74487,502-156-1353-1007,29.97,1920,1080,train\nZjN0kL_SVJw,74693,74823,472-98-1355-981,29.97,1920,1080,train\nZjN0kL_SVJw,77783,78105,293-184-1024-915,29.97,1920,1080,train\nZjN0kL_SVJw,84420,84673,435-196-1163-924,29.97,1920,1080,train\nZjN0kL_SVJw,84901,85161,470-71-1437-1038,29.97,1920,1080,train\nZjN0kL_SVJw,85253,85513,423-19-1467-1063,29.97,1920,1080,train\nZjN0kL_SVJw,87050,88074,492-82-1417-1007,29.97,1920,1080,train\nZjN0kL_SVJw,88509,88751,529-161-1366-998,29.97,1920,1080,train\nZjN0kL_SVJw,88883,89056,579-176-1404-1001,29.97,1920,1080,train\nZjN0kL_SVJw,89056,89290,569-132-1437-1000,29.97,1920,1080,train\nZjN0kL_SVJw,89290,89565,537-177-1399-1039,29.97,1920,1080,train\nZjN0kL_SVJw,89567,89891,527-123-1433-1029,29.97,1920,1080,train\nZjN0kL_SVJw,90851,91195,570-178-1396-1004,29.97,1920,1080,train\nZjN0kL_SVJw,91442,91871,472-146-1326-1000,29.97,1920,1080,train\nZjN0kL_SVJw,92039,92215,581-120-1489-1028,29.97,1920,1080,train\nZjN0kL_SVJw,92223,92364,481-31-1450-1000,29.97,1920,1080,train\nZjN0kL_SVJw,93338,93652,464-52-1467-1055,29.97,1920,1080,train\nZjN0kL_SVJw,93653,93893,565-98-1479-1012,29.97,1920,1080,train\nZjN0kL_SVJw,93935,94135,468-109-1365-1006,29.97,1920,1080,train\nZjN0kL_SVJw,94183,94754,381-46-1352-1017,29.97,1920,1080,train\nZjN0kL_SVJw,94967,95169,468-101-1371-1004,29.97,1920,1080,train\nZjN0kL_SVJw,95169,95467,477-55-1446-1024,29.97,1920,1080,train\nZjN0kL_SVJw,95854,96270,481-82-1439-1040,29.97,1920,1080,train\nZjN0kL_SVJw,96581,97075,493-78-1456-1041,29.97,1920,1080,train\nZjN0kL_SVJw,97442,97937,457-67-1459-1069,29.97,1920,1080,train\nZjN0kL_SVJw,98039,98628,418-92-1362-1036,29.97,1920,1080,train\nFBuF0xOal9M,2445,2573,381-299-1150-1068,59.94,1920,1080,test\nFBuF0xOal9M,2697,2840,655-362-1362-1069,59.94,1920,1080,test\nFBuF0xOal9M,5168,5451,549-253-1357-1061,59.94,1920,1080,test\nFBuF0xOal9M,6989,7146,565-239-1404-1078,59.94,1920,1080,test\nFBuF0xOal9M,8657,8880,497-321-1251-1075,59.94,1920,1080,test\nFBuF0xOal9M,11184,11359,632-253-1452-1073,59.94,1920,1080,test\nFBuF0xOal9M,12781,12914,569-338-1303-1072,59.94,1920,1080,test\nFBuF0xOal9M,12914,13183,664-320-1399-1055,59.94,1920,1080,test\nFBuF0xOal9M,13311,13440,584-363-1290-1069,59.94,1920,1080,test\nFBuF0xOal9M,13521,13680,536-275-1333-1072,59.94,1920,1080,test\nFBuF0xOal9M,14632,14977,459-87-1441-1069,59.94,1920,1080,test\nFBuF0xOal9M,15166,15296,761-317-1507-1063,59.94,1920,1080,test\nFBuF0xOal9M,16204,16425,614-198-1423-1007,59.94,1920,1080,test\nFBuF0xOal9M,16845,17032,467-213-1255-1001,59.94,1920,1080,test\nFBuF0xOal9M,18334,18480,510-240-1262-992,59.94,1920,1080,test\nFBuF0xOal9M,18515,18662,643-279-1341-977,59.94,1920,1080,test\nFBuF0xOal9M,18892,19332,476-208-1280-1012,59.94,1920,1080,test\nFBuF0xOal9M,19516,19645,585-268-1347-1030,59.94,1920,1080,test\nFBuF0xOal9M,19762,19920,494-242-1258-1006,59.94,1920,1080,test\nFBuF0xOal9M,20546,20880,531-180-1359-1008,59.94,1920,1080,test\nFBuF0xOal9M,21432,21717,629-231-1424-1026,59.94,1920,1080,test\nFBuF0xOal9M,22427,22560,692-223-1518-1049,59.94,1920,1080,test\nFBuF0xOal9M,23027,23171,617-250-1371-1004,59.94,1920,1080,test\nFBuF0xOal9M,23520,23680,379-157-1268-1046,59.94,1920,1080,test\nFBuF0xOal9M,25129,25327,427-112-1360-1045,59.94,1920,1080,test\nFBuF0xOal9M,25690,25859,429-235-1223-1029,59.94,1920,1080,test\nFBuF0xOal9M,25920,26069,397-237-1181-1021,59.94,1920,1080,test\nFBuF0xOal9M,26990,27198,599-219-1436-1056,59.94,1920,1080,test\nFBuF0xOal9M,27360,27641,466-353-1154-1041,59.94,1920,1080,test\nFBuF0xOal9M,27676,27831,299-279-1063-1043,59.94,1920,1080,test\nFBuF0xOal9M,27831,27985,525-314-1259-1048,59.94,1920,1080,test\nFBuF0xOal9M,28148,28335,557-284-1309-1036,59.94,1920,1080,test\nFBuF0xOal9M,28446,28683,597-311-1339-1053,59.94,1920,1080,test\nFBuF0xOal9M,28903,29040,632-213-1490-1071,59.94,1920,1080,test\nFBuF0xOal9M,29146,29407,515-252-1342-1079,59.94,1920,1080,test\nFBuF0xOal9M,29520,29741,574-230-1357-1013,59.94,1920,1080,test\nFBuF0xOal9M,30073,30214,458-228-1252-1022,59.94,1920,1080,test\nFBuF0xOal9M,30241,30452,560-267-1307-1014,59.94,1920,1080,test\nFBuF0xOal9M,30639,30929,443-244-1243-1044,59.94,1920,1080,test\nFBuF0xOal9M,30929,31220,588-244-1358-1014,59.94,1920,1080,test\nFBuF0xOal9M,31760,31920,535-127-1418-1010,59.94,1920,1080,test\nFBuF0xOal9M,31920,32073,478-277-1209-1008,59.94,1920,1080,test\nFBuF0xOal9M,32312,32523,609-299-1316-1006,59.94,1920,1080,test\nFBuF0xOal9M,32611,32740,599-234-1371-1006,59.94,1920,1080,test\nFBuF0xOal9M,32744,32946,469-235-1220-986,59.94,1920,1080,test\nFBuF0xOal9M,33424,33581,680-241-1437-998,59.94,1920,1080,test\nFBuF0xOal9M,33930,34077,919-208-1703-992,59.94,1920,1080,test\nFBuF0xOal9M,37437,37599,560-209-1356-1005,59.94,1920,1080,test\nFBuF0xOal9M,37737,37992,511-277-1244-1010,59.94,1920,1080,test\nFBuF0xOal9M,38269,38400,540-234-1313-1007,59.94,1920,1080,test\nFBuF0xOal9M,40260,40473,568-294-1284-1010,59.94,1920,1080,test\nFBuF0xOal9M,42017,42216,462-132-1370-1040,59.94,1920,1080,test\nFBuF0xOal9M,42959,43131,666-256-1430-1020,59.94,1920,1080,test\nFBuF0xOal9M,43327,43575,529-151-1410-1032,59.94,1920,1080,test\nFBuF0xOal9M,44165,44384,553-205-1388-1040,59.94,1920,1080,test\nFBuF0xOal9M,45663,46051,487-178-1294-985,59.94,1920,1080,test\nFBuF0xOal9M,46320,46458,620-191-1453-1024,59.94,1920,1080,test\nFBuF0xOal9M,46555,46733,558-217-1340-999,59.94,1920,1080,test\nFBuF0xOal9M,46824,47542,509-108-1421-1020,59.94,1920,1080,test\n"
},
{
"path": "data/taichi256.csv",
"content": "distance,source,driving,frame\n3.54437869822485,ab28GAufK8o#000261#000596.mp4,aDyyTMUBoLE#000164#000351.mp4,0\n2.8639053254437887,DMEaUoA8EPE#000028#000354.mp4,0Q914by5A98#010440#010764.mp4,0\n2.153846153846153,L82WHgYRq6I#000021#000479.mp4,0Q914by5A98#010440#010764.mp4,0\n2.8994082840236666,oNkBx4CZuEg#000000#001024.mp4,DMEaUoA8EPE#000028#000354.mp4,0\n3.3905325443786998,ab28GAufK8o#000261#000596.mp4,uEqWZ9S_-Lw#000089#000581.mp4,0\n3.266272189349112,0Q914by5A98#010440#010764.mp4,ab28GAufK8o#000261#000596.mp4,0\n2.7514792899408294,WlDYrq8K6nk#008186#008512.mp4,OiblkvkAHWM#014331#014459.mp4,0\n3.0177514792899407,oNkBx4CZuEg#001024#002048.mp4,aDyyTMUBoLE#000375#000518.mp4,0\n3.4792899408284064,aDyyTMUBoLE#000164#000351.mp4,w2awOCDRtrc#001729#002009.mp4,0\n2.769230769230769,oNkBx4CZuEg#000000#001024.mp4,L82WHgYRq6I#000021#000479.mp4,0\n3.8047337278106514,ab28GAufK8o#000261#000596.mp4,w2awOCDRtrc#001729#002009.mp4,0\n3.4260355029585763,w2awOCDRtrc#001729#002009.mp4,oNkBx4CZuEg#000000#001024.mp4,0\n3.313609467455621,DMEaUoA8EPE#000028#000354.mp4,WlDYrq8K6nk#005943#006135.mp4,0\n3.8402366863905333,oNkBx4CZuEg#001024#002048.mp4,ab28GAufK8o#000261#000596.mp4,0\n3.3254437869822504,aDyyTMUBoLE#000164#000351.mp4,oNkBx4CZuEg#000000#001024.mp4,0\n1.2485207100591724,0Q914by5A98#010440#010764.mp4,aDyyTMUBoLE#000164#000351.mp4,0\n3.804733727810652,OiblkvkAHWM#006251#006533.mp4,aDyyTMUBoLE#000375#000518.mp4,0\n3.662721893491124,uEqWZ9S_-Lw#000089#000581.mp4,DMEaUoA8EPE#000028#000354.mp4,0\n3.230769230769233,A3ZmT97hAWU#000095#000678.mp4,ab28GAufK8o#000261#000596.mp4,0\n3.3668639053254434,w81Tr0Dp1K8#015329#015485.mp4,WlDYrq8K6nk#008186#008512.mp4,0\n3.313609467455621,WlDYrq8K6nk#005943#006135.mp4,DMEaUoA8EPE#000028#000354.mp4,0\n2.7514792899408294,OiblkvkAHWM#014331#014459.mp4,WlDYrq8K6nk#008186#008512.mp4,0\n1.964497041420118,L82WHgYRq6I#000021#000479.mp4,DMEaUoA8EPE#000028#000354.mp4,0\n3.78698224852071,FBuF0xOal9M#046824#047542.mp4,lCb5w6n8kPs#011879#012014.mp4,0\n3.92307692307692,ab28GAufK8o#000261#000596.mp4,L82WHgYRq6I#000021#000479.mp4,0\n3.8402366863905333,ab28GAufK8o#000261#000596.mp4,oNkBx4CZuEg#001024#002048.mp4,0\n3.828402366863905,ab28GAufK8o#000261#000596.mp4,OiblkvkAHWM#006251#006533.mp4,0\n2.041420118343196,L82WHgYRq6I#000021#000479.mp4,aDyyTMUBoLE#000164#000351.mp4,0\n3.2485207100591724,0Q914by5A98#010440#010764.mp4,w2awOCDRtrc#001729#002009.mp4,0\n3.2485207100591746,oNkBx4CZuEg#000000#001024.mp4,0Q914by5A98#010440#010764.mp4,0\n1.964497041420118,DMEaUoA8EPE#000028#000354.mp4,L82WHgYRq6I#000021#000479.mp4,0\n3.5266272189349115,kgvcI9oe3NI#001578#001763.mp4,lCb5w6n8kPs#004451#004631.mp4,0\n3.005917159763317,A3ZmT97hAWU#000095#000678.mp4,0Q914by5A98#010440#010764.mp4,0\n3.230769230769233,ab28GAufK8o#000261#000596.mp4,A3ZmT97hAWU#000095#000678.mp4,0\n3.5266272189349115,lCb5w6n8kPs#004451#004631.mp4,kgvcI9oe3NI#001578#001763.mp4,0\n2.769230769230769,L82WHgYRq6I#000021#000479.mp4,oNkBx4CZuEg#000000#001024.mp4,0\n3.165680473372782,WlDYrq8K6nk#005943#006135.mp4,w81Tr0Dp1K8#001375#001516.mp4,0\n2.8994082840236666,DMEaUoA8EPE#000028#000354.mp4,oNkBx4CZuEg#000000#001024.mp4,0\n2.4556213017751523,0Q914by5A98#010440#010764.mp4,mndSqTrxpts#000000#000175.mp4,0\n2.201183431952659,A3ZmT97hAWU#000095#000678.mp4,VMSqvTE90hk#007168#007312.mp4,0\n3.8047337278106514,w2awOCDRtrc#001729#002009.mp4,ab28GAufK8o#000261#000596.mp4,0\n3.769230769230769,uEqWZ9S_-Lw#000089#000581.mp4,0Q914by5A98#010440#010764.mp4,0\n3.6568047337278102,A3ZmT97hAWU#000095#000678.mp4,aDyyTMUBoLE#000164#000351.mp4,0\n3.7869822485207107,uEqWZ9S_-Lw#000089#000581.mp4,L82WHgYRq6I#000021#000479.mp4,0\n3.78698224852071,lCb5w6n8kPs#011879#012014.mp4,FBuF0xOal9M#046824#047542.mp4,0\n3.591715976331361,nAQEOC1Z10M#020177#020600.mp4,w81Tr0Dp1K8#004036#004218.mp4,0\n3.8757396449704156,uEqWZ9S_-Lw#000089#000581.mp4,aDyyTMUBoLE#000164#000351.mp4,0\n2.45562130177515,aDyyTMUBoLE#000164#000351.mp4,DMEaUoA8EPE#000028#000354.mp4,0\n3.5502958579881647,uEqWZ9S_-Lw#000089#000581.mp4,OiblkvkAHWM#006251#006533.mp4,0\n3.7928994082840224,aDyyTMUBoLE#000375#000518.mp4,ab28GAufK8o#000261#000596.mp4,0\n"
},
{
"path": "demo.ipynb",
"content": "{\n \"nbformat\": 4,\n \"nbformat_minor\": 0,\n \"metadata\": {\n \"colab\": {\n \"name\": \"first-order-model-demo\",\n \"provenance\": []\n },\n \"kernelspec\": {\n \"name\": \"python3\",\n \"display_name\": \"Python 3\"\n },\n \"accelerator\": \"GPU\"\n },\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {\n \"id\": \"view-in-github\",\n \"colab_type\": \"text\"\n },\n \"source\": [\n \"![\\\"Open](\\\"https://colab.research.google.com/assets/colab-badge.svg\\\")
\",\n \"![\\\"Kaggle\\\"](\\\"https://kaggle.com/static/images/open-in-kaggle.svg\\\" "\\\\"Open")
\"\n ]\n },\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {\n \"id\": \"cdO_RxQZLahB\"\n },\n \"source\": [\n \"# Demo for paper \\\"First Order Motion Model for Image Animation\\\"\\n\",\n \"To try the demo, press the 2 play buttons in order and scroll to the bottom. Note that it may take several minutes to load.\"\n ]\n },\n {\n \"cell_type\": \"code\",\n \"metadata\": {\n \"id\": \"UCMFMJV7K-ag\"\n },\n \"source\": [\n \"%%capture\\n\",\n \"%pip install ffmpeg-python imageio-ffmpeg\\n\",\n \"!git init .\\n\",\n \"!git remote add origin https://github.com/AliaksandrSiarohin/first-order-model\\n\",\n \"!git pull origin master\\n\",\n \"!git clone https://github.com/graphemecluster/first-order-model-demo demo\"\n ],\n \"execution_count\": null,\n \"outputs\": []\n },\n {\n \"cell_type\": \"code\",\n \"metadata\": {\n \"id\": \"Oxi6-riLOgnm\"\n },\n \"source\": [\n \"import IPython.display\\n\",\n \"import PIL.Image\\n\",\n \"import cv2\\n\",\n \"import ffmpeg\\n\",\n \"import imageio\\n\",\n \"import io\\n\",\n \"import ipywidgets\\n\",\n \"import numpy\\n\",\n \"import os.path\\n\",\n \"import requests\\n\",\n \"import skimage.transform\\n\",\n \"import warnings\\n\",\n \"from base64 import b64encode\\n\",\n \"from demo import load_checkpoints, make_animation # type: ignore (local file)\\n\",\n \"from google.colab import files, output\\n\",\n \"from IPython.display import HTML, Javascript\\n\",\n \"from shutil import copyfileobj\\n\",\n \"from skimage import img_as_ubyte\\n\",\n \"from tempfile import NamedTemporaryFile\\n\",\n \"from tqdm.auto import tqdm\\n\",\n \"warnings.filterwarnings(\\\"ignore\\\")\\n\",\n \"os.makedirs(\\\"user\\\", exist_ok=True)\\n\",\n \"\\n\",\n \"display(HTML(\\\"\\\"\\\"\\n\",\n \"\\n\",\n \"\\\"\\\"\\\"))\\n\",\n \"\\n\",\n \"def thumbnail(file):\\n\",\n \"\\treturn imageio.get_reader(file, mode='I', format='FFMPEG').get_next_data()\\n\",\n \"\\n\",\n \"def create_image(i, j):\\n\",\n \"\\timage_widget = ipywidgets.Image.from_file('demo/images/%d%d.png' % (i, j))\\n\",\n \"\\timage_widget.add_class('resource')\\n\",\n \"\\timage_widget.add_class('resource-image')\\n\",\n \"\\timage_widget.add_class('resource-image%d%d' % (i, j))\\n\",\n \"\\treturn image_widget\\n\",\n \"\\n\",\n \"def create_video(i):\\n\",\n \"\\tvideo_widget = ipywidgets.Image(\\n\",\n \"\\t\\tvalue=cv2.imencode('.png', cv2.cvtColor(thumbnail('demo/videos/%d.mp4' % i), cv2.COLOR_RGB2BGR))[1].tostring(),\\n\",\n \"\\t\\tformat='png'\\n\",\n \"\\t)\\n\",\n \"\\tvideo_widget.add_class('resource')\\n\",\n \"\\tvideo_widget.add_class('resource-video')\\n\",\n \"\\tvideo_widget.add_class('resource-video%d' % i)\\n\",\n \"\\treturn video_widget\\n\",\n \"\\n\",\n \"def create_title(title):\\n\",\n \"\\ttitle_widget = ipywidgets.Label(title)\\n\",\n \"\\ttitle_widget.add_class('title')\\n\",\n \"\\treturn title_widget\\n\",\n \"\\n\",\n \"def download_output(button):\\n\",\n \"\\tcomplete.layout.display = 'none'\\n\",\n \"\\tloading.layout.display = ''\\n\",\n \"\\tfiles.download('output.mp4')\\n\",\n \"\\tloading.layout.display = 'none'\\n\",\n \"\\tcomplete.layout.display = ''\\n\",\n \"\\n\",\n \"def convert_output(button):\\n\",\n \"\\tcomplete.layout.display = 'none'\\n\",\n \"\\tloading.layout.display = ''\\n\",\n \"\\tffmpeg.input('output.mp4').output('scaled.mp4', vf='scale=1080x1080:flags=lanczos,pad=1920:1080:420:0').overwrite_output().run()\\n\",\n \"\\tfiles.download('scaled.mp4')\\n\",\n \"\\tloading.layout.display = 'none'\\n\",\n \"\\tcomplete.layout.display = ''\\n\",\n \"\\n\",\n \"def back_to_main(button):\\n\",\n \"\\tcomplete.layout.display = 'none'\\n\",\n \"\\tmain.layout.display = ''\\n\",\n \"\\n\",\n \"label_or = ipywidgets.Label('or')\\n\",\n \"label_or.add_class('label-or')\\n\",\n \"\\n\",\n \"image_titles = ['Peoples', 'Cartoons', 'Dolls', 'Game of Thrones', 'Statues']\\n\",\n \"image_lengths = [8, 4, 8, 9, 4]\\n\",\n \"\\n\",\n \"image_tab = ipywidgets.Tab()\\n\",\n \"image_tab.children = [ipywidgets.HBox([create_image(i, j) for j in range(length)]) for i, length in enumerate(image_lengths)]\\n\",\n \"for i, title in enumerate(image_titles):\\n\",\n \"\\timage_tab.set_title(i, title)\\n\",\n \"\\n\",\n \"input_image_widget = ipywidgets.Output()\\n\",\n \"input_image_widget.add_class('input-widget')\\n\",\n \"upload_input_image_button = ipywidgets.FileUpload(accept='image/*', button_style='primary')\\n\",\n \"upload_input_image_button.add_class('input-button')\\n\",\n \"image_part = ipywidgets.HBox([\\n\",\n \"\\tipywidgets.VBox([input_image_widget, upload_input_image_button]),\\n\",\n \"\\tlabel_or,\\n\",\n \"\\timage_tab\\n\",\n \"])\\n\",\n \"\\n\",\n \"video_tab = ipywidgets.Tab()\\n\",\n \"video_tab.children = [ipywidgets.HBox([create_video(i) for i in range(5)])]\\n\",\n \"video_tab.set_title(0, 'All Videos')\\n\",\n \"\\n\",\n \"input_video_widget = ipywidgets.Output()\\n\",\n \"input_video_widget.add_class('input-widget')\\n\",\n \"upload_input_video_button = ipywidgets.FileUpload(accept='video/*', button_style='primary')\\n\",\n \"upload_input_video_button.add_class('input-button')\\n\",\n \"video_part = ipywidgets.HBox([\\n\",\n \"\\tipywidgets.VBox([input_video_widget, upload_input_video_button]),\\n\",\n \"\\tlabel_or,\\n\",\n \"\\tvideo_tab\\n\",\n \"])\\n\",\n \"\\n\",\n \"model = ipywidgets.Dropdown(\\n\",\n \"\\tdescription=\\\"Model:\\\",\\n\",\n \"\\toptions=[\\n\",\n \"\\t\\t'vox',\\n\",\n \"\\t\\t'vox-adv',\\n\",\n \"\\t\\t'taichi',\\n\",\n \"\\t\\t'taichi-adv',\\n\",\n \"\\t\\t'nemo',\\n\",\n \"\\t\\t'mgif',\\n\",\n \"\\t\\t'fashion',\\n\",\n \"\\t\\t'bair'\\n\",\n \"\\t]\\n\",\n \")\\n\",\n \"warning = ipywidgets.HTML('Warning: Upload your own images and videos (see README)')\\n\",\n \"warning.add_class('warning')\\n\",\n \"model_part = ipywidgets.HBox([model, warning])\\n\",\n \"\\n\",\n \"relative = ipywidgets.Checkbox(description=\\\"Relative keypoint displacement (Inherit object proporions from the video)\\\", value=True)\\n\",\n \"adapt_movement_scale = ipywidgets.Checkbox(description=\\\"Adapt movement scale (Don’t touch unless you know want you are doing)\\\", value=True)\\n\",\n \"generate_button = ipywidgets.Button(description=\\\"Generate\\\", button_style='primary')\\n\",\n \"main = ipywidgets.VBox([\\n\",\n \"\\tcreate_title('Choose Image'),\\n\",\n \"\\timage_part,\\n\",\n \"\\tcreate_title('Choose Video'),\\n\",\n \"\\tvideo_part,\\n\",\n \"\\tcreate_title('Settings'),\\n\",\n \"\\tmodel_part,\\n\",\n \"\\trelative,\\n\",\n \"\\tadapt_movement_scale,\\n\",\n \"\\tgenerate_button\\n\",\n \"])\\n\",\n \"\\n\",\n \"loader = ipywidgets.Label()\\n\",\n \"loader.add_class(\\\"loader\\\")\\n\",\n \"loading_label = ipywidgets.Label(\\\"This may take several minutes to process…\\\")\\n\",\n \"loading_label.add_class(\\\"loading-label\\\")\\n\",\n \"progress_bar = ipywidgets.Output()\\n\",\n \"loading = ipywidgets.VBox([loader, loading_label, progress_bar])\\n\",\n \"loading.add_class('loading')\\n\",\n \"\\n\",\n \"output_widget = ipywidgets.Output()\\n\",\n \"output_widget.add_class('output-widget')\\n\",\n \"download = ipywidgets.Button(description='Download', button_style='primary')\\n\",\n \"download.add_class('output-button')\\n\",\n \"download.on_click(download_output)\\n\",\n \"convert = ipywidgets.Button(description='Convert to 1920×1080', button_style='primary')\\n\",\n \"convert.add_class('output-button')\\n\",\n \"convert.on_click(convert_output)\\n\",\n \"back = ipywidgets.Button(description='Back', button_style='primary')\\n\",\n \"back.add_class('output-button')\\n\",\n \"back.on_click(back_to_main)\\n\",\n \"\\n\",\n \"comparison_widget = ipywidgets.Output()\\n\",\n \"comparison_widget.add_class('comparison-widget')\\n\",\n \"comparison_label = ipywidgets.Label('Comparison')\\n\",\n \"comparison_label.add_class('comparison-label')\\n\",\n \"complete = ipywidgets.HBox([\\n\",\n \"\\tipywidgets.VBox([output_widget, download, convert, back]),\\n\",\n \"\\tipywidgets.VBox([comparison_widget, comparison_label])\\n\",\n \"])\\n\",\n \"\\n\",\n \"display(ipywidgets.VBox([main, loading, complete]))\\n\",\n \"display(Javascript(\\\"\\\"\\\"\\n\",\n \"var images, videos;\\n\",\n \"function deselectImages() {\\n\",\n \"\\timages.forEach(function(item) {\\n\",\n \"\\t\\titem.classList.remove(\\\"selected\\\");\\n\",\n \"\\t});\\n\",\n \"}\\n\",\n \"function deselectVideos() {\\n\",\n \"\\tvideos.forEach(function(item) {\\n\",\n \"\\t\\titem.classList.remove(\\\"selected\\\");\\n\",\n \"\\t});\\n\",\n \"}\\n\",\n \"function invokePython(func) {\\n\",\n \"\\tgoogle.colab.kernel.invokeFunction(\\\"notebook.\\\" + func, [].slice.call(arguments, 1), {});\\n\",\n \"}\\n\",\n \"setTimeout(function() {\\n\",\n \"\\t(images = [].slice.call(document.getElementsByClassName(\\\"resource-image\\\"))).forEach(function(item) {\\n\",\n \"\\t\\titem.addEventListener(\\\"click\\\", function() {\\n\",\n \"\\t\\t\\tdeselectImages();\\n\",\n \"\\t\\t\\titem.classList.add(\\\"selected\\\");\\n\",\n \"\\t\\t\\tinvokePython(\\\"select_image\\\", item.className.match(/resource-image(\\\\d\\\\d)/)[1]);\\n\",\n \"\\t\\t});\\n\",\n \"\\t});\\n\",\n \"\\timages[0].classList.add(\\\"selected\\\");\\n\",\n \"\\t(videos = [].slice.call(document.getElementsByClassName(\\\"resource-video\\\"))).forEach(function(item) {\\n\",\n \"\\t\\titem.addEventListener(\\\"click\\\", function() {\\n\",\n \"\\t\\t\\tdeselectVideos();\\n\",\n \"\\t\\t\\titem.classList.add(\\\"selected\\\");\\n\",\n \"\\t\\t\\tinvokePython(\\\"select_video\\\", item.className.match(/resource-video(\\\\d)/)[1]);\\n\",\n \"\\t\\t});\\n\",\n \"\\t});\\n\",\n \"\\tvideos[0].classList.add(\\\"selected\\\");\\n\",\n \"}, 1000);\\n\",\n \"\\\"\\\"\\\"))\\n\",\n \"\\n\",\n \"selected_image = None\\n\",\n \"def select_image(filename):\\n\",\n \"\\tglobal selected_image\\n\",\n \"\\tselected_image = resize(PIL.Image.open('demo/images/%s.png' % filename).convert(\\\"RGB\\\"))\\n\",\n \"\\tinput_image_widget.clear_output(wait=True)\\n\",\n \"\\twith input_image_widget:\\n\",\n \"\\t\\tdisplay(HTML('Image'))\\n\",\n \"\\tinput_image_widget.remove_class('uploaded')\\n\",\n \"output.register_callback(\\\"notebook.select_image\\\", select_image)\\n\",\n \"\\n\",\n \"selected_video = None\\n\",\n \"def select_video(filename):\\n\",\n \"\\tglobal selected_video\\n\",\n \"\\tselected_video = 'demo/videos/%s.mp4' % filename\\n\",\n \"\\tinput_video_widget.clear_output(wait=True)\\n\",\n \"\\twith input_video_widget:\\n\",\n \"\\t\\tdisplay(HTML('Video'))\\n\",\n \"\\tinput_video_widget.remove_class('uploaded')\\n\",\n \"output.register_callback(\\\"notebook.select_video\\\", select_video)\\n\",\n \"\\n\",\n \"def resize(image, size=(256, 256)):\\n\",\n \"\\tw, h = image.size\\n\",\n \"\\td = min(w, h)\\n\",\n \"\\tr = ((w - d) // 2, (h - d) // 2, (w + d) // 2, (h + d) // 2)\\n\",\n \"\\treturn image.resize(size, resample=PIL.Image.LANCZOS, box=r)\\n\",\n \"\\n\",\n \"def upload_image(change):\\n\",\n \"\\tglobal selected_image\\n\",\n \"\\tfor name, file_info in upload_input_image_button.value.items():\\n\",\n \"\\t\\tcontent = file_info['content']\\n\",\n \"\\tif content is not None:\\n\",\n \"\\t\\tselected_image = resize(PIL.Image.open(io.BytesIO(content)).convert(\\\"RGB\\\"))\\n\",\n \"\\t\\tinput_image_widget.clear_output(wait=True)\\n\",\n \"\\t\\twith input_image_widget:\\n\",\n \"\\t\\t\\tdisplay(selected_image)\\n\",\n \"\\t\\tinput_image_widget.add_class('uploaded')\\n\",\n \"\\t\\tdisplay(Javascript('deselectImages()'))\\n\",\n \"upload_input_image_button.observe(upload_image, names='value')\\n\",\n \"\\n\",\n \"def upload_video(change):\\n\",\n \"\\tglobal selected_video\\n\",\n \"\\tfor name, file_info in upload_input_video_button.value.items():\\n\",\n \"\\t\\tcontent = file_info['content']\\n\",\n \"\\tif content is not None:\\n\",\n \"\\t\\tselected_video = 'user/' + name\\n\",\n \"\\t\\twith open(selected_video, 'wb') as video:\\n\",\n \"\\t\\t\\tvideo.write(content)\\n\",\n \"\\t\\tpreview = resize(PIL.Image.fromarray(thumbnail(selected_video)).convert(\\\"RGB\\\"))\\n\",\n \"\\t\\tinput_video_widget.clear_output(wait=True)\\n\",\n \"\\t\\twith input_video_widget:\\n\",\n \"\\t\\t\\tdisplay(preview)\\n\",\n \"\\t\\tinput_video_widget.add_class('uploaded')\\n\",\n \"\\t\\tdisplay(Javascript('deselectVideos()'))\\n\",\n \"upload_input_video_button.observe(upload_video, names='value')\\n\",\n \"\\n\",\n \"def change_model(change):\\n\",\n \"\\tif model.value.startswith('vox'):\\n\",\n \"\\t\\twarning.remove_class('warn')\\n\",\n \"\\telse:\\n\",\n \"\\t\\twarning.add_class('warn')\\n\",\n \"model.observe(change_model, names='value')\\n\",\n \"\\n\",\n \"def generate(button):\\n\",\n \"\\tmain.layout.display = 'none'\\n\",\n \"\\tloading.layout.display = ''\\n\",\n \"\\tfilename = model.value + ('' if model.value == 'fashion' else '-cpk') + '.pth.tar'\\n\",\n \"\\tif not os.path.isfile(filename):\\n\",\n \"\\t\\tresponse = requests.get('https://github.com/graphemecluster/first-order-model-demo/releases/download/checkpoints/' + filename, stream=True)\\n\",\n \"\\t\\twith progress_bar:\\n\",\n \"\\t\\t\\twith tqdm.wrapattr(response.raw, 'read', total=int(response.headers.get('Content-Length', 0)), unit='B', unit_scale=True, unit_divisor=1024) as raw:\\n\",\n \"\\t\\t\\t\\twith open(filename, 'wb') as file:\\n\",\n \"\\t\\t\\t\\t\\tcopyfileobj(raw, file)\\n\",\n \"\\t\\tprogress_bar.clear_output()\\n\",\n \"\\treader = imageio.get_reader(selected_video, mode='I', format='FFMPEG')\\n\",\n \"\\tfps = reader.get_meta_data()['fps']\\n\",\n \"\\tdriving_video = []\\n\",\n \"\\tfor frame in reader:\\n\",\n \"\\t\\tdriving_video.append(frame)\\n\",\n \"\\tgenerator, kp_detector = load_checkpoints(config_path='config/%s-256.yaml' % model.value, checkpoint_path=filename)\\n\",\n \"\\twith progress_bar:\\n\",\n \"\\t\\tpredictions = make_animation(\\n\",\n \"\\t\\t\\tskimage.transform.resize(numpy.asarray(selected_image), (256, 256)),\\n\",\n \"\\t\\t\\t[skimage.transform.resize(frame, (256, 256)) for frame in driving_video],\\n\",\n \"\\t\\t\\tgenerator,\\n\",\n \"\\t\\t\\tkp_detector,\\n\",\n \"\\t\\t\\trelative=relative.value,\\n\",\n \"\\t\\t\\tadapt_movement_scale=adapt_movement_scale.value\\n\",\n \"\\t\\t)\\n\",\n \"\\tprogress_bar.clear_output()\\n\",\n \"\\timageio.mimsave('output.mp4', [img_as_ubyte(frame) for frame in predictions], fps=fps)\\n\",\n \"\\ttry:\\n\",\n \"\\t\\twith NamedTemporaryFile(suffix='.mp4') as output:\\n\",\n \"\\t\\t\\tffmpeg.output(ffmpeg.input('output.mp4').video, ffmpeg.input(selected_video).audio, output.name, c='copy').run()\\n\",\n \"\\t\\t\\twith open('output.mp4', 'wb') as result:\\n\",\n \"\\t\\t\\t\\tcopyfileobj(output, result)\\n\",\n \"\\texcept ffmpeg.Error:\\n\",\n \"\\t\\tpass\\n\",\n \"\\toutput_widget.clear_output(True)\\n\",\n \"\\twith output_widget:\\n\",\n \"\\t\\tvideo_widget = ipywidgets.Video.from_file('output.mp4', autoplay=False, loop=False)\\n\",\n \"\\t\\tvideo_widget.add_class('video')\\n\",\n \"\\t\\tvideo_widget.add_class('video-left')\\n\",\n \"\\t\\tdisplay(video_widget)\\n\",\n \"\\tcomparison_widget.clear_output(True)\\n\",\n \"\\twith comparison_widget:\\n\",\n \"\\t\\tvideo_widget = ipywidgets.Video.from_file(selected_video, autoplay=False, loop=False, controls=False)\\n\",\n \"\\t\\tvideo_widget.add_class('video')\\n\",\n \"\\t\\tvideo_widget.add_class('video-right')\\n\",\n \"\\t\\tdisplay(video_widget)\\n\",\n \"\\tdisplay(Javascript(\\\"\\\"\\\"\\n\",\n \"\\tsetTimeout(function() {\\n\",\n \"\\t\\t(function(left, right) {\\n\",\n \"\\t\\t\\tleft.addEventListener(\\\"play\\\", function() {\\n\",\n \"\\t\\t\\t\\tright.play();\\n\",\n \"\\t\\t\\t});\\n\",\n \"\\t\\t\\tleft.addEventListener(\\\"pause\\\", function() {\\n\",\n \"\\t\\t\\t\\tright.pause();\\n\",\n \"\\t\\t\\t});\\n\",\n \"\\t\\t\\tleft.addEventListener(\\\"seeking\\\", function() {\\n\",\n \"\\t\\t\\t\\tright.currentTime = left.currentTime;\\n\",\n \"\\t\\t\\t});\\n\",\n \"\\t\\t\\tright.muted = true;\\n\",\n \"\\t\\t})(document.getElementsByClassName(\\\"video-left\\\")[0], document.getElementsByClassName(\\\"video-right\\\")[0]);\\n\",\n \"\\t}, 1000);\\n\",\n \"\\t\\\"\\\"\\\"))\\n\",\n \"\\tloading.layout.display = 'none'\\n\",\n \"\\tcomplete.layout.display = ''\\n\",\n \"\\n\",\n \"generate_button.on_click(generate)\\n\",\n \"\\n\",\n \"loading.layout.display = 'none'\\n\",\n \"complete.layout.display = 'none'\\n\",\n \"select_image('00')\\n\",\n \"select_video('0')\"\n ],\n \"execution_count\": null,\n \"outputs\": []\n }\n ]\n}\n"
},
{
"path": "demo.py",
"content": "import sys\nimport yaml\nfrom argparse import ArgumentParser\nfrom tqdm.auto import tqdm\n\nimport imageio\nimport numpy as np\nfrom skimage.transform import resize\nfrom skimage import img_as_ubyte\nimport torch\nfrom sync_batchnorm import DataParallelWithCallback\n\nfrom modules.generator import OcclusionAwareGenerator\nfrom modules.keypoint_detector import KPDetector\nfrom animate import normalize_kp\n\nimport ffmpeg\nfrom os.path import splitext\nfrom shutil import copyfileobj\nfrom tempfile import NamedTemporaryFile\n\nif sys.version_info[0] < 3:\n raise Exception(\"You must use Python 3 or higher. Recommended version is Python 3.7\")\n\ndef load_checkpoints(config_path, checkpoint_path, cpu=False):\n\n with open(config_path) as f:\n config = yaml.full_load(f)\n\n generator = OcclusionAwareGenerator(**config['model_params']['generator_params'],\n **config['model_params']['common_params'])\n if not cpu:\n generator.cuda()\n\n kp_detector = KPDetector(**config['model_params']['kp_detector_params'],\n **config['model_params']['common_params'])\n if not cpu:\n kp_detector.cuda()\n\n if cpu:\n checkpoint = torch.load(checkpoint_path, map_location=torch.device('cpu'))\n else:\n checkpoint = torch.load(checkpoint_path)\n\n generator.load_state_dict(checkpoint['generator'])\n kp_detector.load_state_dict(checkpoint['kp_detector'])\n\n if not cpu:\n generator = DataParallelWithCallback(generator)\n kp_detector = DataParallelWithCallback(kp_detector)\n\n generator.eval()\n kp_detector.eval()\n\n return generator, kp_detector\n\n\ndef make_animation(source_image, driving_video, generator, kp_detector, relative=True, adapt_movement_scale=True, cpu=False):\n with torch.no_grad():\n predictions = []\n source = torch.tensor(source_image[np.newaxis].astype(np.float32)).permute(0, 3, 1, 2)\n if not cpu:\n source = source.cuda()\n driving = torch.tensor(np.array(driving_video)[np.newaxis].astype(np.float32)).permute(0, 4, 1, 2, 3)\n kp_source = kp_detector(source)\n kp_driving_initial = kp_detector(driving[:, :, 0])\n\n for frame_idx in tqdm(range(driving.shape[2])):\n driving_frame = driving[:, :, frame_idx]\n if not cpu:\n driving_frame = driving_frame.cuda()\n kp_driving = kp_detector(driving_frame)\n kp_norm = normalize_kp(kp_source=kp_source, kp_driving=kp_driving,\n kp_driving_initial=kp_driving_initial, use_relative_movement=relative,\n use_relative_jacobian=relative, adapt_movement_scale=adapt_movement_scale)\n out = generator(source, kp_source=kp_source, kp_driving=kp_norm)\n\n predictions.append(np.transpose(out['prediction'].data.cpu().numpy(), [0, 2, 3, 1])[0])\n return predictions\n\ndef find_best_frame(source, driving, cpu=False):\n import face_alignment # type: ignore (local file)\n from scipy.spatial import ConvexHull\n\n def normalize_kp(kp):\n kp = kp - kp.mean(axis=0, keepdims=True)\n area = ConvexHull(kp[:, :2]).volume\n area = np.sqrt(area)\n kp[:, :2] = kp[:, :2] / area\n return kp\n\n fa = face_alignment.FaceAlignment(face_alignment.LandmarksType._2D, flip_input=True,\n device='cpu' if cpu else 'cuda')\n kp_source = fa.get_landmarks(255 * source)[0]\n kp_source = normalize_kp(kp_source)\n norm = float('inf')\n frame_num = 0\n for i, image in tqdm(enumerate(driving)):\n kp_driving = fa.get_landmarks(255 * image)[0]\n kp_driving = normalize_kp(kp_driving)\n new_norm = (np.abs(kp_source - kp_driving) ** 2).sum()\n if new_norm < norm:\n norm = new_norm\n frame_num = i\n return frame_num\n\nif __name__ == \"__main__\":\n parser = ArgumentParser()\n parser.add_argument(\"--config\", required=True, help=\"path to config\")\n parser.add_argument(\"--checkpoint\", default='vox-cpk.pth.tar', help=\"path to checkpoint to restore\")\n\n parser.add_argument(\"--source_image\", default='sup-mat/source.png', help=\"path to source image\")\n parser.add_argument(\"--driving_video\", default='driving.mp4', help=\"path to driving video\")\n parser.add_argument(\"--result_video\", default='result.mp4', help=\"path to output\")\n\n parser.add_argument(\"--relative\", dest=\"relative\", action=\"store_true\", help=\"use relative or absolute keypoint coordinates\")\n parser.add_argument(\"--adapt_scale\", dest=\"adapt_scale\", action=\"store_true\", help=\"adapt movement scale based on convex hull of keypoints\")\n\n parser.add_argument(\"--find_best_frame\", dest=\"find_best_frame\", action=\"store_true\",\n help=\"Generate from the frame that is the most alligned with source. (Only for faces, requires face_aligment lib)\")\n\n parser.add_argument(\"--best_frame\", dest=\"best_frame\", type=int, default=None, help=\"Set frame to start from.\")\n\n parser.add_argument(\"--cpu\", dest=\"cpu\", action=\"store_true\", help=\"cpu mode.\")\n\n parser.add_argument(\"--audio\", dest=\"audio\", action=\"store_true\", help=\"copy audio to output from the driving video\" )\n\n parser.set_defaults(relative=False)\n parser.set_defaults(adapt_scale=False)\n parser.set_defaults(audio_on=False)\n\n opt = parser.parse_args()\n\n source_image = imageio.imread(opt.source_image)\n reader = imageio.get_reader(opt.driving_video)\n fps = reader.get_meta_data()['fps']\n driving_video = []\n try:\n for im in reader:\n driving_video.append(im)\n except RuntimeError:\n pass\n reader.close()\n\n source_image = resize(source_image, (256, 256))[..., :3]\n driving_video = [resize(frame, (256, 256))[..., :3] for frame in driving_video]\n generator, kp_detector = load_checkpoints(config_path=opt.config, checkpoint_path=opt.checkpoint, cpu=opt.cpu)\n\n if opt.find_best_frame or opt.best_frame is not None:\n i = opt.best_frame if opt.best_frame is not None else find_best_frame(source_image, driving_video, cpu=opt.cpu)\n print(\"Best frame: \" + str(i))\n driving_forward = driving_video[i:]\n driving_backward = driving_video[:(i+1)][::-1]\n predictions_forward = make_animation(source_image, driving_forward, generator, kp_detector, relative=opt.relative, adapt_movement_scale=opt.adapt_scale, cpu=opt.cpu)\n predictions_backward = make_animation(source_image, driving_backward, generator, kp_detector, relative=opt.relative, adapt_movement_scale=opt.adapt_scale, cpu=opt.cpu)\n predictions = predictions_backward[::-1] + predictions_forward[1:]\n else:\n predictions = make_animation(source_image, driving_video, generator, kp_detector, relative=opt.relative, adapt_movement_scale=opt.adapt_scale, cpu=opt.cpu)\n imageio.mimsave(opt.result_video, [img_as_ubyte(frame) for frame in predictions], fps=fps)\n\n if opt.audio:\n try:\n with NamedTemporaryFile(suffix=splitext(opt.result_video)[1]) as output:\n ffmpeg.output(ffmpeg.input(opt.result_video).video, ffmpeg.input(opt.driving_video).audio, output.name, c='copy').run()\n with open(opt.result_video, 'wb') as result:\n copyfileobj(output, result)\n except ffmpeg.Error:\n print(\"Failed to copy audio: the driving video may have no audio track or the audio format is invalid.\")\n"
},
{
"path": "demo_jupyter.ipynb",
"content": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {\n \"colab_type\": \"text\",\n \"id\": \"view-in-github\"\n },\n \"source\": [\n \"\"\n ]\n },\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {\n \"id\": \"cdO_RxQZLahB\"\n },\n \"source\": [\n \"# Demo for paper \\\"First Order Motion Model for Image Animation\\\"\\n\",\n \"To try the demo, press the 2 play buttons in order and scroll to the bottom. Note that it may take several minutes to load.\"\n ]\n },\n {\n \"cell_type\": \"code\",\n \"execution_count\": 4,\n \"metadata\": {\n \"id\": \"UCMFMJV7K-ag\"\n },\n \"outputs\": [],\n \"source\": [\n \"%%capture\\n\",\n \"%pip install ffmpeg-python imageio-ffmpeg\\n\",\n \"!git init .\\n\",\n \"!git remote add origin https://github.com/AliaksandrSiarohin/first-order-model\\n\",\n \"!git pull origin master\\n\",\n \"!git clone https://github.com/graphemecluster/first-order-model-demo demo\"\n ]\n },\n {\n \"cell_type\": \"code\",\n \"execution_count\": 104,\n \"metadata\": {\n \"id\": \"Oxi6-riLOgnm\"\n },\n \"outputs\": [\n {\n \"data\": {\n \"text/html\": [\n \"\\n\",\n \"\\n\"\n ],\n \"text/plain\": [\n \"\"\n ]\n },\n \"metadata\": {},\n \"output_type\": \"display_data\"\n },\n {\n \"data\": {\n \"application/vnd.jupyter.widget-view+json\": {\n \"model_id\": \"f53c7ccd3ec34f7ea8491237d5bf03ff\",\n \"version_major\": 2,\n \"version_minor\": 0\n },\n \"text/plain\": [\n \"VBox(children=(VBox(children=(Label(value='Choose Image', _dom_classes=('title',)), HBox(children=(VBox(childr…\"\n ]\n },\n \"metadata\": {},\n \"output_type\": \"display_data\"\n },\n {\n \"data\": {\n \"application/javascript\": [\n \"\\n\",\n \"var images, videos;\\n\",\n \"function deselectImages() {\\n\",\n \"\\timages.forEach(function(item) {\\n\",\n \"\\t\\titem.classList.remove(\\\"selected\\\");\\n\",\n \"\\t});\\n\",\n \"}\\n\",\n \"function deselectVideos() {\\n\",\n \"\\tvideos.forEach(function(item) {\\n\",\n \"\\t\\titem.classList.remove(\\\"selected\\\");\\n\",\n \"\\t});\\n\",\n \"}\\n\",\n \"function invokePython(func) {\\n\",\n \"\\tgoogle.colab.kernel.invokeFunction(\\\"notebook.\\\" + func, [].slice.call(arguments, 1), {});\\n\",\n \"}\\n\",\n \"setTimeout(function() {\\n\",\n \"\\t(images = [].slice.call(document.getElementsByClassName(\\\"resource-image\\\"))).forEach(function(item) {\\n\",\n \"\\t\\titem.addEventListener(\\\"click\\\", function() {\\n\",\n \"\\t\\t\\tdeselectImages();\\n\",\n \"\\t\\t\\titem.classList.add(\\\"selected\\\");\\n\",\n \"\\t\\t\\tinvokePython(\\\"select_image\\\", item.className.match(/resource-image(\\\\d\\\\d)/)[1]);\\n\",\n \"\\t\\t});\\n\",\n \"\\t});\\n\",\n \"\\timages[0].classList.add(\\\"selected\\\");\\n\",\n \"\\t(videos = [].slice.call(document.getElementsByClassName(\\\"resource-video\\\"))).forEach(function(item) {\\n\",\n \"\\t\\titem.addEventListener(\\\"click\\\", function() {\\n\",\n \"\\t\\t\\tdeselectVideos();\\n\",\n \"\\t\\t\\titem.classList.add(\\\"selected\\\");\\n\",\n \"\\t\\t\\tinvokePython(\\\"select_video\\\", item.className.match(/resource-video(\\\\d)/)[1]);\\n\",\n \"\\t\\t});\\n\",\n \"\\t});\\n\",\n \"\\tvideos[0].classList.add(\\\"selected\\\");\\n\",\n \"}, 1000);\\n\"\n ],\n \"text/plain\": [\n \"\"\n ]\n },\n \"metadata\": {},\n \"output_type\": \"display_data\"\n }\n ],\n \"source\": [\n \"import IPython.display\\n\",\n \"import PIL.Image\\n\",\n \"import cv2\\n\",\n \"import ffmpeg\\n\",\n \"import imageio\\n\",\n \"import io\\n\",\n \"import ipywidgets\\n\",\n \"import numpy\\n\",\n \"import os.path\\n\",\n \"import requests\\n\",\n \"import skimage.transform\\n\",\n \"import warnings\\n\",\n \"from base64 import b64encode\\n\",\n \"from demo import load_checkpoints, make_animation # type: ignore (local file)\\n\",\n \"from IPython.display import HTML, Javascript\\n\",\n \"from shutil import copyfileobj\\n\",\n \"from skimage import img_as_ubyte\\n\",\n \"from tempfile import NamedTemporaryFile\\n\",\n \"import os\\n\",\n \"import ipywidgets as ipyw\\n\",\n \"from IPython.display import display, FileLink\\n\",\n \"warnings.filterwarnings(\\\"ignore\\\")\\n\",\n \"os.makedirs(\\\"user\\\", exist_ok=True)\\n\",\n \"\\n\",\n \"display(HTML(\\\"\\\"\\\"\\n\",\n \"\\n\",\n \"\\\"\\\"\\\"))\\n\",\n \"\\n\",\n \"\\n\",\n \"def uploaded_file(change):\\n\",\n \" save_dir = 'uploads'\\n\",\n \" if not os.path.exists(save_dir): os.mkdir(save_dir)\\n\",\n \" \\n\",\n \" uploads = change['new']\\n\",\n \" for upload in uploads:\\n\",\n \" filename = upload['name']\\n\",\n \" content = upload['content']\\n\",\n \" with open(os.path.join(save_dir,filename), 'wb') as f:\\n\",\n \" f.write(content)\\n\",\n \" with out:\\n\",\n \" print(change)\\n\",\n \" \\n\",\n \"def create_uploader():\\n\",\n \" uploader = ipyw.FileUpload(multiple=True)\\n\",\n \" display(uploader)\\n\",\n \" uploader.description = '📂 Upload'\\n\",\n \" uploader.observe(uploaded_file, names='value')\\n\",\n \"\\n\",\n \"def download_file(filename='./face.mp4') -> HTML:\\n\",\n \" fl=FileLink(filename)\\n\",\n \" fl.html_link_str =\\\"%s\\\"\\n\",\n \" \\n\",\n \" display(fl)\\n\",\n \" display(HTML(f\\\"\\\"\\\"\\n\",\n \"\\n\",\n \"\\\"\\\"\\\"))\\n\",\n \" \\n\",\n \"def thumbnail(file):\\n\",\n \"\\treturn imageio.get_reader(file, mode='I', format='FFMPEG').get_next_data()\\n\",\n \"\\n\",\n \"def create_image(i, j):\\n\",\n \"\\timage_widget = ipywidgets.Image.from_file('demo/images/%d%d.png' % (i, j))\\n\",\n \"\\timage_widget.add_class('resource')\\n\",\n \"\\timage_widget.add_class('resource-image')\\n\",\n \"\\timage_widget.add_class('resource-image%d%d' % (i, j))\\n\",\n \"\\treturn image_widget\\n\",\n \"\\n\",\n \"def create_video(i):\\n\",\n \"\\tvideo_widget = ipywidgets.Image(\\n\",\n \"\\t\\tvalue=cv2.imencode('.png', cv2.cvtColor(thumbnail('demo/videos/%d.mp4' % i), cv2.COLOR_RGB2BGR))[1].tostring(),\\n\",\n \"\\t\\tformat='png'\\n\",\n \"\\t)\\n\",\n \"\\tvideo_widget.add_class('resource')\\n\",\n \"\\tvideo_widget.add_class('resource-video')\\n\",\n \"\\tvideo_widget.add_class('resource-video%d' % i)\\n\",\n \"\\treturn video_widget\\n\",\n \"\\n\",\n \"def create_title(title):\\n\",\n \"\\ttitle_widget = ipywidgets.Label(title)\\n\",\n \"\\ttitle_widget.add_class('title')\\n\",\n \"\\treturn title_widget\\n\",\n \"\\n\",\n \"def download_output(button):\\n\",\n \"\\tcomplete.layout.display = 'none'\\n\",\n \"\\tloading.layout.display = ''\\n\",\n \"\\tdownload_file('./output.mp4')\\n\",\n \"\\t# files.download('output.mp4')\\n\",\n \"\\tloading.layout.display = 'none'\\n\",\n \"\\tcomplete.layout.display = ''\\n\",\n \"\\n\",\n \"def convert_output(button):\\n\",\n \"\\tcomplete.layout.display = 'none'\\n\",\n \"\\tloading.layout.display = ''\\n\",\n \"\\tffmpeg.input('output.mp4').output('scaled.mp4', vf='scale=1080x1080:flags=lanczos,pad=1920:1080:420:0').overwrite_output().run()\\n\",\n \"\\tfiles.download('scaled.mp4')\\n\",\n \"\\tloading.layout.display = 'none'\\n\",\n \"\\tcomplete.layout.display = ''\\n\",\n \"\\n\",\n \"def back_to_main(button):\\n\",\n \"\\tcomplete.layout.display = 'none'\\n\",\n \"\\tmain.layout.display = ''\\n\",\n \"\\n\",\n \"label_or = ipywidgets.Label('or')\\n\",\n \"label_or.add_class('label-or')\\n\",\n \"\\n\",\n \"image_titles = ['Peoples', 'Cartoons', 'Dolls', 'Game of Thrones', 'Statues']\\n\",\n \"image_lengths = [8, 4, 8, 9, 4]\\n\",\n \"\\n\",\n \"image_tab = ipywidgets.Tab()\\n\",\n \"image_tab.children = [ipywidgets.HBox([create_image(i, j) for j in range(length)]) for i, length in enumerate(image_lengths)]\\n\",\n \"for i, title in enumerate(image_titles):\\n\",\n \"\\timage_tab.set_title(i, title)\\n\",\n \"\\n\",\n \"input_image_widget = ipywidgets.Output()\\n\",\n \"input_image_widget.add_class('input-widget')\\n\",\n \"upload_input_image_button = ipywidgets.FileUpload(accept='image/*', button_style='primary')\\n\",\n \"upload_input_image_button.add_class('input-button')\\n\",\n \"image_part = ipywidgets.HBox([\\n\",\n \"\\tipywidgets.VBox([input_image_widget, upload_input_image_button]),\\n\",\n \"\\tlabel_or,\\n\",\n \"\\timage_tab\\n\",\n \"])\\n\",\n \"\\n\",\n \"video_tab = ipywidgets.Tab()\\n\",\n \"video_tab.children = [ipywidgets.HBox([create_video(i) for i in range(5)])]\\n\",\n \"video_tab.set_title(0, 'All Videos')\\n\",\n \"\\n\",\n \"input_video_widget = ipywidgets.Output()\\n\",\n \"input_video_widget.add_class('input-widget')\\n\",\n \"upload_input_video_button = ipywidgets.FileUpload(accept='video/*', button_style='primary')\\n\",\n \"upload_input_video_button.add_class('input-button')\\n\",\n \"video_part = ipywidgets.HBox([\\n\",\n \"\\tipywidgets.VBox([input_video_widget, upload_input_video_button]),\\n\",\n \"\\tlabel_or,\\n\",\n \"\\tvideo_tab\\n\",\n \"])\\n\",\n \"\\n\",\n \"model = ipywidgets.Dropdown(\\n\",\n \"\\tdescription=\\\"Model:\\\",\\n\",\n \"\\toptions=[\\n\",\n \"\\t\\t'vox',\\n\",\n \"\\t\\t'vox-adv',\\n\",\n \"\\t\\t'taichi',\\n\",\n \"\\t\\t'taichi-adv',\\n\",\n \"\\t\\t'nemo',\\n\",\n \"\\t\\t'mgif',\\n\",\n \"\\t\\t'fashion',\\n\",\n \"\\t\\t'bair'\\n\",\n \"\\t]\\n\",\n \")\\n\",\n \"warning = ipywidgets.HTML('Warning: Upload your own images and videos (see README)')\\n\",\n \"warning.add_class('warning')\\n\",\n \"model_part = ipywidgets.HBox([model, warning])\\n\",\n \"\\n\",\n \"relative = ipywidgets.Checkbox(description=\\\"Relative keypoint displacement (Inherit object proporions from the video)\\\", value=True)\\n\",\n \"adapt_movement_scale = ipywidgets.Checkbox(description=\\\"Adapt movement scale (Don’t touch unless you know want you are doing)\\\", value=True)\\n\",\n \"generate_button = ipywidgets.Button(description=\\\"Generate\\\", button_style='primary')\\n\",\n \"main = ipywidgets.VBox([\\n\",\n \"\\tcreate_title('Choose Image'),\\n\",\n \"\\timage_part,\\n\",\n \"\\tcreate_title('Choose Video'),\\n\",\n \"\\tvideo_part,\\n\",\n \"\\tcreate_title('Settings'),\\n\",\n \"\\tmodel_part,\\n\",\n \"\\trelative,\\n\",\n \"\\tadapt_movement_scale,\\n\",\n \"\\tgenerate_button\\n\",\n \"])\\n\",\n \"\\n\",\n \"loader = ipywidgets.Label()\\n\",\n \"loader.add_class(\\\"loader\\\")\\n\",\n \"loading_label = ipywidgets.Label(\\\"This may take several minutes to process…\\\")\\n\",\n \"loading_label.add_class(\\\"loading-label\\\")\\n\",\n \"progress_bar = ipywidgets.Output()\\n\",\n \"loading = ipywidgets.VBox([loader, loading_label, progress_bar])\\n\",\n \"loading.add_class('loading')\\n\",\n \"\\n\",\n \"output_widget = ipywidgets.Output()\\n\",\n \"output_widget.add_class('output-widget')\\n\",\n \"download = ipywidgets.Button(description='Download', button_style='primary')\\n\",\n \"download.add_class('output-button')\\n\",\n \"download.on_click(download_output)\\n\",\n \"convert = ipywidgets.Button(description='Convert to 1920×1080', button_style='primary')\\n\",\n \"convert.add_class('output-button')\\n\",\n \"convert.on_click(convert_output)\\n\",\n \"back = ipywidgets.Button(description='Back', button_style='primary')\\n\",\n \"back.add_class('output-button')\\n\",\n \"back.on_click(back_to_main)\\n\",\n \"\\n\",\n \"comparison_widget = ipywidgets.Output()\\n\",\n \"comparison_widget.add_class('comparison-widget')\\n\",\n \"comparison_label = ipywidgets.Label('Comparison')\\n\",\n \"comparison_label.add_class('comparison-label')\\n\",\n \"complete = ipywidgets.HBox([\\n\",\n \"\\tipywidgets.VBox([output_widget, download, convert, back]),\\n\",\n \"\\tipywidgets.VBox([comparison_widget, comparison_label])\\n\",\n \"])\\n\",\n \"\\n\",\n \"display(ipywidgets.VBox([main, loading, complete]))\\n\",\n \"display(Javascript(\\\"\\\"\\\"\\n\",\n \"var images, videos;\\n\",\n \"function deselectImages() {\\n\",\n \"\\timages.forEach(function(item) {\\n\",\n \"\\t\\titem.classList.remove(\\\"selected\\\");\\n\",\n \"\\t});\\n\",\n \"}\\n\",\n \"function deselectVideos() {\\n\",\n \"\\tvideos.forEach(function(item) {\\n\",\n \"\\t\\titem.classList.remove(\\\"selected\\\");\\n\",\n \"\\t});\\n\",\n \"}\\n\",\n \"function invokePython(func) {\\n\",\n \"\\tgoogle.colab.kernel.invokeFunction(\\\"notebook.\\\" + func, [].slice.call(arguments, 1), {});\\n\",\n \"}\\n\",\n \"setTimeout(function() {\\n\",\n \"\\t(images = [].slice.call(document.getElementsByClassName(\\\"resource-image\\\"))).forEach(function(item) {\\n\",\n \"\\t\\titem.addEventListener(\\\"click\\\", function() {\\n\",\n \"\\t\\t\\tdeselectImages();\\n\",\n \"\\t\\t\\titem.classList.add(\\\"selected\\\");\\n\",\n \"\\t\\t\\tinvokePython(\\\"select_image\\\", item.className.match(/resource-image(\\\\d\\\\d)/)[1]);\\n\",\n \"\\t\\t});\\n\",\n \"\\t});\\n\",\n \"\\timages[0].classList.add(\\\"selected\\\");\\n\",\n \"\\t(videos = [].slice.call(document.getElementsByClassName(\\\"resource-video\\\"))).forEach(function(item) {\\n\",\n \"\\t\\titem.addEventListener(\\\"click\\\", function() {\\n\",\n \"\\t\\t\\tdeselectVideos();\\n\",\n \"\\t\\t\\titem.classList.add(\\\"selected\\\");\\n\",\n \"\\t\\t\\tinvokePython(\\\"select_video\\\", item.className.match(/resource-video(\\\\d)/)[1]);\\n\",\n \"\\t\\t});\\n\",\n \"\\t});\\n\",\n \"\\tvideos[0].classList.add(\\\"selected\\\");\\n\",\n \"}, 1000);\\n\",\n \"\\\"\\\"\\\"))\\n\",\n \"\\n\",\n \"selected_image = None\\n\",\n \"def select_image(filename):\\n\",\n \"\\tglobal selected_image\\n\",\n \"\\tselected_image = resize(PIL.Image.open('demo/images/%s.png' % filename).convert(\\\"RGB\\\"))\\n\",\n \"\\tinput_image_widget.clear_output(wait=True)\\n\",\n \"\\twith input_image_widget:\\n\",\n \"\\t\\tdisplay(HTML('Image'))\\n\",\n \"\\tinput_image_widget.remove_class('uploaded')\\n\",\n \"# output.register_callback(\\\"notebook.select_image\\\", select_image)\\n\",\n \"\\n\",\n \"selected_video = None\\n\",\n \"def select_video(filename):\\n\",\n \"\\tglobal selected_video\\n\",\n \"\\tselected_video = 'demo/videos/%s.mp4' % filename\\n\",\n \"\\tinput_video_widget.clear_output(wait=True)\\n\",\n \"\\twith input_video_widget:\\n\",\n \"\\t\\tdisplay(HTML('Video'))\\n\",\n \"\\tinput_video_widget.remove_class('uploaded')\\n\",\n \"# output.register_callback(\\\"notebook.select_video\\\", select_video)\\n\",\n \"\\n\",\n \"def resize(image, size=(256, 256)):\\n\",\n \"\\tw, h = image.size\\n\",\n \"\\td = min(w, h)\\n\",\n \"\\tr = ((w - d) // 2, (h - d) // 2, (w + d) // 2, (h + d) // 2)\\n\",\n \"\\treturn image.resize(size, resample=PIL.Image.LANCZOS, box=r)\\n\",\n \"\\n\",\n \"def upload_image(change):\\n\",\n \"\\tglobal selected_image\\n\",\n \"\\tcontent = upload_input_image_button.value[0]['content']\\n\",\n \"\\tname = upload_input_image_button.value[0]['name']\\n\",\n \" \\n\",\n \"\\t# for name, file_info in upload_input_image_button.value.items():\\n\",\n \"\\t\\t# content = file_info['content']\\n\",\n \"\\tif content is not None:\\n\",\n \"\\t\\tselected_image = resize(PIL.Image.open(io.BytesIO(content)).convert(\\\"RGB\\\"))\\n\",\n \"\\t\\tinput_image_widget.clear_output(wait=True)\\n\",\n \"\\t\\twith input_image_widget:\\n\",\n \"\\t\\t\\tdisplay(selected_image)\\n\",\n \"\\t\\tinput_image_widget.add_class('uploaded')\\n\",\n \"\\t\\tdisplay(Javascript('deselectImages()'))\\n\",\n \"upload_input_image_button.observe(upload_image, names='value')\\n\",\n \"\\n\",\n \"def upload_video(change):\\n\",\n \"\\tglobal selected_video\\n\",\n \"\\t# for name, file_info in upload_input_video_button.value.items():\\n\",\n \"\\t\\t# content = file_info['content']\\n\",\n \"\\tcontent = upload_input_video_button.value[0]['content']\\n\",\n \"\\tname = upload_input_video_button.value[0]['name']\\n\",\n \"\\tif content is not None:\\n\",\n \"\\t\\tselected_video = 'user/' + name\\n\",\n \"\\t\\tpreview = resize(PIL.Image.fromarray(thumbnail(content)).convert(\\\"RGB\\\"))\\n\",\n \"\\t\\tinput_video_widget.clear_output(wait=True)\\n\",\n \"\\t\\twith input_video_widget:\\n\",\n \"\\t\\t\\tdisplay(preview)\\n\",\n \"\\t\\tinput_video_widget.add_class('uploaded')\\n\",\n \"\\t\\tdisplay(Javascript('deselectVideos()'))\\n\",\n \"\\t\\twith open(selected_video, 'wb') as video:\\n\",\n \"\\t\\t\\tvideo.write(content)\\n\",\n \"upload_input_video_button.observe(upload_video, names='value')\\n\",\n \"\\n\",\n \"def change_model(change):\\n\",\n \"\\tif model.value.startswith('vox'):\\n\",\n \"\\t\\twarning.remove_class('warn')\\n\",\n \"\\telse:\\n\",\n \"\\t\\twarning.add_class('warn')\\n\",\n \"model.observe(change_model, names='value')\\n\",\n \"\\n\",\n \"def generate(button):\\n\",\n \"\\tmain.layout.display = 'none'\\n\",\n \"\\tloading.layout.display = ''\\n\",\n \"\\tfilename = model.value + ('' if model.value == 'fashion' else '-cpk') + '.pth.tar'\\n\",\n \"\\tif not os.path.isfile(filename):\\n\",\n \"\\t\\tdownload = requests.get(requests.get('https://cloud-api.yandex.net/v1/disk/public/resources/download?public_key=https://yadi.sk/d/lEw8uRm140L_eQ&path=/' + filename).json().get('href'))\\n\",\n \"\\t\\twith open(filename, 'wb') as checkpoint:\\n\",\n \"\\t\\t\\tcheckpoint.write(download.content)\\n\",\n \"\\treader = imageio.get_reader(selected_video, mode='I', format='FFMPEG')\\n\",\n \"\\tfps = reader.get_meta_data()['fps']\\n\",\n \"\\tdriving_video = []\\n\",\n \"\\tfor frame in reader:\\n\",\n \"\\t\\tdriving_video.append(frame)\\n\",\n \"\\tgenerator, kp_detector = load_checkpoints(config_path='config/%s-256.yaml' % model.value, checkpoint_path=filename)\\n\",\n \"\\twith progress_bar:\\n\",\n \"\\t\\tpredictions = make_animation(\\n\",\n \"\\t\\t\\tskimage.transform.resize(numpy.asarray(selected_image), (256, 256)),\\n\",\n \"\\t\\t\\t[skimage.transform.resize(frame, (256, 256)) for frame in driving_video],\\n\",\n \"\\t\\t\\tgenerator,\\n\",\n \"\\t\\t\\tkp_detector,\\n\",\n \"\\t\\t\\trelative=relative.value,\\n\",\n \"\\t\\t\\tadapt_movement_scale=adapt_movement_scale.value\\n\",\n \"\\t\\t)\\n\",\n \"\\tprogress_bar.clear_output()\\n\",\n \"\\timageio.mimsave('output.mp4', [img_as_ubyte(frame) for frame in predictions], fps=fps)\\n\",\n \"\\tif selected_video.startswith('user/') or selected_video == 'demo/videos/0.mp4':\\n\",\n \"\\t\\twith NamedTemporaryFile(suffix='.mp4') as output:\\n\",\n \"\\t\\t\\tffmpeg.output(ffmpeg.input('output.mp4').video, ffmpeg.input(selected_video).audio, output.name, c='copy').overwrite_output().run()\\n\",\n \"\\t\\t\\twith open('output.mp4', 'wb') as result:\\n\",\n \"\\t\\t\\t\\tcopyfileobj(output, result)\\n\",\n \"\\twith output_widget:\\n\",\n \"\\t\\tvideo_widget = ipywidgets.Video.from_file('output.mp4', autoplay=False, loop=False)\\n\",\n \"\\t\\tvideo_widget.add_class('video')\\n\",\n \"\\t\\tvideo_widget.add_class('video-left')\\n\",\n \"\\t\\tdisplay(video_widget)\\n\",\n \"\\twith comparison_widget:\\n\",\n \"\\t\\tvideo_widget = ipywidgets.Video.from_file(selected_video, autoplay=False, loop=False, controls=False)\\n\",\n \"\\t\\tvideo_widget.add_class('video')\\n\",\n \"\\t\\tvideo_widget.add_class('video-right')\\n\",\n \"\\t\\tdisplay(video_widget)\\n\",\n \"\\tdisplay(Javascript(\\\"\\\"\\\"\\n\",\n \"\\tsetTimeout(function() {\\n\",\n \"\\t\\t(function(left, right) {\\n\",\n \"\\t\\t\\tleft.addEventListener(\\\"play\\\", function() {\\n\",\n \"\\t\\t\\t\\tright.play();\\n\",\n \"\\t\\t\\t});\\n\",\n \"\\t\\t\\tleft.addEventListener(\\\"pause\\\", function() {\\n\",\n \"\\t\\t\\t\\tright.pause();\\n\",\n \"\\t\\t\\t});\\n\",\n \"\\t\\t\\tleft.addEventListener(\\\"seeking\\\", function() {\\n\",\n \"\\t\\t\\t\\tright.currentTime = left.currentTime;\\n\",\n \"\\t\\t\\t});\\n\",\n \"\\t\\t\\tright.muted = true;\\n\",\n \"\\t\\t})(document.getElementsByClassName(\\\"video-left\\\")[0], document.getElementsByClassName(\\\"video-right\\\")[0]);\\n\",\n \"\\t}, 1000);\\n\",\n \"\\t\\\"\\\"\\\"))\\n\",\n \"\\tloading.layout.display = 'none'\\n\",\n \"\\tcomplete.layout.display = ''\\n\",\n \"\\n\",\n \"generate_button.on_click(generate)\\n\",\n \"\\n\",\n \"loading.layout.display = 'none'\\n\",\n \"complete.layout.display = 'none'\\n\",\n \"select_image('00')\\n\",\n \"select_video('0')\"\n ]\n }\n ],\n \"metadata\": {\n \"accelerator\": \"GPU\",\n \"colab\": {\n \"name\": \"first-order-model-demo\",\n \"provenance\": []\n },\n \"kernelspec\": {\n \"display_name\": \"ldm\",\n \"language\": \"python\",\n \"name\": \"ldm\"\n },\n \"language_info\": {\n \"codemirror_mode\": {\n \"name\": \"ipython\",\n \"version\": 3\n },\n \"file_extension\": \".py\",\n \"mimetype\": \"text/x-python\",\n \"name\": \"python\",\n \"nbconvert_exporter\": \"python\",\n \"pygments_lexer\": \"ipython3\",\n \"version\": \"3.8.5\"\n }\n },\n \"nbformat\": 4,\n \"nbformat_minor\": 4\n}\n"
},
{
"path": "frames_dataset.py",
"content": "import os\nfrom skimage import io, img_as_float32\nfrom skimage.color import gray2rgb\nfrom sklearn.model_selection import train_test_split\nfrom imageio import mimread\n\nimport numpy as np\nfrom torch.utils.data import Dataset\nimport pandas as pd\nfrom augmentation import AllAugmentationTransform\nimport glob\n\n\ndef read_video(name, frame_shape):\n \"\"\"\n Read video which can be:\n - an image of concatenated frames\n - '.mp4' and'.gif'\n - folder with videos\n \"\"\"\n\n if os.path.isdir(name):\n frames = sorted(os.listdir(name))\n num_frames = len(frames)\n video_array = np.array(\n [img_as_float32(io.imread(os.path.join(name, frames[idx]))) for idx in range(num_frames)])\n elif name.lower().endswith('.png') or name.lower().endswith('.jpg'):\n image = io.imread(name)\n\n if len(image.shape) == 2 or image.shape[2] == 1:\n image = gray2rgb(image)\n\n if image.shape[2] == 4:\n image = image[..., :3]\n\n image = img_as_float32(image)\n\n video_array = np.moveaxis(image, 1, 0)\n\n video_array = video_array.reshape((-1,) + frame_shape)\n video_array = np.moveaxis(video_array, 1, 2)\n elif name.lower().endswith('.gif') or name.lower().endswith('.mp4') or name.lower().endswith('.mov'):\n video = np.array(mimread(name))\n if len(video.shape) == 3:\n video = np.array([gray2rgb(frame) for frame in video])\n if video.shape[-1] == 4:\n video = video[..., :3]\n video_array = img_as_float32(video)\n else:\n raise Exception(\"Unknown file extensions %s\" % name)\n\n return video_array\n\n\nclass FramesDataset(Dataset):\n \"\"\"\n Dataset of videos, each video can be represented as:\n - an image of concatenated frames\n - '.mp4' or '.gif'\n - folder with all frames\n \"\"\"\n\n def __init__(self, root_dir, frame_shape=(256, 256, 3), id_sampling=False, is_train=True,\n random_seed=0, pairs_list=None, augmentation_params=None):\n self.root_dir = root_dir\n self.videos = os.listdir(root_dir)\n self.frame_shape = tuple(frame_shape)\n self.pairs_list = pairs_list\n self.id_sampling = id_sampling\n if os.path.exists(os.path.join(root_dir, 'train')):\n assert os.path.exists(os.path.join(root_dir, 'test'))\n print(\"Use predefined train-test split.\")\n if id_sampling:\n train_videos = {os.path.basename(video).split('#')[0] for video in\n os.listdir(os.path.join(root_dir, 'train'))}\n train_videos = list(train_videos)\n else:\n train_videos = os.listdir(os.path.join(root_dir, 'train'))\n test_videos = os.listdir(os.path.join(root_dir, 'test'))\n self.root_dir = os.path.join(self.root_dir, 'train' if is_train else 'test')\n else:\n print(\"Use random train-test split.\")\n train_videos, test_videos = train_test_split(self.videos, random_state=random_seed, test_size=0.2)\n\n if is_train:\n self.videos = train_videos\n else:\n self.videos = test_videos\n\n self.is_train = is_train\n\n if self.is_train:\n self.transform = AllAugmentationTransform(**augmentation_params)\n else:\n self.transform = None\n\n def __len__(self):\n return len(self.videos)\n\n def __getitem__(self, idx):\n if self.is_train and self.id_sampling:\n name = self.videos[idx]\n path = np.random.choice(glob.glob(os.path.join(self.root_dir, name + '*.mp4')))\n else:\n name = self.videos[idx]\n path = os.path.join(self.root_dir, name)\n\n video_name = os.path.basename(path)\n\n if self.is_train and os.path.isdir(path):\n frames = os.listdir(path)\n num_frames = len(frames)\n frame_idx = np.sort(np.random.choice(num_frames, replace=True, size=2))\n video_array = [img_as_float32(io.imread(os.path.join(path, frames[idx]))) for idx in frame_idx]\n else:\n video_array = read_video(path, frame_shape=self.frame_shape)\n num_frames = len(video_array)\n frame_idx = np.sort(np.random.choice(num_frames, replace=True, size=2)) if self.is_train else range(\n num_frames)\n video_array = video_array[frame_idx]\n\n if self.transform is not None:\n video_array = self.transform(video_array)\n\n out = {}\n if self.is_train:\n source = np.array(video_array[0], dtype='float32')\n driving = np.array(video_array[1], dtype='float32')\n\n out['driving'] = driving.transpose((2, 0, 1))\n out['source'] = source.transpose((2, 0, 1))\n else:\n video = np.array(video_array, dtype='float32')\n out['video'] = video.transpose((3, 0, 1, 2))\n\n out['name'] = video_name\n\n return out\n\n\nclass DatasetRepeater(Dataset):\n \"\"\"\n Pass several times over the same dataset for better i/o performance\n \"\"\"\n\n def __init__(self, dataset, num_repeats=100):\n self.dataset = dataset\n self.num_repeats = num_repeats\n\n def __len__(self):\n return self.num_repeats * self.dataset.__len__()\n\n def __getitem__(self, idx):\n return self.dataset[idx % self.dataset.__len__()]\n\n\nclass PairedDataset(Dataset):\n \"\"\"\n Dataset of pairs for animation.\n \"\"\"\n\n def __init__(self, initial_dataset, number_of_pairs, seed=0):\n self.initial_dataset = initial_dataset\n pairs_list = self.initial_dataset.pairs_list\n\n np.random.seed(seed)\n\n if pairs_list is None:\n max_idx = min(number_of_pairs, len(initial_dataset))\n nx, ny = max_idx, max_idx\n xy = np.mgrid[:nx, :ny].reshape(2, -1).T\n number_of_pairs = min(xy.shape[0], number_of_pairs)\n self.pairs = xy.take(np.random.choice(xy.shape[0], number_of_pairs, replace=False), axis=0)\n else:\n videos = self.initial_dataset.videos\n name_to_index = {name: index for index, name in enumerate(videos)}\n pairs = pd.read_csv(pairs_list)\n pairs = pairs[np.logical_and(pairs['source'].isin(videos), pairs['driving'].isin(videos))]\n\n number_of_pairs = min(pairs.shape[0], number_of_pairs)\n self.pairs = []\n self.start_frames = []\n for ind in range(number_of_pairs):\n self.pairs.append(\n (name_to_index[pairs['driving'].iloc[ind]], name_to_index[pairs['source'].iloc[ind]]))\n\n def __len__(self):\n return len(self.pairs)\n\n def __getitem__(self, idx):\n pair = self.pairs[idx]\n first = self.initial_dataset[pair[0]]\n second = self.initial_dataset[pair[1]]\n first = {'driving_' + key: value for key, value in first.items()}\n second = {'source_' + key: value for key, value in second.items()}\n\n return {**first, **second}\n"
},
{
"path": "logger.py",
"content": "import numpy as np\nimport torch\nimport torch.nn.functional as F\nimport imageio\n\nimport os\nfrom skimage.draw import disk\n\nimport matplotlib.pyplot as plt\nimport collections\n\n\nclass Logger:\n def __init__(self, log_dir, checkpoint_freq=100, visualizer_params=None, zfill_num=8, log_file_name='log.txt'):\n\n self.loss_list = []\n self.cpk_dir = log_dir\n self.visualizations_dir = os.path.join(log_dir, 'train-vis')\n if not os.path.exists(self.visualizations_dir):\n os.makedirs(self.visualizations_dir)\n self.log_file = open(os.path.join(log_dir, log_file_name), 'a')\n self.zfill_num = zfill_num\n self.visualizer = Visualizer(**visualizer_params)\n self.checkpoint_freq = checkpoint_freq\n self.epoch = 0\n self.best_loss = float('inf')\n self.names = None\n\n def log_scores(self, loss_names):\n loss_mean = np.array(self.loss_list).mean(axis=0)\n\n loss_string = \"; \".join([\"%s - %.5f\" % (name, value) for name, value in zip(loss_names, loss_mean)])\n loss_string = str(self.epoch).zfill(self.zfill_num) + \") \" + loss_string\n\n print(loss_string, file=self.log_file)\n self.loss_list = []\n self.log_file.flush()\n\n def visualize_rec(self, inp, out):\n image = self.visualizer.visualize(inp['driving'], inp['source'], out)\n imageio.imsave(os.path.join(self.visualizations_dir, \"%s-rec.png\" % str(self.epoch).zfill(self.zfill_num)), image)\n\n def save_cpk(self, emergent=False):\n cpk = {k: v.state_dict() for k, v in self.models.items()}\n cpk['epoch'] = self.epoch\n cpk_path = os.path.join(self.cpk_dir, '%s-checkpoint.pth.tar' % str(self.epoch).zfill(self.zfill_num)) \n if not (os.path.exists(cpk_path) and emergent):\n torch.save(cpk, cpk_path)\n\n @staticmethod\n def load_cpk(checkpoint_path, generator=None, discriminator=None, kp_detector=None,\n optimizer_generator=None, optimizer_discriminator=None, optimizer_kp_detector=None):\n if torch.cuda.is_available():\n map_location = None\n else:\n map_location = 'cpu'\n checkpoint = torch.load(checkpoint_path, map_location)\n if generator is not None:\n generator.load_state_dict(checkpoint['generator'])\n if kp_detector is not None:\n kp_detector.load_state_dict(checkpoint['kp_detector'])\n if discriminator is not None:\n try:\n discriminator.load_state_dict(checkpoint['discriminator'])\n except:\n print ('No discriminator in the state-dict. Dicriminator will be randomly initialized')\n if optimizer_generator is not None:\n optimizer_generator.load_state_dict(checkpoint['optimizer_generator'])\n if optimizer_discriminator is not None:\n try:\n optimizer_discriminator.load_state_dict(checkpoint['optimizer_discriminator'])\n except RuntimeError as e:\n print ('No discriminator optimizer in the state-dict. Optimizer will be not initialized')\n if optimizer_kp_detector is not None:\n optimizer_kp_detector.load_state_dict(checkpoint['optimizer_kp_detector'])\n\n return checkpoint['epoch']\n\n def __enter__(self):\n return self\n\n def __exit__(self, exc_type, exc_val, exc_tb):\n if 'models' in self.__dict__:\n self.save_cpk()\n self.log_file.close()\n\n def log_iter(self, losses):\n losses = collections.OrderedDict(losses.items())\n if self.names is None:\n self.names = list(losses.keys())\n self.loss_list.append(list(losses.values()))\n\n def log_epoch(self, epoch, models, inp, out):\n self.epoch = epoch\n self.models = models\n if (self.epoch + 1) % self.checkpoint_freq == 0:\n self.save_cpk()\n self.log_scores(self.names)\n self.visualize_rec(inp, out)\n\n\nclass Visualizer:\n def __init__(self, kp_size=5, draw_border=False, colormap='gist_rainbow'):\n self.kp_size = kp_size\n self.draw_border = draw_border\n self.colormap = plt.get_cmap(colormap)\n\n def draw_image_with_kp(self, image, kp_array):\n image = np.copy(image)\n spatial_size = np.array(image.shape[:2][::-1])[np.newaxis]\n kp_array = spatial_size * (kp_array + 1) / 2\n num_kp = kp_array.shape[0]\n for kp_ind, kp in enumerate(kp_array):\n rr, cc = disk(kp[1], kp[0], self.kp_size, shape=image.shape[:2])\n image[rr, cc] = np.array(self.colormap(kp_ind / num_kp))[:3]\n return image\n\n def create_image_column_with_kp(self, images, kp):\n image_array = np.array([self.draw_image_with_kp(v, k) for v, k in zip(images, kp)])\n return self.create_image_column(image_array)\n\n def create_image_column(self, images):\n if self.draw_border:\n images = np.copy(images)\n images[:, :, [0, -1]] = (1, 1, 1)\n return np.concatenate(list(images), axis=0)\n\n def create_image_grid(self, *args):\n out = []\n for arg in args:\n if type(arg) == tuple:\n out.append(self.create_image_column_with_kp(arg[0], arg[1]))\n else:\n out.append(self.create_image_column(arg))\n return np.concatenate(out, axis=1)\n\n def visualize(self, driving, source, out):\n images = []\n\n # Source image with keypoints\n source = source.data.cpu()\n kp_source = out['kp_source']['value'].data.cpu().numpy()\n source = np.transpose(source, [0, 2, 3, 1])\n images.append((source, kp_source))\n\n # Equivariance visualization\n if 'transformed_frame' in out:\n transformed = out['transformed_frame'].data.cpu().numpy()\n transformed = np.transpose(transformed, [0, 2, 3, 1])\n transformed_kp = out['transformed_kp']['value'].data.cpu().numpy()\n images.append((transformed, transformed_kp))\n\n # Driving image with keypoints\n kp_driving = out['kp_driving']['value'].data.cpu().numpy()\n driving = driving.data.cpu().numpy()\n driving = np.transpose(driving, [0, 2, 3, 1])\n images.append((driving, kp_driving))\n\n # Deformed image\n if 'deformed' in out:\n deformed = out['deformed'].data.cpu().numpy()\n deformed = np.transpose(deformed, [0, 2, 3, 1])\n images.append(deformed)\n\n # Result with and without keypoints\n prediction = out['prediction'].data.cpu().numpy()\n prediction = np.transpose(prediction, [0, 2, 3, 1])\n if 'kp_norm' in out:\n kp_norm = out['kp_norm']['value'].data.cpu().numpy()\n images.append((prediction, kp_norm))\n images.append(prediction)\n\n\n ## Occlusion map\n if 'occlusion_map' in out:\n occlusion_map = out['occlusion_map'].data.cpu().repeat(1, 3, 1, 1)\n occlusion_map = F.interpolate(occlusion_map, size=source.shape[1:3]).numpy()\n occlusion_map = np.transpose(occlusion_map, [0, 2, 3, 1])\n images.append(occlusion_map)\n\n # Deformed images according to each individual transform\n if 'sparse_deformed' in out:\n full_mask = []\n for i in range(out['sparse_deformed'].shape[1]):\n image = out['sparse_deformed'][:, i].data.cpu()\n image = F.interpolate(image, size=source.shape[1:3])\n mask = out['mask'][:, i:(i+1)].data.cpu().repeat(1, 3, 1, 1)\n mask = F.interpolate(mask, size=source.shape[1:3])\n image = np.transpose(image.numpy(), (0, 2, 3, 1))\n mask = np.transpose(mask.numpy(), (0, 2, 3, 1))\n\n if i != 0:\n color = np.array(self.colormap((i - 1) / (out['sparse_deformed'].shape[1] - 1)))[:3]\n else:\n color = np.array((0, 0, 0))\n\n color = color.reshape((1, 1, 1, 3))\n\n images.append(image)\n if i != 0:\n images.append(mask * color)\n else:\n images.append(mask)\n\n full_mask.append(mask * color)\n\n images.append(sum(full_mask))\n\n image = self.create_image_grid(*images)\n image = (255 * image).astype(np.uint8)\n return image\n"
},
{
"path": "modules/dense_motion.py",
"content": "from torch import nn\nimport torch.nn.functional as F\nimport torch\nfrom modules.util import Hourglass, AntiAliasInterpolation2d, make_coordinate_grid, kp2gaussian\n\n\nclass DenseMotionNetwork(nn.Module):\n \"\"\"\n Module that predicting a dense motion from sparse motion representation given by kp_source and kp_driving\n \"\"\"\n\n def __init__(self, block_expansion, num_blocks, max_features, num_kp, num_channels, estimate_occlusion_map=False,\n scale_factor=1, kp_variance=0.01):\n super(DenseMotionNetwork, self).__init__()\n self.hourglass = Hourglass(block_expansion=block_expansion, in_features=(num_kp + 1) * (num_channels + 1),\n max_features=max_features, num_blocks=num_blocks)\n\n self.mask = nn.Conv2d(self.hourglass.out_filters, num_kp + 1, kernel_size=(7, 7), padding=(3, 3))\n\n if estimate_occlusion_map:\n self.occlusion = nn.Conv2d(self.hourglass.out_filters, 1, kernel_size=(7, 7), padding=(3, 3))\n else:\n self.occlusion = None\n\n self.num_kp = num_kp\n self.scale_factor = scale_factor\n self.kp_variance = kp_variance\n\n if self.scale_factor != 1:\n self.down = AntiAliasInterpolation2d(num_channels, self.scale_factor)\n\n def create_heatmap_representations(self, source_image, kp_driving, kp_source):\n \"\"\"\n Eq 6. in the paper H_k(z)\n \"\"\"\n spatial_size = source_image.shape[2:]\n gaussian_driving = kp2gaussian(kp_driving, spatial_size=spatial_size, kp_variance=self.kp_variance)\n gaussian_source = kp2gaussian(kp_source, spatial_size=spatial_size, kp_variance=self.kp_variance)\n heatmap = gaussian_driving - gaussian_source\n\n #adding background feature\n zeros = torch.zeros(heatmap.shape[0], 1, spatial_size[0], spatial_size[1]).type(heatmap.type())\n heatmap = torch.cat([zeros, heatmap], dim=1)\n heatmap = heatmap.unsqueeze(2)\n return heatmap\n\n def create_sparse_motions(self, source_image, kp_driving, kp_source):\n \"\"\"\n Eq 4. in the paper T_{s<-d}(z)\n \"\"\"\n bs, _, h, w = source_image.shape\n identity_grid = make_coordinate_grid((h, w), type=kp_source['value'].type())\n identity_grid = identity_grid.view(1, 1, h, w, 2)\n coordinate_grid = identity_grid - kp_driving['value'].view(bs, self.num_kp, 1, 1, 2)\n if 'jacobian' in kp_driving:\n jacobian = torch.matmul(kp_source['jacobian'], torch.inverse(kp_driving['jacobian']))\n jacobian = jacobian.unsqueeze(-3).unsqueeze(-3)\n jacobian = jacobian.repeat(1, 1, h, w, 1, 1)\n coordinate_grid = torch.matmul(jacobian, coordinate_grid.unsqueeze(-1))\n coordinate_grid = coordinate_grid.squeeze(-1)\n\n driving_to_source = coordinate_grid + kp_source['value'].view(bs, self.num_kp, 1, 1, 2)\n\n #adding background feature\n identity_grid = identity_grid.repeat(bs, 1, 1, 1, 1)\n sparse_motions = torch.cat([identity_grid, driving_to_source], dim=1)\n return sparse_motions\n\n def create_deformed_source_image(self, source_image, sparse_motions):\n \"\"\"\n Eq 7. in the paper \\hat{T}_{s<-d}(z)\n \"\"\"\n bs, _, h, w = source_image.shape\n source_repeat = source_image.unsqueeze(1).unsqueeze(1).repeat(1, self.num_kp + 1, 1, 1, 1, 1)\n source_repeat = source_repeat.view(bs * (self.num_kp + 1), -1, h, w)\n sparse_motions = sparse_motions.view((bs * (self.num_kp + 1), h, w, -1))\n sparse_deformed = F.grid_sample(source_repeat, sparse_motions)\n sparse_deformed = sparse_deformed.view((bs, self.num_kp + 1, -1, h, w))\n return sparse_deformed\n\n def forward(self, source_image, kp_driving, kp_source):\n if self.scale_factor != 1:\n source_image = self.down(source_image)\n\n bs, _, h, w = source_image.shape\n\n out_dict = dict()\n heatmap_representation = self.create_heatmap_representations(source_image, kp_driving, kp_source)\n sparse_motion = self.create_sparse_motions(source_image, kp_driving, kp_source)\n deformed_source = self.create_deformed_source_image(source_image, sparse_motion)\n out_dict['sparse_deformed'] = deformed_source\n\n input = torch.cat([heatmap_representation, deformed_source], dim=2)\n input = input.view(bs, -1, h, w)\n\n prediction = self.hourglass(input)\n\n mask = self.mask(prediction)\n mask = F.softmax(mask, dim=1)\n out_dict['mask'] = mask\n mask = mask.unsqueeze(2)\n sparse_motion = sparse_motion.permute(0, 1, 4, 2, 3)\n deformation = (sparse_motion * mask).sum(dim=1)\n deformation = deformation.permute(0, 2, 3, 1)\n\n out_dict['deformation'] = deformation\n\n # Sec. 3.2 in the paper\n if self.occlusion:\n occlusion_map = torch.sigmoid(self.occlusion(prediction))\n out_dict['occlusion_map'] = occlusion_map\n\n return out_dict\n"
},
{
"path": "modules/discriminator.py",
"content": "from torch import nn\nimport torch.nn.functional as F\nfrom modules.util import kp2gaussian\nimport torch\n\n\nclass DownBlock2d(nn.Module):\n \"\"\"\n Simple block for processing video (encoder).\n \"\"\"\n\n def __init__(self, in_features, out_features, norm=False, kernel_size=4, pool=False, sn=False):\n super(DownBlock2d, self).__init__()\n self.conv = nn.Conv2d(in_channels=in_features, out_channels=out_features, kernel_size=kernel_size)\n\n if sn:\n self.conv = nn.utils.spectral_norm(self.conv)\n\n if norm:\n self.norm = nn.InstanceNorm2d(out_features, affine=True)\n else:\n self.norm = None\n self.pool = pool\n\n def forward(self, x):\n out = x\n out = self.conv(out)\n if self.norm:\n out = self.norm(out)\n out = F.leaky_relu(out, 0.2)\n if self.pool:\n out = F.avg_pool2d(out, (2, 2))\n return out\n\n\nclass Discriminator(nn.Module):\n \"\"\"\n Discriminator similar to Pix2Pix\n \"\"\"\n\n def __init__(self, num_channels=3, block_expansion=64, num_blocks=4, max_features=512,\n sn=False, use_kp=False, num_kp=10, kp_variance=0.01, **kwargs):\n super(Discriminator, self).__init__()\n\n down_blocks = []\n for i in range(num_blocks):\n down_blocks.append(\n DownBlock2d(num_channels + num_kp * use_kp if i == 0 else min(max_features, block_expansion * (2 ** i)),\n min(max_features, block_expansion * (2 ** (i + 1))),\n norm=(i != 0), kernel_size=4, pool=(i != num_blocks - 1), sn=sn))\n\n self.down_blocks = nn.ModuleList(down_blocks)\n self.conv = nn.Conv2d(self.down_blocks[-1].conv.out_channels, out_channels=1, kernel_size=1)\n if sn:\n self.conv = nn.utils.spectral_norm(self.conv)\n self.use_kp = use_kp\n self.kp_variance = kp_variance\n\n def forward(self, x, kp=None):\n feature_maps = []\n out = x\n if self.use_kp:\n heatmap = kp2gaussian(kp, x.shape[2:], self.kp_variance)\n out = torch.cat([out, heatmap], dim=1)\n\n for down_block in self.down_blocks:\n feature_maps.append(down_block(out))\n out = feature_maps[-1]\n prediction_map = self.conv(out)\n\n return feature_maps, prediction_map\n\n\nclass MultiScaleDiscriminator(nn.Module):\n \"\"\"\n Multi-scale (scale) discriminator\n \"\"\"\n\n def __init__(self, scales=(), **kwargs):\n super(MultiScaleDiscriminator, self).__init__()\n self.scales = scales\n discs = {}\n for scale in scales:\n discs[str(scale).replace('.', '-')] = Discriminator(**kwargs)\n self.discs = nn.ModuleDict(discs)\n\n def forward(self, x, kp=None):\n out_dict = {}\n for scale, disc in self.discs.items():\n scale = str(scale).replace('-', '.')\n key = 'prediction_' + scale\n feature_maps, prediction_map = disc(x[key], kp)\n out_dict['feature_maps_' + scale] = feature_maps\n out_dict['prediction_map_' + scale] = prediction_map\n return out_dict\n"
},
{
"path": "modules/generator.py",
"content": "import torch\nfrom torch import nn\nimport torch.nn.functional as F\nfrom modules.util import ResBlock2d, SameBlock2d, UpBlock2d, DownBlock2d\nfrom modules.dense_motion import DenseMotionNetwork\n\n\nclass OcclusionAwareGenerator(nn.Module):\n \"\"\"\n Generator that given source image and and keypoints try to transform image according to movement trajectories\n induced by keypoints. Generator follows Johnson architecture.\n \"\"\"\n\n def __init__(self, num_channels, num_kp, block_expansion, max_features, num_down_blocks,\n num_bottleneck_blocks, estimate_occlusion_map=False, dense_motion_params=None, estimate_jacobian=False):\n super(OcclusionAwareGenerator, self).__init__()\n\n if dense_motion_params is not None:\n self.dense_motion_network = DenseMotionNetwork(num_kp=num_kp, num_channels=num_channels,\n estimate_occlusion_map=estimate_occlusion_map,\n **dense_motion_params)\n else:\n self.dense_motion_network = None\n\n self.first = SameBlock2d(num_channels, block_expansion, kernel_size=(7, 7), padding=(3, 3))\n\n down_blocks = []\n for i in range(num_down_blocks):\n in_features = min(max_features, block_expansion * (2 ** i))\n out_features = min(max_features, block_expansion * (2 ** (i + 1)))\n down_blocks.append(DownBlock2d(in_features, out_features, kernel_size=(3, 3), padding=(1, 1)))\n self.down_blocks = nn.ModuleList(down_blocks)\n\n up_blocks = []\n for i in range(num_down_blocks):\n in_features = min(max_features, block_expansion * (2 ** (num_down_blocks - i)))\n out_features = min(max_features, block_expansion * (2 ** (num_down_blocks - i - 1)))\n up_blocks.append(UpBlock2d(in_features, out_features, kernel_size=(3, 3), padding=(1, 1)))\n self.up_blocks = nn.ModuleList(up_blocks)\n\n self.bottleneck = torch.nn.Sequential()\n in_features = min(max_features, block_expansion * (2 ** num_down_blocks))\n for i in range(num_bottleneck_blocks):\n self.bottleneck.add_module('r' + str(i), ResBlock2d(in_features, kernel_size=(3, 3), padding=(1, 1)))\n\n self.final = nn.Conv2d(block_expansion, num_channels, kernel_size=(7, 7), padding=(3, 3))\n self.estimate_occlusion_map = estimate_occlusion_map\n self.num_channels = num_channels\n\n def deform_input(self, inp, deformation):\n _, h_old, w_old, _ = deformation.shape\n _, _, h, w = inp.shape\n if h_old != h or w_old != w:\n deformation = deformation.permute(0, 3, 1, 2)\n deformation = F.interpolate(deformation, size=(h, w), mode='bilinear')\n deformation = deformation.permute(0, 2, 3, 1)\n return F.grid_sample(inp, deformation)\n\n def forward(self, source_image, kp_driving, kp_source):\n # Encoding (downsampling) part\n out = self.first(source_image)\n for i in range(len(self.down_blocks)):\n out = self.down_blocks[i](out)\n\n # Transforming feature representation according to deformation and occlusion\n output_dict = {}\n if self.dense_motion_network is not None:\n dense_motion = self.dense_motion_network(source_image=source_image, kp_driving=kp_driving,\n kp_source=kp_source)\n output_dict['mask'] = dense_motion['mask']\n output_dict['sparse_deformed'] = dense_motion['sparse_deformed']\n\n if 'occlusion_map' in dense_motion:\n occlusion_map = dense_motion['occlusion_map']\n output_dict['occlusion_map'] = occlusion_map\n else:\n occlusion_map = None\n deformation = dense_motion['deformation']\n out = self.deform_input(out, deformation)\n\n if occlusion_map is not None:\n if out.shape[2] != occlusion_map.shape[2] or out.shape[3] != occlusion_map.shape[3]:\n occlusion_map = F.interpolate(occlusion_map, size=out.shape[2:], mode='bilinear')\n out = out * occlusion_map\n\n output_dict[\"deformed\"] = self.deform_input(source_image, deformation)\n\n # Decoding part\n out = self.bottleneck(out)\n for i in range(len(self.up_blocks)):\n out = self.up_blocks[i](out)\n out = self.final(out)\n out = F.sigmoid(out)\n\n output_dict[\"prediction\"] = out\n\n return output_dict\n"
},
{
"path": "modules/keypoint_detector.py",
"content": "from torch import nn\nimport torch\nimport torch.nn.functional as F\nfrom modules.util import Hourglass, make_coordinate_grid, AntiAliasInterpolation2d\n\n\nclass KPDetector(nn.Module):\n \"\"\"\n Detecting a keypoints. Return keypoint position and jacobian near each keypoint.\n \"\"\"\n\n def __init__(self, block_expansion, num_kp, num_channels, max_features,\n num_blocks, temperature, estimate_jacobian=False, scale_factor=1,\n single_jacobian_map=False, pad=0):\n super(KPDetector, self).__init__()\n\n self.predictor = Hourglass(block_expansion, in_features=num_channels,\n max_features=max_features, num_blocks=num_blocks)\n\n self.kp = nn.Conv2d(in_channels=self.predictor.out_filters, out_channels=num_kp, kernel_size=(7, 7),\n padding=pad)\n\n if estimate_jacobian:\n self.num_jacobian_maps = 1 if single_jacobian_map else num_kp\n self.jacobian = nn.Conv2d(in_channels=self.predictor.out_filters,\n out_channels=4 * self.num_jacobian_maps, kernel_size=(7, 7), padding=pad)\n self.jacobian.weight.data.zero_()\n self.jacobian.bias.data.copy_(torch.tensor([1, 0, 0, 1] * self.num_jacobian_maps, dtype=torch.float))\n else:\n self.jacobian = None\n\n self.temperature = temperature\n self.scale_factor = scale_factor\n if self.scale_factor != 1:\n self.down = AntiAliasInterpolation2d(num_channels, self.scale_factor)\n\n def gaussian2kp(self, heatmap):\n \"\"\"\n Extract the mean and from a heatmap\n \"\"\"\n shape = heatmap.shape\n heatmap = heatmap.unsqueeze(-1)\n grid = make_coordinate_grid(shape[2:], heatmap.type()).unsqueeze_(0).unsqueeze_(0)\n value = (heatmap * grid).sum(dim=(2, 3))\n kp = {'value': value}\n\n return kp\n\n def forward(self, x):\n if self.scale_factor != 1:\n x = self.down(x)\n\n feature_map = self.predictor(x)\n prediction = self.kp(feature_map)\n\n final_shape = prediction.shape\n heatmap = prediction.view(final_shape[0], final_shape[1], -1)\n heatmap = F.softmax(heatmap / self.temperature, dim=2)\n heatmap = heatmap.view(*final_shape)\n\n out = self.gaussian2kp(heatmap)\n\n if self.jacobian is not None:\n jacobian_map = self.jacobian(feature_map)\n jacobian_map = jacobian_map.reshape(final_shape[0], self.num_jacobian_maps, 4, final_shape[2],\n final_shape[3])\n heatmap = heatmap.unsqueeze(2)\n\n jacobian = heatmap * jacobian_map\n jacobian = jacobian.view(final_shape[0], final_shape[1], 4, -1)\n jacobian = jacobian.sum(dim=-1)\n jacobian = jacobian.view(jacobian.shape[0], jacobian.shape[1], 2, 2)\n out['jacobian'] = jacobian\n\n return out\n"
},
{
"path": "modules/model.py",
"content": "from torch import nn\nimport torch\nimport torch.nn.functional as F\nfrom modules.util import AntiAliasInterpolation2d, make_coordinate_grid\nfrom torchvision import models\nimport numpy as np\nfrom torch.autograd import grad\n\n\nclass Vgg19(torch.nn.Module):\n \"\"\"\n Vgg19 network for perceptual loss. See Sec 3.3.\n \"\"\"\n def __init__(self, requires_grad=False):\n super(Vgg19, self).__init__()\n vgg_pretrained_features = models.vgg19(pretrained=True).features\n self.slice1 = torch.nn.Sequential()\n self.slice2 = torch.nn.Sequential()\n self.slice3 = torch.nn.Sequential()\n self.slice4 = torch.nn.Sequential()\n self.slice5 = torch.nn.Sequential()\n for x in range(2):\n self.slice1.add_module(str(x), vgg_pretrained_features[x])\n for x in range(2, 7):\n self.slice2.add_module(str(x), vgg_pretrained_features[x])\n for x in range(7, 12):\n self.slice3.add_module(str(x), vgg_pretrained_features[x])\n for x in range(12, 21):\n self.slice4.add_module(str(x), vgg_pretrained_features[x])\n for x in range(21, 30):\n self.slice5.add_module(str(x), vgg_pretrained_features[x])\n\n self.mean = torch.nn.Parameter(data=torch.Tensor(np.array([0.485, 0.456, 0.406]).reshape((1, 3, 1, 1))),\n requires_grad=False)\n self.std = torch.nn.Parameter(data=torch.Tensor(np.array([0.229, 0.224, 0.225]).reshape((1, 3, 1, 1))),\n requires_grad=False)\n\n if not requires_grad:\n for param in self.parameters():\n param.requires_grad = False\n\n def forward(self, X):\n X = (X - self.mean) / self.std\n h_relu1 = self.slice1(X)\n h_relu2 = self.slice2(h_relu1)\n h_relu3 = self.slice3(h_relu2)\n h_relu4 = self.slice4(h_relu3)\n h_relu5 = self.slice5(h_relu4)\n out = [h_relu1, h_relu2, h_relu3, h_relu4, h_relu5]\n return out\n\n\nclass ImagePyramide(torch.nn.Module):\n \"\"\"\n Create image pyramide for computing pyramide perceptual loss. See Sec 3.3\n \"\"\"\n def __init__(self, scales, num_channels):\n super(ImagePyramide, self).__init__()\n downs = {}\n for scale in scales:\n downs[str(scale).replace('.', '-')] = AntiAliasInterpolation2d(num_channels, scale)\n self.downs = nn.ModuleDict(downs)\n\n def forward(self, x):\n out_dict = {}\n for scale, down_module in self.downs.items():\n out_dict['prediction_' + str(scale).replace('-', '.')] = down_module(x)\n return out_dict\n\n\nclass Transform:\n \"\"\"\n Random tps transformation for equivariance constraints. See Sec 3.3\n \"\"\"\n def __init__(self, bs, **kwargs):\n noise = torch.normal(mean=0, std=kwargs['sigma_affine'] * torch.ones([bs, 2, 3]))\n self.theta = noise + torch.eye(2, 3).view(1, 2, 3)\n self.bs = bs\n\n if ('sigma_tps' in kwargs) and ('points_tps' in kwargs):\n self.tps = True\n self.control_points = make_coordinate_grid((kwargs['points_tps'], kwargs['points_tps']), type=noise.type())\n self.control_points = self.control_points.unsqueeze(0)\n self.control_params = torch.normal(mean=0,\n std=kwargs['sigma_tps'] * torch.ones([bs, 1, kwargs['points_tps'] ** 2]))\n else:\n self.tps = False\n\n def transform_frame(self, frame):\n grid = make_coordinate_grid(frame.shape[2:], type=frame.type()).unsqueeze(0)\n grid = grid.view(1, frame.shape[2] * frame.shape[3], 2)\n grid = self.warp_coordinates(grid).view(self.bs, frame.shape[2], frame.shape[3], 2)\n return F.grid_sample(frame, grid, padding_mode=\"reflection\")\n\n def warp_coordinates(self, coordinates):\n theta = self.theta.type(coordinates.type())\n theta = theta.unsqueeze(1)\n transformed = torch.matmul(theta[:, :, :, :2], coordinates.unsqueeze(-1)) + theta[:, :, :, 2:]\n transformed = transformed.squeeze(-1)\n\n if self.tps:\n control_points = self.control_points.type(coordinates.type())\n control_params = self.control_params.type(coordinates.type())\n distances = coordinates.view(coordinates.shape[0], -1, 1, 2) - control_points.view(1, 1, -1, 2)\n distances = torch.abs(distances).sum(-1)\n\n result = distances ** 2\n result = result * torch.log(distances + 1e-6)\n result = result * control_params\n result = result.sum(dim=2).view(self.bs, coordinates.shape[1], 1)\n transformed = transformed + result\n\n return transformed\n\n def jacobian(self, coordinates):\n new_coordinates = self.warp_coordinates(coordinates)\n grad_x = grad(new_coordinates[..., 0].sum(), coordinates, create_graph=True)\n grad_y = grad(new_coordinates[..., 1].sum(), coordinates, create_graph=True)\n jacobian = torch.cat([grad_x[0].unsqueeze(-2), grad_y[0].unsqueeze(-2)], dim=-2)\n return jacobian\n\n\ndef detach_kp(kp):\n return {key: value.detach() for key, value in kp.items()}\n\n\nclass GeneratorFullModel(torch.nn.Module):\n \"\"\"\n Merge all generator related updates into single model for better multi-gpu usage\n \"\"\"\n\n def __init__(self, kp_extractor, generator, discriminator, train_params):\n super(GeneratorFullModel, self).__init__()\n self.kp_extractor = kp_extractor\n self.generator = generator\n self.discriminator = discriminator\n self.train_params = train_params\n self.scales = train_params['scales']\n self.disc_scales = self.discriminator.scales\n self.pyramid = ImagePyramide(self.scales, generator.num_channels)\n if torch.cuda.is_available():\n self.pyramid = self.pyramid.cuda()\n\n self.loss_weights = train_params['loss_weights']\n\n if sum(self.loss_weights['perceptual']) != 0:\n self.vgg = Vgg19()\n if torch.cuda.is_available():\n self.vgg = self.vgg.cuda()\n\n def forward(self, x):\n kp_source = self.kp_extractor(x['source'])\n kp_driving = self.kp_extractor(x['driving'])\n\n generated = self.generator(x['source'], kp_source=kp_source, kp_driving=kp_driving)\n generated.update({'kp_source': kp_source, 'kp_driving': kp_driving})\n\n loss_values = {}\n\n pyramide_real = self.pyramid(x['driving'])\n pyramide_generated = self.pyramid(generated['prediction'])\n\n if sum(self.loss_weights['perceptual']) != 0:\n value_total = 0\n for scale in self.scales:\n x_vgg = self.vgg(pyramide_generated['prediction_' + str(scale)])\n y_vgg = self.vgg(pyramide_real['prediction_' + str(scale)])\n\n for i, weight in enumerate(self.loss_weights['perceptual']):\n value = torch.abs(x_vgg[i] - y_vgg[i].detach()).mean()\n value_total += self.loss_weights['perceptual'][i] * value\n loss_values['perceptual'] = value_total\n\n if self.loss_weights['generator_gan'] != 0:\n discriminator_maps_generated = self.discriminator(pyramide_generated, kp=detach_kp(kp_driving))\n discriminator_maps_real = self.discriminator(pyramide_real, kp=detach_kp(kp_driving))\n value_total = 0\n for scale in self.disc_scales:\n key = 'prediction_map_%s' % scale\n value = ((1 - discriminator_maps_generated[key]) ** 2).mean()\n value_total += self.loss_weights['generator_gan'] * value\n loss_values['gen_gan'] = value_total\n\n if sum(self.loss_weights['feature_matching']) != 0:\n value_total = 0\n for scale in self.disc_scales:\n key = 'feature_maps_%s' % scale\n for i, (a, b) in enumerate(zip(discriminator_maps_real[key], discriminator_maps_generated[key])):\n if self.loss_weights['feature_matching'][i] == 0:\n continue\n value = torch.abs(a - b).mean()\n value_total += self.loss_weights['feature_matching'][i] * value\n loss_values['feature_matching'] = value_total\n\n if (self.loss_weights['equivariance_value'] + self.loss_weights['equivariance_jacobian']) != 0:\n transform = Transform(x['driving'].shape[0], **self.train_params['transform_params'])\n transformed_frame = transform.transform_frame(x['driving'])\n transformed_kp = self.kp_extractor(transformed_frame)\n\n generated['transformed_frame'] = transformed_frame\n generated['transformed_kp'] = transformed_kp\n\n ## Value loss part\n if self.loss_weights['equivariance_value'] != 0:\n value = torch.abs(kp_driving['value'] - transform.warp_coordinates(transformed_kp['value'])).mean()\n loss_values['equivariance_value'] = self.loss_weights['equivariance_value'] * value\n\n ## jacobian loss part\n if self.loss_weights['equivariance_jacobian'] != 0:\n jacobian_transformed = torch.matmul(transform.jacobian(transformed_kp['value']),\n transformed_kp['jacobian'])\n\n normed_driving = torch.inverse(kp_driving['jacobian'])\n normed_transformed = jacobian_transformed\n value = torch.matmul(normed_driving, normed_transformed)\n\n eye = torch.eye(2).view(1, 1, 2, 2).type(value.type())\n\n value = torch.abs(eye - value).mean()\n loss_values['equivariance_jacobian'] = self.loss_weights['equivariance_jacobian'] * value\n\n return loss_values, generated\n\n\nclass DiscriminatorFullModel(torch.nn.Module):\n \"\"\"\n Merge all discriminator related updates into single model for better multi-gpu usage\n \"\"\"\n\n def __init__(self, kp_extractor, generator, discriminator, train_params):\n super(DiscriminatorFullModel, self).__init__()\n self.kp_extractor = kp_extractor\n self.generator = generator\n self.discriminator = discriminator\n self.train_params = train_params\n self.scales = self.discriminator.scales\n self.pyramid = ImagePyramide(self.scales, generator.num_channels)\n if torch.cuda.is_available():\n self.pyramid = self.pyramid.cuda()\n\n self.loss_weights = train_params['loss_weights']\n\n def forward(self, x, generated):\n pyramide_real = self.pyramid(x['driving'])\n pyramide_generated = self.pyramid(generated['prediction'].detach())\n\n kp_driving = generated['kp_driving']\n discriminator_maps_generated = self.discriminator(pyramide_generated, kp=detach_kp(kp_driving))\n discriminator_maps_real = self.discriminator(pyramide_real, kp=detach_kp(kp_driving))\n\n loss_values = {}\n value_total = 0\n for scale in self.scales:\n key = 'prediction_map_%s' % scale\n value = (1 - discriminator_maps_real[key]) ** 2 + discriminator_maps_generated[key] ** 2\n value_total += self.loss_weights['discriminator_gan'] * value.mean()\n loss_values['disc_gan'] = value_total\n\n return loss_values\n"
},
{
"path": "modules/util.py",
"content": "from torch import nn\n\nimport torch.nn.functional as F\nimport torch\n\nfrom sync_batchnorm import SynchronizedBatchNorm2d as BatchNorm2d\n\n\ndef kp2gaussian(kp, spatial_size, kp_variance):\n \"\"\"\n Transform a keypoint into gaussian like representation\n \"\"\"\n mean = kp['value']\n\n coordinate_grid = make_coordinate_grid(spatial_size, mean.type())\n number_of_leading_dimensions = len(mean.shape) - 1\n shape = (1,) * number_of_leading_dimensions + coordinate_grid.shape\n coordinate_grid = coordinate_grid.view(*shape)\n repeats = mean.shape[:number_of_leading_dimensions] + (1, 1, 1)\n coordinate_grid = coordinate_grid.repeat(*repeats)\n\n # Preprocess kp shape\n shape = mean.shape[:number_of_leading_dimensions] + (1, 1, 2)\n mean = mean.view(*shape)\n\n mean_sub = (coordinate_grid - mean)\n\n out = torch.exp(-0.5 * (mean_sub ** 2).sum(-1) / kp_variance)\n\n return out\n\n\ndef make_coordinate_grid(spatial_size, type):\n \"\"\"\n Create a meshgrid [-1,1] x [-1,1] of given spatial_size.\n \"\"\"\n h, w = spatial_size\n x = torch.arange(w).type(type)\n y = torch.arange(h).type(type)\n\n x = (2 * (x / (w - 1)) - 1)\n y = (2 * (y / (h - 1)) - 1)\n\n yy = y.view(-1, 1).repeat(1, w)\n xx = x.view(1, -1).repeat(h, 1)\n\n meshed = torch.cat([xx.unsqueeze_(2), yy.unsqueeze_(2)], 2)\n\n return meshed\n\n\nclass ResBlock2d(nn.Module):\n \"\"\"\n Res block, preserve spatial resolution.\n \"\"\"\n\n def __init__(self, in_features, kernel_size, padding):\n super(ResBlock2d, self).__init__()\n self.conv1 = nn.Conv2d(in_channels=in_features, out_channels=in_features, kernel_size=kernel_size,\n padding=padding)\n self.conv2 = nn.Conv2d(in_channels=in_features, out_channels=in_features, kernel_size=kernel_size,\n padding=padding)\n self.norm1 = BatchNorm2d(in_features, affine=True)\n self.norm2 = BatchNorm2d(in_features, affine=True)\n\n def forward(self, x):\n out = self.norm1(x)\n out = F.relu(out)\n out = self.conv1(out)\n out = self.norm2(out)\n out = F.relu(out)\n out = self.conv2(out)\n out += x\n return out\n\n\nclass UpBlock2d(nn.Module):\n \"\"\"\n Upsampling block for use in decoder.\n \"\"\"\n\n def __init__(self, in_features, out_features, kernel_size=3, padding=1, groups=1):\n super(UpBlock2d, self).__init__()\n\n self.conv = nn.Conv2d(in_channels=in_features, out_channels=out_features, kernel_size=kernel_size,\n padding=padding, groups=groups)\n self.norm = BatchNorm2d(out_features, affine=True)\n\n def forward(self, x):\n out = F.interpolate(x, scale_factor=2)\n out = self.conv(out)\n out = self.norm(out)\n out = F.relu(out)\n return out\n\n\nclass DownBlock2d(nn.Module):\n \"\"\"\n Downsampling block for use in encoder.\n \"\"\"\n\n def __init__(self, in_features, out_features, kernel_size=3, padding=1, groups=1):\n super(DownBlock2d, self).__init__()\n self.conv = nn.Conv2d(in_channels=in_features, out_channels=out_features, kernel_size=kernel_size,\n padding=padding, groups=groups)\n self.norm = BatchNorm2d(out_features, affine=True)\n self.pool = nn.AvgPool2d(kernel_size=(2, 2))\n\n def forward(self, x):\n out = self.conv(x)\n out = self.norm(out)\n out = F.relu(out)\n out = self.pool(out)\n return out\n\n\nclass SameBlock2d(nn.Module):\n \"\"\"\n Simple block, preserve spatial resolution.\n \"\"\"\n\n def __init__(self, in_features, out_features, groups=1, kernel_size=3, padding=1):\n super(SameBlock2d, self).__init__()\n self.conv = nn.Conv2d(in_channels=in_features, out_channels=out_features,\n kernel_size=kernel_size, padding=padding, groups=groups)\n self.norm = BatchNorm2d(out_features, affine=True)\n\n def forward(self, x):\n out = self.conv(x)\n out = self.norm(out)\n out = F.relu(out)\n return out\n\n\nclass Encoder(nn.Module):\n \"\"\"\n Hourglass Encoder\n \"\"\"\n\n def __init__(self, block_expansion, in_features, num_blocks=3, max_features=256):\n super(Encoder, self).__init__()\n\n down_blocks = []\n for i in range(num_blocks):\n down_blocks.append(DownBlock2d(in_features if i == 0 else min(max_features, block_expansion * (2 ** i)),\n min(max_features, block_expansion * (2 ** (i + 1))),\n kernel_size=3, padding=1))\n self.down_blocks = nn.ModuleList(down_blocks)\n\n def forward(self, x):\n outs = [x]\n for down_block in self.down_blocks:\n outs.append(down_block(outs[-1]))\n return outs\n\n\nclass Decoder(nn.Module):\n \"\"\"\n Hourglass Decoder\n \"\"\"\n\n def __init__(self, block_expansion, in_features, num_blocks=3, max_features=256):\n super(Decoder, self).__init__()\n\n up_blocks = []\n\n for i in range(num_blocks)[::-1]:\n in_filters = (1 if i == num_blocks - 1 else 2) * min(max_features, block_expansion * (2 ** (i + 1)))\n out_filters = min(max_features, block_expansion * (2 ** i))\n up_blocks.append(UpBlock2d(in_filters, out_filters, kernel_size=3, padding=1))\n\n self.up_blocks = nn.ModuleList(up_blocks)\n self.out_filters = block_expansion + in_features\n\n def forward(self, x):\n out = x.pop()\n for up_block in self.up_blocks:\n out = up_block(out)\n skip = x.pop()\n out = torch.cat([out, skip], dim=1)\n return out\n\n\nclass Hourglass(nn.Module):\n \"\"\"\n Hourglass architecture.\n \"\"\"\n\n def __init__(self, block_expansion, in_features, num_blocks=3, max_features=256):\n super(Hourglass, self).__init__()\n self.encoder = Encoder(block_expansion, in_features, num_blocks, max_features)\n self.decoder = Decoder(block_expansion, in_features, num_blocks, max_features)\n self.out_filters = self.decoder.out_filters\n\n def forward(self, x):\n return self.decoder(self.encoder(x))\n\n\nclass AntiAliasInterpolation2d(nn.Module):\n \"\"\"\n Band-limited downsampling, for better preservation of the input signal.\n \"\"\"\n def __init__(self, channels, scale):\n super(AntiAliasInterpolation2d, self).__init__()\n sigma = (1 / scale - 1) / 2\n kernel_size = 2 * round(sigma * 4) + 1\n self.ka = kernel_size // 2\n self.kb = self.ka - 1 if kernel_size % 2 == 0 else self.ka\n\n kernel_size = [kernel_size, kernel_size]\n sigma = [sigma, sigma]\n # The gaussian kernel is the product of the\n # gaussian function of each dimension.\n kernel = 1\n meshgrids = torch.meshgrid(\n [\n torch.arange(size, dtype=torch.float32)\n for size in kernel_size\n ]\n )\n for size, std, mgrid in zip(kernel_size, sigma, meshgrids):\n mean = (size - 1) / 2\n kernel *= torch.exp(-(mgrid - mean) ** 2 / (2 * std ** 2))\n\n # Make sure sum of values in gaussian kernel equals 1.\n kernel = kernel / torch.sum(kernel)\n # Reshape to depthwise convolutional weight\n kernel = kernel.view(1, 1, *kernel.size())\n kernel = kernel.repeat(channels, *[1] * (kernel.dim() - 1))\n\n self.register_buffer('weight', kernel)\n self.groups = channels\n self.scale = scale\n inv_scale = 1 / scale\n self.int_inv_scale = int(inv_scale)\n\n def forward(self, input):\n if self.scale == 1.0:\n return input\n\n out = F.pad(input, (self.ka, self.kb, self.ka, self.kb))\n out = F.conv2d(out, weight=self.weight, groups=self.groups)\n out = out[:, :, ::self.int_inv_scale, ::self.int_inv_scale]\n\n return out\n"
},
{
"path": "old_demo.ipynb",
"content": "{\n \"nbformat\": 4,\n \"nbformat_minor\": 0,\n \"metadata\": {\n \"colab\": {\n \"name\": \"first-order-model-demo.ipynb\",\n \"provenance\": [],\n \"toc_visible\": true,\n \"include_colab_link\": true\n },\n \"kernelspec\": {\n \"name\": \"python3\",\n \"display_name\": \"Python 3\"\n },\n \"accelerator\": \"GPU\"\n },\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {\n \"id\": \"view-in-github\",\n \"colab_type\": \"text\"\n },\n \"source\": [\n \"\"\n ]\n },\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {\n \"id\": \"cdO_RxQZLahB\"\n },\n \"source\": [\n \"# Demo for paper \\\"First Order Motion Model for Image Animation\\\"\"\n ]\n },\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {\n \"id\": \"GCDNKsEGLtR6\"\n },\n \"source\": [\n \"**Clone repository**\"\n ]\n },\n {\n \"cell_type\": \"code\",\n \"metadata\": {\n \"id\": \"UCMFMJV7K-ag\",\n \"colab\": {\n \"base_uri\": \"https://localhost:8080/\",\n \"height\": 104\n },\n \"outputId\": \"836efe50-65d7-4c95-a17e-13fc3922b491\"\n },\n \"source\": [\n \"!git clone https://github.com/AliaksandrSiarohin/first-order-model\"\n ],\n \"execution_count\": null,\n \"outputs\": [\n {\n \"output_type\": \"stream\",\n \"text\": [\n \"Cloning into 'first-order-model'...\\n\",\n \"remote: Enumerating objects: 246, done.\\u001b[K\\n\",\n \"remote: Total 246 (delta 0), reused 0 (delta 0), pack-reused 246\\u001b[K\\n\",\n \"Receiving objects: 100% (246/246), 71.46 MiB | 22.54 MiB/s, done.\\n\",\n \"Resolving deltas: 100% (121/121), done.\\n\"\n ],\n \"name\": \"stdout\"\n }\n ]\n },\n {\n \"cell_type\": \"code\",\n \"metadata\": {\n \"id\": \"PBp6l_4bBYUL\",\n \"colab\": {\n \"base_uri\": \"https://localhost:8080/\",\n \"height\": 34\n },\n \"outputId\": \"702bdf2c-d6d2-41ec-cf3c-9196452544d8\"\n },\n \"source\": [\n \"cd first-order-model\"\n ],\n \"execution_count\": null,\n \"outputs\": [\n {\n \"output_type\": \"stream\",\n \"text\": [\n \"/content/first-order-model\\n\"\n ],\n \"name\": \"stdout\"\n }\n ]\n },\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {\n \"id\": \"IcMX7ueZO0Oa\"\n },\n \"source\": [\n \"**Mount your Google drive folder on Colab**\"\n ]\n },\n {\n \"cell_type\": \"code\",\n \"metadata\": {\n \"id\": \"tDbMA8R9OuUo\",\n \"colab\": {\n \"base_uri\": \"https://localhost:8080/\",\n \"height\": 34\n },\n \"outputId\": \"f92ce039-d693-4e03-879b-d0d49a121da2\"\n },\n \"source\": [\n \"from google.colab import drive\\n\",\n \"drive.mount('/content/gdrive')\"\n ],\n \"execution_count\": null,\n \"outputs\": [\n {\n \"output_type\": \"stream\",\n \"text\": [\n \"Mounted at /content/gdrive\\n\"\n ],\n \"name\": \"stdout\"\n }\n ]\n },\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {\n \"id\": \"VsgVK1EURXkd\"\n },\n \"source\": [\n \"**Add folder https://drive.google.com/drive/folders/1kZ1gCnpfU0BnpdU47pLM_TQ6RypDDqgw?usp=sharing to your google drive.\\n\",\n \"Alternativelly you can use this mirror link https://drive.google.com/drive/folders/16inDpBRPT1UC0YMGMX3dKvRnOUsf5Dhn?usp=sharing**\"\n ]\n },\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {\n \"id\": \"rW-ipQXPOWUo\"\n },\n \"source\": [\n \"**Load driving video and source image**\"\n ]\n },\n {\n \"cell_type\": \"code\",\n \"metadata\": {\n \"id\": \"Oxi6-riLOgnm\",\n \"colab\": {\n \"base_uri\": \"https://localhost:8080/\",\n \"height\": 453\n },\n \"outputId\": \"d38a8850-9eb1-4de4-9bf2-24cbd847ca1f\"\n },\n \"source\": [\n \"import imageio\\n\",\n \"import numpy as np\\n\",\n \"import matplotlib.pyplot as plt\\n\",\n \"import matplotlib.animation as animation\\n\",\n \"from skimage.transform import resize\\n\",\n \"from IPython.display import HTML\\n\",\n \"import warnings\\n\",\n \"warnings.filterwarnings(\\\"ignore\\\")\\n\",\n \"\\n\",\n \"source_image = imageio.imread('/content/gdrive/My Drive/first-order-motion-model/02.png')\\n\",\n \"reader = imageio.get_reader('/content/gdrive/My Drive/first-order-motion-model/04.mp4')\\n\",\n \"\\n\",\n \"\\n\",\n \"#Resize image and video to 256x256\\n\",\n \"\\n\",\n \"source_image = resize(source_image, (256, 256))[..., :3]\\n\",\n \"\\n\",\n \"fps = reader.get_meta_data()['fps']\\n\",\n \"driving_video = []\\n\",\n \"try:\\n\",\n \" for im in reader:\\n\",\n \" driving_video.append(im)\\n\",\n \"except RuntimeError:\\n\",\n \" pass\\n\",\n \"reader.close()\\n\",\n \"\\n\",\n \"driving_video = [resize(frame, (256, 256))[..., :3] for frame in driving_video]\\n\",\n \"\\n\",\n \"def display(source, driving, generated=None):\\n\",\n \" fig = plt.figure(figsize=(8 + 4 * (generated is not None), 6))\\n\",\n \"\\n\",\n \" ims = []\\n\",\n \" for i in range(len(driving)):\\n\",\n \" cols = [source]\\n\",\n \" cols.append(driving[i])\\n\",\n \" if generated is not None:\\n\",\n \" cols.append(generated[i])\\n\",\n \" im = plt.imshow(np.concatenate(cols, axis=1), animated=True)\\n\",\n \" plt.axis('off')\\n\",\n \" ims.append([im])\\n\",\n \"\\n\",\n \" ani = animation.ArtistAnimation(fig, ims, interval=50, repeat_delay=1000)\\n\",\n \" plt.close()\\n\",\n \" return ani\\n\",\n \" \\n\",\n \"\\n\",\n \"HTML(display(source_image, driving_video).to_html5_video())\"\n ],\n \"execution_count\": null,\n \"outputs\": [\n {\n \"output_type\": \"execute_result\",\n \"data\": {\n \"text/html\": [\n \"\"\n ],\n \"text/plain\": [\n \"\"\n ]\n },\n \"metadata\": {\n \"tags\": []\n },\n \"execution_count\": 5\n }\n ]\n },\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {\n \"id\": \"xjM7ubVfWrwT\"\n },\n \"source\": [\n \"**Create a model and load checkpoints**\"\n ]\n },\n {\n \"cell_type\": \"code\",\n \"metadata\": {\n \"id\": \"3FQiXqQPWt5B\"\n },\n \"source\": [\n \"from demo import load_checkpoints\\n\",\n \"generator, kp_detector = load_checkpoints(config_path='config/vox-256.yaml', \\n\",\n \" checkpoint_path='/content/gdrive/My Drive/first-order-motion-model/vox-cpk.pth.tar')\"\n ],\n \"execution_count\": null,\n \"outputs\": []\n },\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {\n \"id\": \"fdFdasHEj3t7\"\n },\n \"source\": [\n \"**Perform image animation**\"\n ]\n },\n {\n \"cell_type\": \"code\",\n \"metadata\": {\n \"id\": \"SB12II11kF4c\",\n \"colab\": {\n \"base_uri\": \"https://localhost:8080/\",\n \"height\": 471\n },\n \"outputId\": \"9e2274aa-fd55-4eed-cb50-bec72fcfb8b9\"\n },\n \"source\": [\n \"from demo import make_animation\\n\",\n \"from skimage import img_as_ubyte\\n\",\n \"\\n\",\n \"predictions = make_animation(source_image, driving_video, generator, kp_detector, relative=True)\\n\",\n \"\\n\",\n \"#save resulting video\\n\",\n \"imageio.mimsave('../generated.mp4', [img_as_ubyte(frame) for frame in predictions], fps=fps)\\n\",\n \"#video can be downloaded from /content folder\\n\",\n \"\\n\",\n \"HTML(display(source_image, driving_video, predictions).to_html5_video())\"\n ],\n \"execution_count\": null,\n \"outputs\": [\n {\n \"output_type\": \"stream\",\n \"text\": [\n \"100%|██████████| 211/211 [00:26<00:00, 7.92it/s]\\n\"\n ],\n \"name\": \"stderr\"\n },\n {\n \"output_type\": \"execute_result\",\n \"data\": {\n \"text/html\": [\n \"\"\n ],\n \"text/plain\": [\n \"\"\n ]\n },\n \"metadata\": {\n \"tags\": []\n },\n \"execution_count\": 7\n }\n ]\n },\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {\n \"id\": \"-tJN01xQCpqH\"\n },\n \"source\": [\n \"**In the cell above we use relative keypoint displacement to animate the objects. We can use absolute coordinates instead, but in this way all the object proporions will be inherited from the driving video. For example Putin haircut will be extended to match Trump haircut.**\"\n ]\n },\n {\n \"cell_type\": \"code\",\n \"metadata\": {\n \"id\": \"aOE_W_kfC9aX\",\n \"colab\": {\n \"base_uri\": \"https://localhost:8080/\",\n \"height\": 471\n },\n \"outputId\": \"f472a888-0200-4b21-b6d2-b6f6737bc9e5\"\n },\n \"source\": [\n \"predictions = make_animation(source_image, driving_video, generator, kp_detector, relative=False, adapt_movement_scale=True)\\n\",\n \"HTML(display(source_image, driving_video, predictions).to_html5_video())\"\n ],\n \"execution_count\": null,\n \"outputs\": [\n {\n \"output_type\": \"stream\",\n \"text\": [\n \"100%|██████████| 211/211 [00:26<00:00, 7.90it/s]\\n\"\n ],\n \"name\": \"stderr\"\n },\n {\n \"output_type\": \"execute_result\",\n \"data\": {\n \"text/html\": [\n \"\"\n ],\n \"text/plain\": [\n \"\"\n ]\n },\n \"metadata\": {\n \"tags\": []\n },\n \"execution_count\": 8\n }\n ]\n },\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {\n \"id\": \"QnXrecuX6_Kw\"\n },\n \"source\": [\n \"## Running on your data\\n\",\n \"\\n\",\n \"**First we need to crop a face from both source image and video, while simple graphic editor like paint can be used for cropping from image. Cropping from video is more complicated. You can use ffpmeg for this.**\"\n ]\n },\n {\n \"cell_type\": \"code\",\n \"metadata\": {\n \"id\": \"brJlA_5o72Xc\",\n \"colab\": {\n \"base_uri\": \"https://localhost:8080/\",\n \"height\": 1000\n },\n \"outputId\": \"c2becb7e-e2ee-4651-ee8a-f906b5663417\"\n },\n \"source\": [\n \"!ffmpeg -i /content/gdrive/My\\\\ Drive/first-order-motion-model/07.mkv -ss 00:08:57.50 -t 00:00:08 -filter:v \\\"crop=600:600:760:50\\\" -async 1 hinton.mp4\"\n ],\n \"execution_count\": null,\n \"outputs\": [\n {\n \"output_type\": \"stream\",\n \"text\": [\n \"ffmpeg version 3.4.8-0ubuntu0.2 Copyright (c) 2000-2020 the FFmpeg developers\\n\",\n \" built with gcc 7 (Ubuntu 7.5.0-3ubuntu1~18.04)\\n\",\n \" configuration: --prefix=/usr --extra-version=0ubuntu0.2 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared\\n\",\n \" libavutil 55. 78.100 / 55. 78.100\\n\",\n \" libavcodec 57.107.100 / 57.107.100\\n\",\n \" libavformat 57. 83.100 / 57. 83.100\\n\",\n \" libavdevice 57. 10.100 / 57. 10.100\\n\",\n \" libavfilter 6.107.100 / 6.107.100\\n\",\n \" libavresample 3. 7. 0 / 3. 7. 0\\n\",\n \" libswscale 4. 8.100 / 4. 8.100\\n\",\n \" libswresample 2. 9.100 / 2. 9.100\\n\",\n \" libpostproc 54. 7.100 / 54. 7.100\\n\",\n \"Input #0, matroska,webm, from '/content/gdrive/My Drive/first-order-motion-model/07.mkv':\\n\",\n \" Metadata:\\n\",\n \" ENCODER : Lavf57.83.100\\n\",\n \" Duration: 00:14:59.73, start: 0.000000, bitrate: 2343 kb/s\\n\",\n \" Stream #0:0(eng): Video: vp9 (Profile 0), yuv420p(tv, bt709), 1920x1080, SAR 1:1 DAR 16:9, 29.97 fps, 29.97 tbr, 1k tbn, 1k tbc (default)\\n\",\n \" Metadata:\\n\",\n \" DURATION : 00:14:59.665000000\\n\",\n \" Stream #0:1(eng): Audio: aac (LC), 44100 Hz, stereo, fltp (default)\\n\",\n \" Metadata:\\n\",\n \" HANDLER_NAME : SoundHandler\\n\",\n \" DURATION : 00:14:59.727000000\\n\",\n \"Stream mapping:\\n\",\n \" Stream #0:0 -> #0:0 (vp9 (native) -> h264 (libx264))\\n\",\n \" Stream #0:1 -> #0:1 (aac (native) -> aac (native))\\n\",\n \"Press [q] to stop, [?] for help\\n\",\n \"-async is forwarded to lavfi similarly to -af aresample=async=1:min_hard_comp=0.100000:first_pts=0.\\n\",\n \"\\u001b[1;36m[libx264 @ 0x55709b1c4800] \\u001b[0musing SAR=1/1\\n\",\n \"\\u001b[1;36m[libx264 @ 0x55709b1c4800] \\u001b[0musing cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2\\n\",\n \"\\u001b[1;36m[libx264 @ 0x55709b1c4800] \\u001b[0mprofile High, level 3.1\\n\",\n \"\\u001b[1;36m[libx264 @ 0x55709b1c4800] \\u001b[0m264 - core 152 r2854 e9a5903 - H.264/MPEG-4 AVC codec - Copyleft 2003-2017 - http://www.videolan.org/x264.html - options: cabac=1 ref=3 deblock=1:0:0 analyse=0x3:0x113 me=hex subme=7 psy=1 psy_rd=1.00:0.00 mixed_ref=1 me_range=16 chroma_me=1 trellis=1 8x8dct=1 cqm=0 deadzone=21,11 fast_pskip=1 chroma_qp_offset=-2 threads=3 lookahead_threads=1 sliced_threads=0 nr=0 decimate=1 interlaced=0 bluray_compat=0 constrained_intra=0 bframes=3 b_pyramid=2 b_adapt=1 b_bias=0 direct=1 weightb=1 open_gop=0 weightp=2 keyint=250 keyint_min=25 scenecut=40 intra_refresh=0 rc_lookahead=40 rc=crf mbtree=1 crf=23.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 ip_ratio=1.40 aq=1:1.00\\n\",\n \"Output #0, mp4, to 'hinton.mp4':\\n\",\n \" Metadata:\\n\",\n \" encoder : Lavf57.83.100\\n\",\n \" Stream #0:0(eng): Video: h264 (libx264) (avc1 / 0x31637661), yuv420p, 600x600 [SAR 1:1 DAR 1:1], q=-1--1, 29.97 fps, 30k tbn, 29.97 tbc (default)\\n\",\n \" Metadata:\\n\",\n \" DURATION : 00:14:59.665000000\\n\",\n \" encoder : Lavc57.107.100 libx264\\n\",\n \" Side data:\\n\",\n \" cpb: bitrate max/min/avg: 0/0/0 buffer size: 0 vbv_delay: -1\\n\",\n \" Stream #0:1(eng): Audio: aac (LC) (mp4a / 0x6134706D), 44100 Hz, stereo, fltp, 128 kb/s (default)\\n\",\n \" Metadata:\\n\",\n \" HANDLER_NAME : SoundHandler\\n\",\n \" DURATION : 00:14:59.727000000\\n\",\n \" encoder : Lavc57.107.100 aac\\n\",\n \"frame= 240 fps=2.5 q=-1.0 Lsize= 1301kB time=00:00:08.01 bitrate=1330.6kbits/s speed=0.0844x \\n\",\n \"video:1166kB audio:125kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.761764%\\n\",\n \"\\u001b[1;36m[libx264 @ 0x55709b1c4800] \\u001b[0mframe I:1 Avg QP:22.44 size: 28019\\n\",\n \"\\u001b[1;36m[libx264 @ 0x55709b1c4800] \\u001b[0mframe P:62 Avg QP:23.31 size: 12894\\n\",\n \"\\u001b[1;36m[libx264 @ 0x55709b1c4800] \\u001b[0mframe B:177 Avg QP:28.63 size: 2068\\n\",\n \"\\u001b[1;36m[libx264 @ 0x55709b1c4800] \\u001b[0mconsecutive B-frames: 0.8% 1.7% 2.5% 95.0%\\n\",\n \"\\u001b[1;36m[libx264 @ 0x55709b1c4800] \\u001b[0mmb I I16..4: 12.7% 76.2% 11.1%\\n\",\n \"\\u001b[1;36m[libx264 @ 0x55709b1c4800] \\u001b[0mmb P I16..4: 1.9% 8.9% 1.1% P16..4: 35.3% 21.3% 10.8% 0.0% 0.0% skip:20.7%\\n\",\n \"\\u001b[1;36m[libx264 @ 0x55709b1c4800] \\u001b[0mmb B I16..4: 0.0% 0.1% 0.0% B16..8: 39.1% 5.4% 1.0% direct: 1.4% skip:52.9% L0:35.4% L1:48.5% BI:16.2%\\n\",\n \"\\u001b[1;36m[libx264 @ 0x55709b1c4800] \\u001b[0m8x8 transform intra:75.2% inter:77.3%\\n\",\n \"\\u001b[1;36m[libx264 @ 0x55709b1c4800] \\u001b[0mcoded y,uvDC,uvAC intra: 61.9% 52.1% 5.8% inter: 15.2% 6.9% 0.0%\\n\",\n \"\\u001b[1;36m[libx264 @ 0x55709b1c4800] \\u001b[0mi16 v,h,dc,p: 69% 8% 8% 15%\\n\",\n \"\\u001b[1;36m[libx264 @ 0x55709b1c4800] \\u001b[0mi8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 25% 10% 19% 5% 8% 11% 8% 9% 6%\\n\",\n \"\\u001b[1;36m[libx264 @ 0x55709b1c4800] \\u001b[0mi4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 23% 8% 11% 5% 12% 21% 7% 9% 4%\\n\",\n \"\\u001b[1;36m[libx264 @ 0x55709b1c4800] \\u001b[0mi8c dc,h,v,p: 53% 20% 19% 8%\\n\",\n \"\\u001b[1;36m[libx264 @ 0x55709b1c4800] \\u001b[0mWeighted P-Frames: Y:21.0% UV:1.6%\\n\",\n \"\\u001b[1;36m[libx264 @ 0x55709b1c4800] \\u001b[0mref P L0: 57.9% 21.2% 14.0% 5.9% 1.1%\\n\",\n \"\\u001b[1;36m[libx264 @ 0x55709b1c4800] \\u001b[0mref B L0: 93.5% 5.3% 1.2%\\n\",\n \"\\u001b[1;36m[libx264 @ 0x55709b1c4800] \\u001b[0mref B L1: 97.4% 2.6%\\n\",\n \"\\u001b[1;36m[libx264 @ 0x55709b1c4800] \\u001b[0mkb/s:1192.28\\n\",\n \"\\u001b[1;36m[aac @ 0x55709b1c5700] \\u001b[0mQavg: 534.430\\n\"\n ],\n \"name\": \"stdout\"\n }\n ]\n },\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {\n \"id\": \"NSHSxV8iGybI\"\n },\n \"source\": [\n \"**Another posibility is to use some screen recording tool, or if you need to crop many images at ones use face detector(https://github.com/1adrianb/face-alignment) , see https://github.com/AliaksandrSiarohin/video-preprocessing for preprcessing of VoxCeleb.** \"\n ]\n },\n {\n \"cell_type\": \"code\",\n \"metadata\": {\n \"id\": \"d8kQ3U7MHqh-\",\n \"colab\": {\n \"base_uri\": \"https://localhost:8080/\",\n \"height\": 471\n },\n \"outputId\": \"8890e858-ac38-4d59-b014-cc4ed974f276\"\n },\n \"source\": [\n \"source_image = imageio.imread('/content/gdrive/My Drive/first-order-motion-model/09.png')\\n\",\n \"driving_video = imageio.mimread('hinton.mp4', memtest=False)\\n\",\n \"\\n\",\n \"\\n\",\n \"#Resize image and video to 256x256\\n\",\n \"\\n\",\n \"source_image = resize(source_image, (256, 256))[..., :3]\\n\",\n \"driving_video = [resize(frame, (256, 256))[..., :3] for frame in driving_video]\\n\",\n \"\\n\",\n \"predictions = make_animation(source_image, driving_video, generator, kp_detector, relative=True,\\n\",\n \" adapt_movement_scale=True)\\n\",\n \"\\n\",\n \"HTML(display(source_image, driving_video, predictions).to_html5_video())\"\n ],\n \"execution_count\": null,\n \"outputs\": [\n {\n \"output_type\": \"stream\",\n \"text\": [\n \"100%|██████████| 240/240 [00:30<00:00, 7.94it/s]\\n\"\n ],\n \"name\": \"stderr\"\n },\n {\n \"output_type\": \"execute_result\",\n \"data\": {\n \"text/html\": [\n \"\"\n ],\n \"text/plain\": [\n \"\"\n ]\n },\n \"metadata\": {\n \"tags\": []\n },\n \"execution_count\": 10\n }\n ]\n }\n ]\n}"
},
{
"path": "reconstruction.py",
"content": "import os\nfrom tqdm import tqdm\nimport torch\nfrom torch.utils.data import DataLoader\nfrom logger import Logger, Visualizer\nimport numpy as np\nimport imageio\nfrom sync_batchnorm import DataParallelWithCallback\n\n\ndef reconstruction(config, generator, kp_detector, checkpoint, log_dir, dataset):\n png_dir = os.path.join(log_dir, 'reconstruction/png')\n log_dir = os.path.join(log_dir, 'reconstruction')\n\n if checkpoint is not None:\n Logger.load_cpk(checkpoint, generator=generator, kp_detector=kp_detector)\n else:\n raise AttributeError(\"Checkpoint should be specified for mode='reconstruction'.\")\n dataloader = DataLoader(dataset, batch_size=1, shuffle=False, num_workers=1)\n\n if not os.path.exists(log_dir):\n os.makedirs(log_dir)\n\n if not os.path.exists(png_dir):\n os.makedirs(png_dir)\n\n loss_list = []\n if torch.cuda.is_available():\n generator = DataParallelWithCallback(generator)\n kp_detector = DataParallelWithCallback(kp_detector)\n\n generator.eval()\n kp_detector.eval()\n\n for it, x in tqdm(enumerate(dataloader)):\n if config['reconstruction_params']['num_videos'] is not None:\n if it > config['reconstruction_params']['num_videos']:\n break\n with torch.no_grad():\n predictions = []\n visualizations = []\n if torch.cuda.is_available():\n x['video'] = x['video'].cuda()\n kp_source = kp_detector(x['video'][:, :, 0])\n for frame_idx in range(x['video'].shape[2]):\n source = x['video'][:, :, 0]\n driving = x['video'][:, :, frame_idx]\n kp_driving = kp_detector(driving)\n out = generator(source, kp_source=kp_source, kp_driving=kp_driving)\n out['kp_source'] = kp_source\n out['kp_driving'] = kp_driving\n del out['sparse_deformed']\n predictions.append(np.transpose(out['prediction'].data.cpu().numpy(), [0, 2, 3, 1])[0])\n\n visualization = Visualizer(**config['visualizer_params']).visualize(source=source,\n driving=driving, out=out)\n visualizations.append(visualization)\n\n loss_list.append(torch.abs(out['prediction'] - driving).mean().cpu().numpy())\n\n predictions = np.concatenate(predictions, axis=1)\n imageio.imsave(os.path.join(png_dir, x['name'][0] + '.png'), (255 * predictions).astype(np.uint8))\n\n image_name = x['name'][0] + config['reconstruction_params']['format']\n imageio.mimsave(os.path.join(log_dir, image_name), visualizations)\n\n print(\"Reconstruction loss: %s\" % np.mean(loss_list))\n"
},
{
"path": "requirements.txt",
"content": "ffmpeg-python==0.2.0\nimageio==2.22.0\nimageio-ffmpeg==0.4.7\nmatplotlib==3.6.0\nnumpy==1.23.3\npandas==1.5.0\npython-dateutil==2.8.2\npytz==2022.2.1\nPyYAML==6.0\nscikit-image==0.19.3\nscikit-learn==1.1.2\nscipy==1.9.1\ntorch==1.12.1\ntorchvision==0.13.1\ntqdm==4.64.1\n"
},
{
"path": "run.py",
"content": "import matplotlib\n\nmatplotlib.use('Agg')\n\nimport os, sys\nimport yaml\nfrom argparse import ArgumentParser\nfrom time import gmtime, strftime\nfrom shutil import copy\n\nfrom frames_dataset import FramesDataset\n\nfrom modules.generator import OcclusionAwareGenerator\nfrom modules.discriminator import MultiScaleDiscriminator\nfrom modules.keypoint_detector import KPDetector\n\nimport torch\n\nfrom train import train\nfrom reconstruction import reconstruction\nfrom animate import animate\n\nif __name__ == \"__main__\":\n \n if sys.version_info[0] < 3:\n raise Exception(\"You must use Python 3 or higher. Recommended version is Python 3.7\")\n\n parser = ArgumentParser()\n parser.add_argument(\"--config\", required=True, help=\"path to config\")\n parser.add_argument(\"--mode\", default=\"train\", choices=[\"train\", \"reconstruction\", \"animate\"])\n parser.add_argument(\"--log_dir\", default='log', help=\"path to log into\")\n parser.add_argument(\"--checkpoint\", default=None, help=\"path to checkpoint to restore\")\n parser.add_argument(\"--device_ids\", default=\"0\", type=lambda x: list(map(int, x.split(','))),\n help=\"Names of the devices comma separated.\")\n parser.add_argument(\"--verbose\", dest=\"verbose\", action=\"store_true\", help=\"Print model architecture\")\n parser.set_defaults(verbose=False)\n\n opt = parser.parse_args()\n with open(opt.config) as f:\n config = yaml.load(f)\n\n if opt.checkpoint is not None:\n log_dir = os.path.join(*os.path.split(opt.checkpoint)[:-1])\n else:\n log_dir = os.path.join(opt.log_dir, os.path.basename(opt.config).split('.')[0])\n log_dir += ' ' + strftime(\"%d_%m_%y_%H.%M.%S\", gmtime())\n\n generator = OcclusionAwareGenerator(**config['model_params']['generator_params'],\n **config['model_params']['common_params'])\n\n if torch.cuda.is_available():\n generator.to(opt.device_ids[0])\n if opt.verbose:\n print(generator)\n\n discriminator = MultiScaleDiscriminator(**config['model_params']['discriminator_params'],\n **config['model_params']['common_params'])\n if torch.cuda.is_available():\n discriminator.to(opt.device_ids[0])\n if opt.verbose:\n print(discriminator)\n\n kp_detector = KPDetector(**config['model_params']['kp_detector_params'],\n **config['model_params']['common_params'])\n\n if torch.cuda.is_available():\n kp_detector.to(opt.device_ids[0])\n\n if opt.verbose:\n print(kp_detector)\n\n dataset = FramesDataset(is_train=(opt.mode == 'train'), **config['dataset_params'])\n\n if not os.path.exists(log_dir):\n os.makedirs(log_dir)\n if not os.path.exists(os.path.join(log_dir, os.path.basename(opt.config))):\n copy(opt.config, log_dir)\n\n if opt.mode == 'train':\n print(\"Training...\")\n train(config, generator, discriminator, kp_detector, opt.checkpoint, log_dir, dataset, opt.device_ids)\n elif opt.mode == 'reconstruction':\n print(\"Reconstruction...\")\n reconstruction(config, generator, kp_detector, opt.checkpoint, log_dir, dataset)\n elif opt.mode == 'animate':\n print(\"Animate...\")\n animate(config, generator, kp_detector, opt.checkpoint, log_dir, dataset)\n"
},
{
"path": "sync_batchnorm/__init__.py",
"content": "# -*- coding: utf-8 -*-\n# File : __init__.py\n# Author : Jiayuan Mao\n# Email : maojiayuan@gmail.com\n# Date : 27/01/2018\n# \n# This file is part of Synchronized-BatchNorm-PyTorch.\n# https://github.com/vacancy/Synchronized-BatchNorm-PyTorch\n# Distributed under MIT License.\n\nfrom .batchnorm import SynchronizedBatchNorm1d, SynchronizedBatchNorm2d, SynchronizedBatchNorm3d\nfrom .replicate import DataParallelWithCallback, patch_replication_callback\n"
},
{
"path": "sync_batchnorm/batchnorm.py",
"content": "# -*- coding: utf-8 -*-\n# File : batchnorm.py\n# Author : Jiayuan Mao\n# Email : maojiayuan@gmail.com\n# Date : 27/01/2018\n# \n# This file is part of Synchronized-BatchNorm-PyTorch.\n# https://github.com/vacancy/Synchronized-BatchNorm-PyTorch\n# Distributed under MIT License.\n\nimport collections\n\nimport torch\nimport torch.nn.functional as F\n\nfrom torch.nn.modules.batchnorm import _BatchNorm\nfrom torch.nn.parallel._functions import ReduceAddCoalesced, Broadcast\n\nfrom .comm import SyncMaster\n\n__all__ = ['SynchronizedBatchNorm1d', 'SynchronizedBatchNorm2d', 'SynchronizedBatchNorm3d']\n\n\ndef _sum_ft(tensor):\n \"\"\"sum over the first and last dimention\"\"\"\n return tensor.sum(dim=0).sum(dim=-1)\n\n\ndef _unsqueeze_ft(tensor):\n \"\"\"add new dementions at the front and the tail\"\"\"\n return tensor.unsqueeze(0).unsqueeze(-1)\n\n\n_ChildMessage = collections.namedtuple('_ChildMessage', ['sum', 'ssum', 'sum_size'])\n_MasterMessage = collections.namedtuple('_MasterMessage', ['sum', 'inv_std'])\n\n\nclass _SynchronizedBatchNorm(_BatchNorm):\n def __init__(self, num_features, eps=1e-5, momentum=0.1, affine=True):\n super(_SynchronizedBatchNorm, self).__init__(num_features, eps=eps, momentum=momentum, affine=affine)\n\n self._sync_master = SyncMaster(self._data_parallel_master)\n\n self._is_parallel = False\n self._parallel_id = None\n self._slave_pipe = None\n\n def forward(self, input):\n # If it is not parallel computation or is in evaluation mode, use PyTorch's implementation.\n if not (self._is_parallel and self.training):\n return F.batch_norm(\n input, self.running_mean, self.running_var, self.weight, self.bias,\n self.training, self.momentum, self.eps)\n\n # Resize the input to (B, C, -1).\n input_shape = input.size()\n input = input.view(input.size(0), self.num_features, -1)\n\n # Compute the sum and square-sum.\n sum_size = input.size(0) * input.size(2)\n input_sum = _sum_ft(input)\n input_ssum = _sum_ft(input ** 2)\n\n # Reduce-and-broadcast the statistics.\n if self._parallel_id == 0:\n mean, inv_std = self._sync_master.run_master(_ChildMessage(input_sum, input_ssum, sum_size))\n else:\n mean, inv_std = self._slave_pipe.run_slave(_ChildMessage(input_sum, input_ssum, sum_size))\n\n # Compute the output.\n if self.affine:\n # MJY:: Fuse the multiplication for speed.\n output = (input - _unsqueeze_ft(mean)) * _unsqueeze_ft(inv_std * self.weight) + _unsqueeze_ft(self.bias)\n else:\n output = (input - _unsqueeze_ft(mean)) * _unsqueeze_ft(inv_std)\n\n # Reshape it.\n return output.view(input_shape)\n\n def __data_parallel_replicate__(self, ctx, copy_id):\n self._is_parallel = True\n self._parallel_id = copy_id\n\n # parallel_id == 0 means master device.\n if self._parallel_id == 0:\n ctx.sync_master = self._sync_master\n else:\n self._slave_pipe = ctx.sync_master.register_slave(copy_id)\n\n def _data_parallel_master(self, intermediates):\n \"\"\"Reduce the sum and square-sum, compute the statistics, and broadcast it.\"\"\"\n\n # Always using same \"device order\" makes the ReduceAdd operation faster.\n # Thanks to:: Tete Xiao (http://tetexiao.com/)\n intermediates = sorted(intermediates, key=lambda i: i[1].sum.get_device())\n\n to_reduce = [i[1][:2] for i in intermediates]\n to_reduce = [j for i in to_reduce for j in i] # flatten\n target_gpus = [i[1].sum.get_device() for i in intermediates]\n\n sum_size = sum([i[1].sum_size for i in intermediates])\n sum_, ssum = ReduceAddCoalesced.apply(target_gpus[0], 2, *to_reduce)\n mean, inv_std = self._compute_mean_std(sum_, ssum, sum_size)\n\n broadcasted = Broadcast.apply(target_gpus, mean, inv_std)\n\n outputs = []\n for i, rec in enumerate(intermediates):\n outputs.append((rec[0], _MasterMessage(*broadcasted[i*2:i*2+2])))\n\n return outputs\n\n def _compute_mean_std(self, sum_, ssum, size):\n \"\"\"Compute the mean and standard-deviation with sum and square-sum. This method\n also maintains the moving average on the master device.\"\"\"\n assert size > 1, 'BatchNorm computes unbiased standard-deviation, which requires size > 1.'\n mean = sum_ / size\n sumvar = ssum - sum_ * mean\n unbias_var = sumvar / (size - 1)\n bias_var = sumvar / size\n\n self.running_mean = (1 - self.momentum) * self.running_mean + self.momentum * mean.data\n self.running_var = (1 - self.momentum) * self.running_var + self.momentum * unbias_var.data\n\n return mean, bias_var.clamp(self.eps) ** -0.5\n\n\nclass SynchronizedBatchNorm1d(_SynchronizedBatchNorm):\n r\"\"\"Applies Synchronized Batch Normalization over a 2d or 3d input that is seen as a\n mini-batch.\n\n .. math::\n\n y = \\frac{x - mean[x]}{ \\sqrt{Var[x] + \\epsilon}} * gamma + beta\n\n This module differs from the built-in PyTorch BatchNorm1d as the mean and\n standard-deviation are reduced across all devices during training.\n\n For example, when one uses `nn.DataParallel` to wrap the network during\n training, PyTorch's implementation normalize the tensor on each device using\n the statistics only on that device, which accelerated the computation and\n is also easy to implement, but the statistics might be inaccurate.\n Instead, in this synchronized version, the statistics will be computed\n over all training samples distributed on multiple devices.\n \n Note that, for one-GPU or CPU-only case, this module behaves exactly same\n as the built-in PyTorch implementation.\n\n The mean and standard-deviation are calculated per-dimension over\n the mini-batches and gamma and beta are learnable parameter vectors\n of size C (where C is the input size).\n\n During training, this layer keeps a running estimate of its computed mean\n and variance. The running sum is kept with a default momentum of 0.1.\n\n During evaluation, this running mean/variance is used for normalization.\n\n Because the BatchNorm is done over the `C` dimension, computing statistics\n on `(N, L)` slices, it's common terminology to call this Temporal BatchNorm\n\n Args:\n num_features: num_features from an expected input of size\n `batch_size x num_features [x width]`\n eps: a value added to the denominator for numerical stability.\n Default: 1e-5\n momentum: the value used for the running_mean and running_var\n computation. Default: 0.1\n affine: a boolean value that when set to ``True``, gives the layer learnable\n affine parameters. Default: ``True``\n\n Shape:\n - Input: :math:`(N, C)` or :math:`(N, C, L)`\n - Output: :math:`(N, C)` or :math:`(N, C, L)` (same shape as input)\n\n Examples:\n >>> # With Learnable Parameters\n >>> m = SynchronizedBatchNorm1d(100)\n >>> # Without Learnable Parameters\n >>> m = SynchronizedBatchNorm1d(100, affine=False)\n >>> input = torch.autograd.Variable(torch.randn(20, 100))\n >>> output = m(input)\n \"\"\"\n\n def _check_input_dim(self, input):\n if input.dim() != 2 and input.dim() != 3:\n raise ValueError('expected 2D or 3D input (got {}D input)'\n .format(input.dim()))\n super(SynchronizedBatchNorm1d, self)._check_input_dim(input)\n\n\nclass SynchronizedBatchNorm2d(_SynchronizedBatchNorm):\n r\"\"\"Applies Batch Normalization over a 4d input that is seen as a mini-batch\n of 3d inputs\n\n .. math::\n\n y = \\frac{x - mean[x]}{ \\sqrt{Var[x] + \\epsilon}} * gamma + beta\n\n This module differs from the built-in PyTorch BatchNorm2d as the mean and\n standard-deviation are reduced across all devices during training.\n\n For example, when one uses `nn.DataParallel` to wrap the network during\n training, PyTorch's implementation normalize the tensor on each device using\n the statistics only on that device, which accelerated the computation and\n is also easy to implement, but the statistics might be inaccurate.\n Instead, in this synchronized version, the statistics will be computed\n over all training samples distributed on multiple devices.\n \n Note that, for one-GPU or CPU-only case, this module behaves exactly same\n as the built-in PyTorch implementation.\n\n The mean and standard-deviation are calculated per-dimension over\n the mini-batches and gamma and beta are learnable parameter vectors\n of size C (where C is the input size).\n\n During training, this layer keeps a running estimate of its computed mean\n and variance. The running sum is kept with a default momentum of 0.1.\n\n During evaluation, this running mean/variance is used for normalization.\n\n Because the BatchNorm is done over the `C` dimension, computing statistics\n on `(N, H, W)` slices, it's common terminology to call this Spatial BatchNorm\n\n Args:\n num_features: num_features from an expected input of\n size batch_size x num_features x height x width\n eps: a value added to the denominator for numerical stability.\n Default: 1e-5\n momentum: the value used for the running_mean and running_var\n computation. Default: 0.1\n affine: a boolean value that when set to ``True``, gives the layer learnable\n affine parameters. Default: ``True``\n\n Shape:\n - Input: :math:`(N, C, H, W)`\n - Output: :math:`(N, C, H, W)` (same shape as input)\n\n Examples:\n >>> # With Learnable Parameters\n >>> m = SynchronizedBatchNorm2d(100)\n >>> # Without Learnable Parameters\n >>> m = SynchronizedBatchNorm2d(100, affine=False)\n >>> input = torch.autograd.Variable(torch.randn(20, 100, 35, 45))\n >>> output = m(input)\n \"\"\"\n\n def _check_input_dim(self, input):\n if input.dim() != 4:\n raise ValueError('expected 4D input (got {}D input)'\n .format(input.dim()))\n super(SynchronizedBatchNorm2d, self)._check_input_dim(input)\n\n\nclass SynchronizedBatchNorm3d(_SynchronizedBatchNorm):\n r\"\"\"Applies Batch Normalization over a 5d input that is seen as a mini-batch\n of 4d inputs\n\n .. math::\n\n y = \\frac{x - mean[x]}{ \\sqrt{Var[x] + \\epsilon}} * gamma + beta\n\n This module differs from the built-in PyTorch BatchNorm3d as the mean and\n standard-deviation are reduced across all devices during training.\n\n For example, when one uses `nn.DataParallel` to wrap the network during\n training, PyTorch's implementation normalize the tensor on each device using\n the statistics only on that device, which accelerated the computation and\n is also easy to implement, but the statistics might be inaccurate.\n Instead, in this synchronized version, the statistics will be computed\n over all training samples distributed on multiple devices.\n \n Note that, for one-GPU or CPU-only case, this module behaves exactly same\n as the built-in PyTorch implementation.\n\n The mean and standard-deviation are calculated per-dimension over\n the mini-batches and gamma and beta are learnable parameter vectors\n of size C (where C is the input size).\n\n During training, this layer keeps a running estimate of its computed mean\n and variance. The running sum is kept with a default momentum of 0.1.\n\n During evaluation, this running mean/variance is used for normalization.\n\n Because the BatchNorm is done over the `C` dimension, computing statistics\n on `(N, D, H, W)` slices, it's common terminology to call this Volumetric BatchNorm\n or Spatio-temporal BatchNorm\n\n Args:\n num_features: num_features from an expected input of\n size batch_size x num_features x depth x height x width\n eps: a value added to the denominator for numerical stability.\n Default: 1e-5\n momentum: the value used for the running_mean and running_var\n computation. Default: 0.1\n affine: a boolean value that when set to ``True``, gives the layer learnable\n affine parameters. Default: ``True``\n\n Shape:\n - Input: :math:`(N, C, D, H, W)`\n - Output: :math:`(N, C, D, H, W)` (same shape as input)\n\n Examples:\n >>> # With Learnable Parameters\n >>> m = SynchronizedBatchNorm3d(100)\n >>> # Without Learnable Parameters\n >>> m = SynchronizedBatchNorm3d(100, affine=False)\n >>> input = torch.autograd.Variable(torch.randn(20, 100, 35, 45, 10))\n >>> output = m(input)\n \"\"\"\n\n def _check_input_dim(self, input):\n if input.dim() != 5:\n raise ValueError('expected 5D input (got {}D input)'\n .format(input.dim()))\n super(SynchronizedBatchNorm3d, self)._check_input_dim(input)\n"
},
{
"path": "sync_batchnorm/comm.py",
"content": "# -*- coding: utf-8 -*-\n# File : comm.py\n# Author : Jiayuan Mao\n# Email : maojiayuan@gmail.com\n# Date : 27/01/2018\n# \n# This file is part of Synchronized-BatchNorm-PyTorch.\n# https://github.com/vacancy/Synchronized-BatchNorm-PyTorch\n# Distributed under MIT License.\n\nimport queue\nimport collections\nimport threading\n\n__all__ = ['FutureResult', 'SlavePipe', 'SyncMaster']\n\n\nclass FutureResult(object):\n \"\"\"A thread-safe future implementation. Used only as one-to-one pipe.\"\"\"\n\n def __init__(self):\n self._result = None\n self._lock = threading.Lock()\n self._cond = threading.Condition(self._lock)\n\n def put(self, result):\n with self._lock:\n assert self._result is None, 'Previous result has\\'t been fetched.'\n self._result = result\n self._cond.notify()\n\n def get(self):\n with self._lock:\n if self._result is None:\n self._cond.wait()\n\n res = self._result\n self._result = None\n return res\n\n\n_MasterRegistry = collections.namedtuple('MasterRegistry', ['result'])\n_SlavePipeBase = collections.namedtuple('_SlavePipeBase', ['identifier', 'queue', 'result'])\n\n\nclass SlavePipe(_SlavePipeBase):\n \"\"\"Pipe for master-slave communication.\"\"\"\n\n def run_slave(self, msg):\n self.queue.put((self.identifier, msg))\n ret = self.result.get()\n self.queue.put(True)\n return ret\n\n\nclass SyncMaster(object):\n \"\"\"An abstract `SyncMaster` object.\n\n - During the replication, as the data parallel will trigger an callback of each module, all slave devices should\n call `register(id)` and obtain an `SlavePipe` to communicate with the master.\n - During the forward pass, master device invokes `run_master`, all messages from slave devices will be collected,\n and passed to a registered callback.\n - After receiving the messages, the master device should gather the information and determine to message passed\n back to each slave devices.\n \"\"\"\n\n def __init__(self, master_callback):\n \"\"\"\n\n Args:\n master_callback: a callback to be invoked after having collected messages from slave devices.\n \"\"\"\n self._master_callback = master_callback\n self._queue = queue.Queue()\n self._registry = collections.OrderedDict()\n self._activated = False\n\n def __getstate__(self):\n return {'master_callback': self._master_callback}\n\n def __setstate__(self, state):\n self.__init__(state['master_callback'])\n\n def register_slave(self, identifier):\n \"\"\"\n Register an slave device.\n\n Args:\n identifier: an identifier, usually is the device id.\n\n Returns: a `SlavePipe` object which can be used to communicate with the master device.\n\n \"\"\"\n if self._activated:\n assert self._queue.empty(), 'Queue is not clean before next initialization.'\n self._activated = False\n self._registry.clear()\n future = FutureResult()\n self._registry[identifier] = _MasterRegistry(future)\n return SlavePipe(identifier, self._queue, future)\n\n def run_master(self, master_msg):\n \"\"\"\n Main entry for the master device in each forward pass.\n The messages were first collected from each devices (including the master device), and then\n an callback will be invoked to compute the message to be sent back to each devices\n (including the master device).\n\n Args:\n master_msg: the message that the master want to send to itself. This will be placed as the first\n message when calling `master_callback`. For detailed usage, see `_SynchronizedBatchNorm` for an example.\n\n Returns: the message to be sent back to the master device.\n\n \"\"\"\n self._activated = True\n\n intermediates = [(0, master_msg)]\n for i in range(self.nr_slaves):\n intermediates.append(self._queue.get())\n\n results = self._master_callback(intermediates)\n assert results[0][0] == 0, 'The first result should belongs to the master.'\n\n for i, res in results:\n if i == 0:\n continue\n self._registry[i].result.put(res)\n\n for i in range(self.nr_slaves):\n assert self._queue.get() is True\n\n return results[0][1]\n\n @property\n def nr_slaves(self):\n return len(self._registry)\n"
},
{
"path": "sync_batchnorm/replicate.py",
"content": "# -*- coding: utf-8 -*-\n# File : replicate.py\n# Author : Jiayuan Mao\n# Email : maojiayuan@gmail.com\n# Date : 27/01/2018\n# \n# This file is part of Synchronized-BatchNorm-PyTorch.\n# https://github.com/vacancy/Synchronized-BatchNorm-PyTorch\n# Distributed under MIT License.\n\nimport functools\n\nfrom torch.nn.parallel.data_parallel import DataParallel\n\n__all__ = [\n 'CallbackContext',\n 'execute_replication_callbacks',\n 'DataParallelWithCallback',\n 'patch_replication_callback'\n]\n\n\nclass CallbackContext(object):\n pass\n\n\ndef execute_replication_callbacks(modules):\n \"\"\"\n Execute an replication callback `__data_parallel_replicate__` on each module created by original replication.\n\n The callback will be invoked with arguments `__data_parallel_replicate__(ctx, copy_id)`\n\n Note that, as all modules are isomorphism, we assign each sub-module with a context\n (shared among multiple copies of this module on different devices).\n Through this context, different copies can share some information.\n\n We guarantee that the callback on the master copy (the first copy) will be called ahead of calling the callback\n of any slave copies.\n \"\"\"\n master_copy = modules[0]\n nr_modules = len(list(master_copy.modules()))\n ctxs = [CallbackContext() for _ in range(nr_modules)]\n\n for i, module in enumerate(modules):\n for j, m in enumerate(module.modules()):\n if hasattr(m, '__data_parallel_replicate__'):\n m.__data_parallel_replicate__(ctxs[j], i)\n\n\nclass DataParallelWithCallback(DataParallel):\n \"\"\"\n Data Parallel with a replication callback.\n\n An replication callback `__data_parallel_replicate__` of each module will be invoked after being created by\n original `replicate` function.\n The callback will be invoked with arguments `__data_parallel_replicate__(ctx, copy_id)`\n\n Examples:\n > sync_bn = SynchronizedBatchNorm1d(10, eps=1e-5, affine=False)\n > sync_bn = DataParallelWithCallback(sync_bn, device_ids=[0, 1])\n # sync_bn.__data_parallel_replicate__ will be invoked.\n \"\"\"\n\n def replicate(self, module, device_ids):\n modules = super(DataParallelWithCallback, self).replicate(module, device_ids)\n execute_replication_callbacks(modules)\n return modules\n\n\ndef patch_replication_callback(data_parallel):\n \"\"\"\n Monkey-patch an existing `DataParallel` object. Add the replication callback.\n Useful when you have customized `DataParallel` implementation.\n\n Examples:\n > sync_bn = SynchronizedBatchNorm1d(10, eps=1e-5, affine=False)\n > sync_bn = DataParallel(sync_bn, device_ids=[0, 1])\n > patch_replication_callback(sync_bn)\n # this is equivalent to\n > sync_bn = SynchronizedBatchNorm1d(10, eps=1e-5, affine=False)\n > sync_bn = DataParallelWithCallback(sync_bn, device_ids=[0, 1])\n \"\"\"\n\n assert isinstance(data_parallel, DataParallel)\n\n old_replicate = data_parallel.replicate\n\n @functools.wraps(old_replicate)\n def new_replicate(module, device_ids):\n modules = old_replicate(module, device_ids)\n execute_replication_callbacks(modules)\n return modules\n\n data_parallel.replicate = new_replicate\n"
},
{
"path": "sync_batchnorm/unittest.py",
"content": "# -*- coding: utf-8 -*-\n# File : unittest.py\n# Author : Jiayuan Mao\n# Email : maojiayuan@gmail.com\n# Date : 27/01/2018\n# \n# This file is part of Synchronized-BatchNorm-PyTorch.\n# https://github.com/vacancy/Synchronized-BatchNorm-PyTorch\n# Distributed under MIT License.\n\nimport unittest\n\nimport numpy as np\nfrom torch.autograd import Variable\n\n\ndef as_numpy(v):\n if isinstance(v, Variable):\n v = v.data\n return v.cpu().numpy()\n\n\nclass TorchTestCase(unittest.TestCase):\n def assertTensorClose(self, a, b, atol=1e-3, rtol=1e-3):\n npa, npb = as_numpy(a), as_numpy(b)\n self.assertTrue(\n np.allclose(npa, npb, atol=atol),\n 'Tensor close check failed\\n{}\\n{}\\nadiff={}, rdiff={}'.format(a, b, np.abs(npa - npb).max(), np.abs((npa - npb) / np.fmax(npa, 1e-5)).max())\n )\n"
},
{
"path": "train.py",
"content": "from tqdm import trange\nimport torch\n\nfrom torch.utils.data import DataLoader\n\nfrom logger import Logger\nfrom modules.model import GeneratorFullModel, DiscriminatorFullModel\n\nfrom torch.optim.lr_scheduler import MultiStepLR\n\nfrom sync_batchnorm import DataParallelWithCallback\n\nfrom frames_dataset import DatasetRepeater\n\n\ndef train(config, generator, discriminator, kp_detector, checkpoint, log_dir, dataset, device_ids):\n train_params = config['train_params']\n\n optimizer_generator = torch.optim.Adam(generator.parameters(), lr=train_params['lr_generator'], betas=(0.5, 0.999))\n optimizer_discriminator = torch.optim.Adam(discriminator.parameters(), lr=train_params['lr_discriminator'], betas=(0.5, 0.999))\n optimizer_kp_detector = torch.optim.Adam(kp_detector.parameters(), lr=train_params['lr_kp_detector'], betas=(0.5, 0.999))\n\n if checkpoint is not None:\n start_epoch = Logger.load_cpk(checkpoint, generator, discriminator, kp_detector,\n optimizer_generator, optimizer_discriminator,\n None if train_params['lr_kp_detector'] == 0 else optimizer_kp_detector)\n else:\n start_epoch = 0\n\n scheduler_generator = MultiStepLR(optimizer_generator, train_params['epoch_milestones'], gamma=0.1,\n last_epoch=start_epoch - 1)\n scheduler_discriminator = MultiStepLR(optimizer_discriminator, train_params['epoch_milestones'], gamma=0.1,\n last_epoch=start_epoch - 1)\n scheduler_kp_detector = MultiStepLR(optimizer_kp_detector, train_params['epoch_milestones'], gamma=0.1,\n last_epoch=-1 + start_epoch * (train_params['lr_kp_detector'] != 0))\n\n if 'num_repeats' in train_params or train_params['num_repeats'] != 1:\n dataset = DatasetRepeater(dataset, train_params['num_repeats'])\n dataloader = DataLoader(dataset, batch_size=train_params['batch_size'], shuffle=True, num_workers=6, drop_last=True)\n\n generator_full = GeneratorFullModel(kp_detector, generator, discriminator, train_params)\n discriminator_full = DiscriminatorFullModel(kp_detector, generator, discriminator, train_params)\n\n if torch.cuda.is_available():\n generator_full = DataParallelWithCallback(generator_full, device_ids=device_ids)\n discriminator_full = DataParallelWithCallback(discriminator_full, device_ids=device_ids)\n\n with Logger(log_dir=log_dir, visualizer_params=config['visualizer_params'], checkpoint_freq=train_params['checkpoint_freq']) as logger:\n for epoch in trange(start_epoch, train_params['num_epochs']):\n for x in dataloader:\n losses_generator, generated = generator_full(x)\n\n loss_values = [val.mean() for val in losses_generator.values()]\n loss = sum(loss_values)\n\n loss.backward()\n optimizer_generator.step()\n optimizer_generator.zero_grad()\n optimizer_kp_detector.step()\n optimizer_kp_detector.zero_grad()\n\n if train_params['loss_weights']['generator_gan'] != 0:\n optimizer_discriminator.zero_grad()\n losses_discriminator = discriminator_full(x, generated)\n loss_values = [val.mean() for val in losses_discriminator.values()]\n loss = sum(loss_values)\n\n loss.backward()\n optimizer_discriminator.step()\n optimizer_discriminator.zero_grad()\n else:\n losses_discriminator = {}\n\n losses_generator.update(losses_discriminator)\n losses = {key: value.mean().detach().data.cpu().numpy() for key, value in losses_generator.items()}\n logger.log_iter(losses=losses)\n\n scheduler_generator.step()\n scheduler_discriminator.step()\n scheduler_kp_detector.step()\n \n logger.log_epoch(epoch, {'generator': generator,\n 'discriminator': discriminator,\n 'kp_detector': kp_detector,\n 'optimizer_generator': optimizer_generator,\n 'optimizer_discriminator': optimizer_discriminator,\n 'optimizer_kp_detector': optimizer_kp_detector}, inp=x, out=generated)\n"
}
]