SYMBOL INDEX (88 symbols across 17 files)

FILE: benchmark.py
  function get_model (line 33) | def get_model(name):
  function main (line 52) | def main():

FILE: data_loader.py
  class HairGenerator (line 11) | class HairGenerator(Sequence):
    method __init__ (line 13) | def __init__(self,
    method __getitem__ (line 36) | def __getitem__(self, idx):
    method __len__ (line 61) | def __len__(self):
    method _padding (line 65) | def _padding(self, image):
    method on_epoch_end (line 79) | def on_epoch_end(self):
    method _get_result_map (line 86) | def _get_result_map(self, mask):

FILE: experiments/cal_histogram.py
  class RGBHistogram (line 32) | class RGBHistogram(Histogram):
    method __init__ (line 35) | def __init__(self, bins):
    method describe (line 38) | def describe(self, image, mask):
  class HSVHistogram (line 54) | class HSVHistogram(Histogram):
    method __init__ (line 57) | def __init__(self, bins):
    method describe (line 60) | def describe(self, image, mask):
  class YCrCbHistogram (line 76) | class YCrCbHistogram(Histogram):
    method __init__ (line 79) | def __init__(self, bins):
    method describe (line 82) | def describe(self, image, mask):

FILE: experiments/cal_moments.py
  function color_moments (line 25) | def color_moments(image, mask, color_space):

FILE: experiments/cal_pca.py
  class RGBHistogram (line 29) | class RGBHistogram(Histogram):
    method __init__ (line 32) | def __init__(self, bins):
    method describe (line 35) | def describe(self, image, mask):

FILE: experiments/utils.py
  function plot_confusion_matrix (line 6) | def plot_confusion_matrix(y_true, y_pred, classes,
  class Histogram (line 56) | class Histogram:
    method __init__ (line 59) | def __init__(self, bins):
    method describe (line 62) | def describe(self, image, mask):

FILE: metric.py
  function mean_iou (line 10) | def mean_iou(y_true, y_pred, cls_num=CLS_NUM):
  function mean_accuracy (line 28) | def mean_accuracy(y_true, y_pred, cls_num=CLS_NUM):
  function frequency_weighted_iou (line 40) | def frequency_weighted_iou(y_true, y_pred, cls_num=CLS_NUM):
  function pixel_accuracy (line 56) | def pixel_accuracy(y_true, y_pred):

FILE: model/dfanet.py
  function ConvBlock (line 15) | def ConvBlock(inputs, n_filters, kernel_size=3, strides=1):
  function separable_res_block_deep (line 30) | def separable_res_block_deep(inputs, nb_filters, filter_size=3, strides=...
  function encoder (line 70) | def encoder(inputs, nb_filters, stage):
  function AttentionRefinementModule (line 83) | def AttentionRefinementModule(inputs):
  function xception_backbone (line 105) | def xception_backbone(inputs, size_factor=2):
  function DFANet (line 119) | def DFANet(input_shape, cls_num=3, size_factor=2):

FILE: model/enet.py
  class Conv2DTransposeCustom (line 14) | class Conv2DTransposeCustom(object):
    method __init__ (line 17) | def __init__(self, filters, kernel_size, strides=(1, 1), padding='same'):
    method __call__ (line 23) | def __call__(self, layer):
  function initial_block (line 31) | def initial_block(inp, nb_filter=13, nb_row=3, nb_col=3, strides=(2, 2)):
  function bottleneck (line 38) | def bottleneck(inp, output, internal_scale=4, asymmetric=0, dilated=0, d...
  function en_build (line 89) | def en_build(inp, dropout_rate=0.01):
  function de_bottleneck (line 113) | def de_bottleneck(encoder, output, upsample=False, reverse_module=False):
  function de_build (line 145) | def de_build(encoder, nc):
  function ENet (line 156) | def ENet(input_shape, cls_num=3):

FILE: model/fast_scnn.py
  function resize_image (line 5) | def resize_image(image):
  class Fast_SCNN (line 9) | class Fast_SCNN:
    method __init__ (line 11) | def __init__(self, num_classes=3, input_shape=(256, 256, 3)):
    method conv_block (line 17) | def conv_block(self, inputs, conv_type, kernel, kernel_size, strides, ...
    method learning_to_downsample (line 30) | def learning_to_downsample(self):
    method global_feature_extractor (line 38) | def global_feature_extractor(self):
    method _res_bottleneck (line 45) | def _res_bottleneck(self, inputs, filters, kernel, t, s, r=False):
    method bottleneck_block (line 60) | def bottleneck_block(self, inputs, filters, kernel, t, strides, n):
    method pyramid_pooling_block (line 68) | def pyramid_pooling_block(self, input_tensor, bin_sizes):
    method feature_fusion (line 84) | def feature_fusion(self):
    method classifier (line 97) | def classifier(self):
    method activation (line 113) | def activation(self, activation='softmax'):
    method model (line 118) | def model(self, activation='softmax'):

FILE: model/flops.py
  function get_flops (line 15) | def get_flops(model, table=False):

FILE: model/hlnet.py
  function _conv_block (line 12) | def _conv_block(inputs, filters, kernel, strides=1, padding='same', use_...
  function _bottleneck (line 39) | def _bottleneck(inputs, filters, kernel, t, s, r=False):
  function _inverted_residual_block (line 75) | def _inverted_residual_block(inputs, filters, kernel, t, strides, n):
  function _depthwise_separable_block (line 100) | def _depthwise_separable_block(inputs, kernel, strides, padding='same', ...
  function HLNet (line 110) | def HLNet(input_shape, cls_num=3):

FILE: model/lednet.py
  class LEDNet (line 14) | class LEDNet:
    method __init__ (line 15) | def __init__(self, groups, classes, input_shape):
    method ss_bt (line 20) | def ss_bt(self, x, dilation, strides=(1, 1), padding='same'):
    method channel_shuffle (line 53) | def channel_shuffle(self, x):
    method channel_split (line 60) | def channel_split(self, x):
    method down_sample (line 70) | def down_sample(self, x, filters):
    method apn_module (line 79) | def apn_module(self, x):
    method encoder (line 115) | def encoder(self, x):
    method decoder (line 131) | def decoder(self, x):
    method model (line 139) | def model(self):

FILE: model/mobilenet.py
  function conv_block (line 14) | def conv_block(inputs, filters, alpha, kernel=(3, 3), strides=(1, 1)):
  function depthwise_conv_block (line 22) | def depthwise_conv_block(inputs, pointwise_conv_filters, alpha, depth_mu...
  function MobileNet (line 35) | def MobileNet(input_shape, cls_num, alpha=0.5):

FILE: pipline_test.py
  function color_moments (line 29) | def color_moments(image, mask, color_space):
  function _result_map_toimg (line 81) | def _result_map_toimg(result_map):
  function imcrop (line 97) | def imcrop(img, x1, y1, x2, y2):
  function pad_img_to_fit_bbox (line 103) | def pad_img_to_fit_bbox(img, x1, x2, y1, y2):

FILE: test.py
  function vis_parsing_maps (line 26) | def vis_parsing_maps(im, parsing_anno, data_name):

FILE: train.py
  function get_model (line 49) | def get_model(name):
  class PolyDecay (line 68) | class PolyDecay:
    method __init__ (line 71) | def __init__(self, initial_lr, power, n_epochs):
    method scheduler (line 76) | def scheduler(self, epoch):
  function set_regularization (line 80) | def set_regularization(model,
  function main (line 96) | def main():