Python keras.layers.ZeroPadding2D() Examples

def _conv_block(inp, convs, do_skip=True):
    x = inp
    count = 0
    
    for conv in convs:
        if count == (len(convs) - 2) and do_skip:
            skip_connection = x
        count += 1
        
        if conv['stride'] > 1: x = ZeroPadding2D(((1,0),(1,0)))(x) # unlike tensorflow darknet prefer left and top paddings
        x = Conv2D(conv['filter'], 
                   conv['kernel'], 
                   strides=conv['stride'], 
                   padding='valid' if conv['stride'] > 1 else 'same', # unlike tensorflow darknet prefer left and top paddings
                   name='conv_' + str(conv['layer_idx']), 
                   use_bias=False if conv['bnorm'] else True)(x)
        if conv['bnorm']: x = BatchNormalization(epsilon=0.001, name='bnorm_' + str(conv['layer_idx']))(x)
        if conv['leaky']: x = LeakyReLU(alpha=0.1, name='leaky_' + str(conv['layer_idx']))(x)

    return add([skip_connection, x]) if do_skip else x 

def _conv_block(inp, convs, skip=True):
  x = inp
  count = 0
  len_convs = len(convs)
  for conv in convs:
    if count == (len_convs - 2) and skip:
      skip_connection = x
    count += 1
    if conv['stride'] > 1: x = ZeroPadding2D(((1,0),(1,0)))(x) # peculiar padding as darknet prefer left and top
    x = Conv2D(conv['filter'],
           conv['kernel'],
           strides=conv['stride'],
           padding='valid' if conv['stride'] > 1 else 'same', # peculiar padding as darknet prefer left and top
           name='conv_' + str(conv['layer_idx']),
           use_bias=False if conv['bnorm'] else True)(x)
    if conv['bnorm']: x = BatchNormalization(epsilon=0.001, name='bnorm_' + str(conv['layer_idx']))(x)
    if conv['leaky']: x = LeakyReLU(alpha=0.1, name='leaky_' + str(conv['layer_idx']))(x)
  return add([skip_connection, x]) if skip else x


#SPP block uses three pooling layers of sizes [5, 9, 13] with strides one and all outputs together with the input are concatenated to be fed
  #to the FC block 

def residual(_x, out_dim, name, stride=1):
  shortcut = _x
  num_channels = K.int_shape(shortcut)[-1]
  _x = ZeroPadding2D(padding=1, name=name + '.pad1')(_x)
  _x = Conv2D(out_dim, 3, strides=stride, use_bias=False, name=name + '.conv1')(_x)
  _x = BatchNormalization(epsilon=1e-5, name=name + '.bn1')(_x)
  _x = Activation('relu', name=name + '.relu1')(_x)

  _x = Conv2D(out_dim, 3, padding='same', use_bias=False, name=name + '.conv2')(_x)
  _x = BatchNormalization(epsilon=1e-5, name=name + '.bn2')(_x)

  if num_channels != out_dim or stride != 1:
    shortcut = Conv2D(out_dim, 1, strides=stride, use_bias=False, name=name + '.shortcut.0')(
        shortcut)
    shortcut = BatchNormalization(epsilon=1e-5, name=name + '.shortcut.1')(shortcut)

  _x = Add(name=name + '.add')([_x, shortcut])
  _x = Activation('relu', name=name + '.relu')(_x)
  return _x 

def inception_block_2b(X):
    #inception4e
    X_3x3 = fr_utils.conv2d_bn(X,
                           layer='inception_4e_3x3',
                           cv1_out=160,
                           cv1_filter=(1, 1),
                           cv2_out=256,
                           cv2_filter=(3, 3),
                           cv2_strides=(2, 2),
                           padding=(1, 1))
    X_5x5 = fr_utils.conv2d_bn(X,
                           layer='inception_4e_5x5',
                           cv1_out=64,
                           cv1_filter=(1, 1),
                           cv2_out=128,
                           cv2_filter=(5, 5),
                           cv2_strides=(2, 2),
                           padding=(2, 2))
    
    X_pool = MaxPooling2D(pool_size=3, strides=2, data_format='channels_first')(X)
    X_pool = ZeroPadding2D(padding=((0, 1), (0, 1)), data_format='channels_first')(X_pool)

    inception = concatenate([X_3x3, X_5x5, X_pool], axis=1)

    return inception 

def inception_block_1c(X):
    X_3x3 = fr_utils.conv2d_bn(X,
                           layer='inception_3c_3x3',
                           cv1_out=128,
                           cv1_filter=(1, 1),
                           cv2_out=256,
                           cv2_filter=(3, 3),
                           cv2_strides=(2, 2),
                           padding=(1, 1))

    X_5x5 = fr_utils.conv2d_bn(X,
                           layer='inception_3c_5x5',
                           cv1_out=32,
                           cv1_filter=(1, 1),
                           cv2_out=64,
                           cv2_filter=(5, 5),
                           cv2_strides=(2, 2),
                           padding=(2, 2))

    X_pool = MaxPooling2D(pool_size=3, strides=2, data_format='channels_first')(X)
    X_pool = ZeroPadding2D(padding=((0, 1), (0, 1)), data_format='channels_first')(X_pool)

    inception = concatenate([X_3x3, X_5x5, X_pool], axis=1)

    return inception 

def conv2d_bn(x,
              layer=None,
              cv1_out=None,
              cv1_filter=(1, 1),
              cv1_strides=(1, 1),
              cv2_out=None,
              cv2_filter=(3, 3),
              cv2_strides=(1, 1),
              padding=None):
    num = '' if cv2_out == None else '1'
    tensor = Conv2D(cv1_out, cv1_filter, strides=cv1_strides, data_format='channels_first', name=layer+'_conv'+num)(x)
    tensor = BatchNormalization(axis=1, epsilon=0.00001, name=layer+'_bn'+num)(tensor)
    tensor = Activation('relu')(tensor)
    if padding == None:
        return tensor
    tensor = ZeroPadding2D(padding=padding, data_format='channels_first')(tensor)
    if cv2_out == None:
        return tensor
    tensor = Conv2D(cv2_out, cv2_filter, strides=cv2_strides, data_format='channels_first', name=layer+'_conv'+'2')(tensor)
    tensor = BatchNormalization(axis=1, epsilon=0.00001, name=layer+'_bn'+'2')(tensor)
    tensor = Activation('relu')(tensor)
    return tensor 

def _conv2d_same(x, filters, prefix, stride=1, kernel_size=3, rate=1):
    # 计算padding的数量，hw是否需要收缩
    if stride == 1:
        return Conv2D(filters,
                      (kernel_size, kernel_size),
                      strides=(stride, stride),
                      padding='same', use_bias=False,
                      dilation_rate=(rate, rate),
                      name=prefix)(x)
    else:
        kernel_size_effective = kernel_size + (kernel_size - 1) * (rate - 1)
        pad_total = kernel_size_effective - 1
        pad_beg = pad_total // 2
        pad_end = pad_total - pad_beg
        x = ZeroPadding2D((pad_beg, pad_end))(x)
        return Conv2D(filters,
                      (kernel_size, kernel_size),
                      strides=(stride, stride),
                      padding='valid', use_bias=False,
                      dilation_rate=(rate, rate),
                      name=prefix)(x) 

def resnet_graph(input_image, architecture, stage5=False, train_bn=True):
    """Build a ResNet graph.
        architecture: Can be resnet50 or resnet101
        stage5: Boolean. If False, stage5 of the network is not created
        train_bn: Boolean. Train or freeze Batch Norm layers
    """
    assert architecture in ["resnet50", "resnet101"]
    # Stage 1
    x = KL.ZeroPadding2D((3, 3))(input_image)
    x = KL.Conv2D(64, (7, 7), strides=(2, 2), name='conv1', use_bias=True)(x)
    x = BatchNorm(name='bn_conv1')(x, training=train_bn)
    x = KL.Activation('relu')(x)
    C1 = x = KL.MaxPooling2D((3, 3), strides=(2, 2), padding="same")(x)
    # Stage 2
    x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1), train_bn=train_bn)
    x = identity_block(x, 3, [64, 64, 256], stage=2, block='b', train_bn=train_bn)
    C2 = x = identity_block(x, 3, [64, 64, 256], stage=2, block='c', train_bn=train_bn)
    # Stage 3
    x = conv_block(x, 3, [128, 128, 512], stage=3, block='a', train_bn=train_bn)
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='b', train_bn=train_bn)
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='c', train_bn=train_bn)
    C3 = x = identity_block(x, 3, [128, 128, 512], stage=3, block='d', train_bn=train_bn)
    # Stage 4
    x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a', train_bn=train_bn)
    block_count = {"resnet50": 5, "resnet101": 22}[architecture]
    for i in range(block_count):
        x = identity_block(x, 3, [256, 256, 1024], stage=4, block=chr(98 + i), train_bn=train_bn)
    C4 = x
    # Stage 5
    if stage5:
        x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a', train_bn=train_bn)
        x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b', train_bn=train_bn)
        C5 = x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c', train_bn=train_bn)
    else:
        C5 = None
    return [C1, C2, C3, C4, C5]


############################################################
#  Proposal Layer
############################################################ 

def convolution(_x, k, out_dim, name, stride=1):
  padding = (k - 1) // 2
  _x = ZeroPadding2D(padding=padding, name=name + '.pad')(_x)
  _x = Conv2D(out_dim, k, strides=stride, use_bias=False, name=name + '.conv')(_x)
  _x = BatchNormalization(epsilon=1e-5, name=name + '.bn')(_x)
  _x = Activation('relu', name=name + '.relu')(_x)
  return _x 

def resblock_body(x, num_filters, num_blocks):
    '''A series of resblocks starting with a downsampling Convolution2D'''
    # Darknet uses left and top padding instead of 'same' mode
    x = ZeroPadding2D(((1,0),(1,0)))(x)
    x = DarknetConv2D_BN_Leaky(num_filters, (3,3), strides=(2,2))(x)
    for i in range(num_blocks):
        y = compose(
                DarknetConv2D_BN_Leaky(num_filters//2, (1,1)),
                DarknetConv2D_BN_Leaky(num_filters, (3,3)))(x)
        x = Add()([x,y])
    return x 

def _conv2d_same(x, filters, prefix, stride=1, kernel_size=3, rate=1):
    """Implements right 'same' padding for even kernel sizes
        Without this there is a 1 pixel drift when stride = 2
        Args:
            x: input tensor
            filters: num of filters in pointwise convolution
            prefix: prefix before name
            stride: stride at depthwise conv
            kernel_size: kernel size for depthwise convolution
            rate: atrous rate for depthwise convolution
    """
    if stride == 1:
        return Conv2D(filters,
                      (kernel_size, kernel_size),
                      strides=(stride, stride),
                      padding='same', use_bias=False,
                      dilation_rate=(rate, rate),
                      name=prefix)(x)
    else:
        kernel_size_effective = kernel_size + (kernel_size - 1) * (rate - 1)
        pad_total = kernel_size_effective - 1
        pad_beg = pad_total // 2
        pad_end = pad_total - pad_beg
        x = ZeroPadding2D((pad_beg, pad_end))(x)
        return Conv2D(filters,
                      (kernel_size, kernel_size),
                      strides=(stride, stride),
                      padding='valid', use_bias=False,
                      dilation_rate=(rate, rate),
                      name=prefix)(x) 

def SepConv_BN(x, filters, prefix, stride=1, kernel_size=3, rate=1, depth_activation=False, epsilon=1e-3):
    """ SepConv with BN between depthwise & pointwise. Optionally add activation after BN
        Implements right "same" padding for even kernel sizes
        Args:
            x: input tensor
            filters: num of filters in pointwise convolution
            prefix: prefix before name
            stride: stride at depthwise conv
            kernel_size: kernel size for depthwise convolution
            rate: atrous rate for depthwise convolution
            depth_activation: flag to use activation between depthwise & poinwise convs
            epsilon: epsilon to use in BN layer
    """

    if stride == 1:
        depth_padding = 'same'
    else:
        kernel_size_effective = kernel_size + (kernel_size - 1) * (rate - 1)
        pad_total = kernel_size_effective - 1
        pad_beg = pad_total // 2
        pad_end = pad_total - pad_beg
        x = ZeroPadding2D((pad_beg, pad_end))(x)
        depth_padding = 'valid'

    if not depth_activation:
        x = Activation('relu')(x)
    x = DepthwiseConv2D((kernel_size, kernel_size), strides=(stride, stride), dilation_rate=(rate, rate),
                        padding=depth_padding, use_bias=False, name=prefix + '_depthwise')(x)
    x = BatchNormalization(name=prefix + '_depthwise_BN', epsilon=epsilon)(x)
    if depth_activation:
        x = Activation('relu')(x)
    x = Conv2D(filters, (1, 1), padding='same',
               use_bias=False, name=prefix + '_pointwise')(x)
    x = BatchNormalization(name=prefix + '_pointwise_BN', epsilon=epsilon)(x)
    if depth_activation:
        x = Activation('relu')(x)

    return x 

def inception_block_1b(X):
    X_3x3 = Conv2D(96, (1, 1), data_format='channels_first', name='inception_3b_3x3_conv1')(X)
    X_3x3 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3b_3x3_bn1')(X_3x3)
    X_3x3 = Activation('relu')(X_3x3)
    X_3x3 = ZeroPadding2D(padding=(1, 1), data_format='channels_first')(X_3x3)
    X_3x3 = Conv2D(128, (3, 3), data_format='channels_first', name='inception_3b_3x3_conv2')(X_3x3)
    X_3x3 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3b_3x3_bn2')(X_3x3)
    X_3x3 = Activation('relu')(X_3x3)

    X_5x5 = Conv2D(32, (1, 1), data_format='channels_first', name='inception_3b_5x5_conv1')(X)
    X_5x5 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3b_5x5_bn1')(X_5x5)
    X_5x5 = Activation('relu')(X_5x5)
    X_5x5 = ZeroPadding2D(padding=(2, 2), data_format='channels_first')(X_5x5)
    X_5x5 = Conv2D(64, (5, 5), data_format='channels_first', name='inception_3b_5x5_conv2')(X_5x5)
    X_5x5 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3b_5x5_bn2')(X_5x5)
    X_5x5 = Activation('relu')(X_5x5)

    X_pool = AveragePooling2D(pool_size=(3, 3), strides=(3, 3), data_format='channels_first')(X)
    X_pool = Conv2D(64, (1, 1), data_format='channels_first', name='inception_3b_pool_conv')(X_pool)
    X_pool = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3b_pool_bn')(X_pool)
    X_pool = Activation('relu')(X_pool)
    X_pool = ZeroPadding2D(padding=(4, 4), data_format='channels_first')(X_pool)

    X_1x1 = Conv2D(64, (1, 1), data_format='channels_first', name='inception_3b_1x1_conv')(X)
    X_1x1 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3b_1x1_bn')(X_1x1)
    X_1x1 = Activation('relu')(X_1x1)

    inception = concatenate([X_3x3, X_5x5, X_pool, X_1x1], axis=1)

    return inception 

def inception_block_1a(X):
    """
    Implementation of an inception block
    """
    
    X_3x3 = Conv2D(96, (1, 1), data_format='channels_first', name ='inception_3a_3x3_conv1')(X)
    X_3x3 = BatchNormalization(axis=1, epsilon=0.00001, name = 'inception_3a_3x3_bn1')(X_3x3)
    X_3x3 = Activation('relu')(X_3x3)
    X_3x3 = ZeroPadding2D(padding=(1, 1), data_format='channels_first')(X_3x3)
    X_3x3 = Conv2D(128, (3, 3), data_format='channels_first', name='inception_3a_3x3_conv2')(X_3x3)
    X_3x3 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_3x3_bn2')(X_3x3)
    X_3x3 = Activation('relu')(X_3x3)
    
    X_5x5 = Conv2D(16, (1, 1), data_format='channels_first', name='inception_3a_5x5_conv1')(X)
    X_5x5 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_5x5_bn1')(X_5x5)
    X_5x5 = Activation('relu')(X_5x5)
    X_5x5 = ZeroPadding2D(padding=(2, 2), data_format='channels_first')(X_5x5)
    X_5x5 = Conv2D(32, (5, 5), data_format='channels_first', name='inception_3a_5x5_conv2')(X_5x5)
    X_5x5 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_5x5_bn2')(X_5x5)
    X_5x5 = Activation('relu')(X_5x5)

    X_pool = MaxPooling2D(pool_size=3, strides=2, data_format='channels_first')(X)
    X_pool = Conv2D(32, (1, 1), data_format='channels_first', name='inception_3a_pool_conv')(X_pool)
    X_pool = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_pool_bn')(X_pool)
    X_pool = Activation('relu')(X_pool)
    X_pool = ZeroPadding2D(padding=((3, 4), (3, 4)), data_format='channels_first')(X_pool)

    X_1x1 = Conv2D(64, (1, 1), data_format='channels_first', name='inception_3a_1x1_conv')(X)
    X_1x1 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_1x1_bn')(X_1x1)
    X_1x1 = Activation('relu')(X_1x1)
        
    # CONCAT
    inception = concatenate([X_3x3, X_5x5, X_pool, X_1x1], axis=1)

    return inception 

def resnet_graph(input_image, architecture, stage5=False, train_bn=True):
    """Build a ResNet graph.
        architecture: Can be resnet50 or resnet101
        stage5: Boolean. If False, stage5 of the network is not created
        train_bn: Boolean. Train or freeze Batch Norm layres
    """
    assert architecture in ["resnet50", "resnet101"]
    # Stage 1
    x = KL.ZeroPadding2D((3, 3))(input_image)
    x = KL.Conv2D(64, (7, 7), strides=(2, 2), name='conv1', use_bias=True)(x)
    x = BatchNorm(name='bn_conv1')(x, training=train_bn)
    x = KL.Activation('relu')(x)
    C1 = x = KL.MaxPooling2D((3, 3), strides=(2, 2), padding="same")(x)
    # Stage 2
    x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1), train_bn=train_bn)
    x = identity_block(x, 3, [64, 64, 256], stage=2, block='b', train_bn=train_bn)
    C2 = x = identity_block(x, 3, [64, 64, 256], stage=2, block='c', train_bn=train_bn)
    # Stage 3
    x = conv_block(x, 3, [128, 128, 512], stage=3, block='a', train_bn=train_bn)
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='b', train_bn=train_bn)
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='c', train_bn=train_bn)
    C3 = x = identity_block(x, 3, [128, 128, 512], stage=3, block='d', train_bn=train_bn)
    # Stage 4
    x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a', train_bn=train_bn)
    block_count = {"resnet50": 5, "resnet101": 22}[architecture]
    for i in range(block_count):
        x = identity_block(x, 3, [256, 256, 1024], stage=4, block=chr(98 + i), train_bn=train_bn)
    C4 = x
    # Stage 5
    if stage5:
        x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a', train_bn=train_bn)
        x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b', train_bn=train_bn)
        C5 = x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c', train_bn=train_bn)
    else:
        C5 = None
    return [C1, C2, C3, C4, C5]


############################################################
#  Proposal Layer
############################################################ 

def residual_block(input, channels, num_blocks):
    network = ZeroPadding2D(((1,0), (1,0)))(input)
    network = NetworkConv2D_BN_Leaky(input=network,channels=channels, kernel_size=(3,3), strides=(2,2), padding="valid")

    for blocks in range(num_blocks):
        network_1 = NetworkConv2D_BN_Leaky(input=network, channels= channels // 2, kernel_size=(1,1))
        network_1 = NetworkConv2D_BN_Leaky(input=network_1,channels= channels, kernel_size=(3,3))

        network = Add()([network, network_1])
    return network 

def resnet_graph(input_image, architecture, stage5=False):
    assert architecture in ["resnet50", "resnet101"]
    # Stage 1
    x = KL.ZeroPadding2D((3, 3))(input_image)
    x = KL.Conv2D(64, (7, 7), strides=(2, 2), name='conv1', use_bias=True)(x)
    x = BatchNorm(axis=3, name='bn_conv1')(x)
    x = KL.Activation('relu')(x)
    C1 = x = KL.MaxPooling2D((3, 3), strides=(2, 2), padding="same")(x)
    # Stage 2
    x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
    x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
    C2 = x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')
    # Stage 3
    x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
    C3 = x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')
    # Stage 4
    x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
    block_count = {"resnet50": 5, "resnet101": 22}[architecture]
    for i in range(block_count):
        x = identity_block(x, 3, [256, 256, 1024], stage=4, block=chr(98 + i))
    C4 = x
    # Stage 5
    if stage5:
        x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
        x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
        C5 = x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')
    else:
        C5 = None
    return [C1, C2, C3, C4, C5]


############################################################
#  Proposal Layer
############################################################ 

def test_zeropad_simple(self):

        input_shape = (48, 48, 3)
        model = Sequential()
        model.add(ZeroPadding2D((1, 1), input_shape=input_shape))

        # Set some random weights
        model.set_weights([np.random.rand(*w.shape) for w in model.get_weights()])

        # Get the coreml model
        self._test_model(model) 

def _conv2d_same(x, filters, prefix, stride=1, kernel_size=3, rate=1):
    """Implements right 'same' padding for even kernel sizes
        Without this there is a 1 pixel drift when stride = 2
        Args:
            x: input tensor
            filters: num of filters in pointwise convolution
            prefix: prefix before name
            stride: stride at depthwise conv
            kernel_size: kernel size for depthwise convolution
            rate: atrous rate for depthwise convolution
    """
    if stride == 1:
        return Conv2D(filters,
                      (kernel_size, kernel_size),
                      strides=(stride, stride),
                      padding='same', use_bias=False,
                      dilation_rate=(rate, rate),
                      name=prefix)(x)
    else:
        kernel_size_effective = kernel_size + (kernel_size - 1) * (rate - 1)
        pad_total = kernel_size_effective - 1
        pad_beg = pad_total // 2
        pad_end = pad_total - pad_beg
        x = ZeroPadding2D((pad_beg, pad_end))(x)
        return Conv2D(filters,
                      (kernel_size, kernel_size),
                      strides=(stride, stride),
                      padding='valid', use_bias=False,
                      dilation_rate=(rate, rate),
                      name=prefix)(x) 

def resnet_graph(input_image, architecture, stage5=False, train_bn=True):
    """Build a ResNet graph.
        architecture: Can be resnet50 or resnet101
        stage5: Boolean. If False, stage5 of the network is not created
        train_bn: Boolean. Train or freeze Batch Norm layres
    """
    assert architecture in ["resnet50", "resnet101"]
    # Stage 1
    x = KL.ZeroPadding2D((3, 3))(input_image)
    x = KL.Conv2D(64, (7, 7), strides=(2, 2), name='conv1', use_bias=True)(x)
    x = BatchNorm(name='bn_conv1')(x, training=train_bn)
    x = KL.Activation('relu')(x)
    C1 = x = KL.MaxPooling2D((3, 3), strides=(2, 2), padding="same")(x)
    # Stage 2
    x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1), train_bn=train_bn)
    x = identity_block(x, 3, [64, 64, 256], stage=2, block='b', train_bn=train_bn)
    C2 = x = identity_block(x, 3, [64, 64, 256], stage=2, block='c', train_bn=train_bn)
    # Stage 3
    x = conv_block(x, 3, [128, 128, 512], stage=3, block='a', train_bn=train_bn)
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='b', train_bn=train_bn)
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='c', train_bn=train_bn)
    C3 = x = identity_block(x, 3, [128, 128, 512], stage=3, block='d', train_bn=train_bn)
    # Stage 4
    x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a', train_bn=train_bn)
    block_count = {"resnet50": 5, "resnet101": 22}[architecture]
    for i in range(block_count):
        x = identity_block(x, 3, [256, 256, 1024], stage=4, block=chr(98 + i), train_bn=train_bn)
    C4 = x
    # Stage 5
    if stage5:
        x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a', train_bn=train_bn)
        x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b', train_bn=train_bn)
        C5 = x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c', train_bn=train_bn)
    else:
        C5 = None
    return [C1, C2, C3, C4, C5]


############################################################
#  Proposal Layer
############################################################ 

def resblock_body(x, num_filters, num_blocks):
    '''A series of resblocks starting with a downsampling Convolution2D'''
    # Darknet uses left and top padding instead of 'same' mode
    x = ZeroPadding2D(((1,0),(1,0)))(x)
    x = DarknetConv2D_BN_Leaky(num_filters, (3,3), strides=(2,2))(x)
    for i in range(num_blocks):
        y = compose(
                DarknetConv2D_BN_Leaky(num_filters//2, (1,1)),
                DarknetConv2D_BN_Leaky(num_filters, (3,3)))(x)
        x = Add()([x,y])
    return x 

def resblock_body(x, num_filters, num_blocks):
    '''A series of resblocks starting with a downsampling Convolution2D'''
    # Darknet uses left and top padding instead of 'same' mode
    x = ZeroPadding2D(((1,0),(1,0)))(x)
    x = DarknetConv2D_BN_Leaky(num_filters, (3,3), strides=(2,2))(x)
    for i in range(num_blocks):
        y = compose(
                DarknetConv2D_BN_Leaky(num_filters//2, (1,1)),
                DarknetConv2D_BN_Leaky(num_filters, (3,3)))(x)
        x = Add()([x,y])
    return x 

def build_discriminator(self):
        """Discriminator network with PatchGAN."""
        inp_img = Input(shape = (self.image_size, self.image_size, 3))
        x = ZeroPadding2D(padding = 1)(inp_img)
        x = Conv2D(filters = self.d_conv_dim, kernel_size = 4, strides = 2, padding = 'valid', use_bias = False)(x)
        x = LeakyReLU(0.01)(x)
    
        curr_dim = self.d_conv_dim
        for i in range(1, self.d_repeat_num):
            x = ZeroPadding2D(padding = 1)(x)
            x = Conv2D(filters = curr_dim*2, kernel_size = 4, strides = 2, padding = 'valid')(x)
            x = LeakyReLU(0.01)(x)
            curr_dim = curr_dim * 2
    
        kernel_size = int(self.image_size / np.power(2, self.d_repeat_num))
    
        out_src = ZeroPadding2D(padding = 1)(x)
        out_src = Conv2D(filters = 1, kernel_size = 3, strides = 1, padding = 'valid', use_bias = False)(out_src)
    
        out_cls = Conv2D(filters = self.c_dim, kernel_size = kernel_size, strides = 1, padding = 'valid', use_bias = False)(x)
        out_cls = Reshape((self.c_dim, ))(out_cls)
    
        return Model(inp_img, [out_src, out_cls]) 

def ResidualBlock(self, inp, dim_out):
        """Residual Block with instance normalization."""
        x = ZeroPadding2D(padding = 1)(inp)
        x = Conv2D(filters = dim_out, kernel_size=3, strides=1, padding='valid', use_bias = False)(x)
        x = InstanceNormalization(axis = -1)(x)
        x = ReLU()(x)
        x = ZeroPadding2D(padding = 1)(x)
        x = Conv2D(filters = dim_out, kernel_size=3, strides=1, padding='valid', use_bias = False)(x)
        x = InstanceNormalization(axis = -1)(x)
        return Add()([inp, x]) 

def build_discriminator(self):

        model = Sequential()

        model.add(Conv2D(32, kernel_size=3, strides=2, input_shape=self.img_shape, padding="same"))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.25))
        model.add(Conv2D(64, kernel_size=3, strides=2, padding="same"))
        model.add(ZeroPadding2D(padding=((0,1),(0,1))))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.25))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Conv2D(128, kernel_size=3, strides=2, padding="same"))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.25))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Conv2D(256, kernel_size=3, strides=1, padding="same"))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.25))
        model.add(Flatten())

        model.summary()

        img = Input(shape=self.img_shape)

        features = model(img)
        valid = Dense(1, activation="sigmoid")(features)
        label = Dense(self.num_classes+1, activation="softmax")(features)

        return Model(img, [valid, label]) 

def resnet_graph(input_image, architecture, stage5=False):
    assert architecture in ["resnet50", "resnet101"]
    # Stage 1
    x = KL.ZeroPadding2D((3, 3))(input_image)
    x = KL.Conv2D(64, (7, 7), strides=(2, 2), name='conv1', use_bias=True)(x)
    x = BatchNorm(axis=3, name='bn_conv1')(x)
    x = KL.Activation('relu')(x)
    C1 = x = KL.MaxPooling2D((3, 3), strides=(2, 2), padding="same")(x)
    # Stage 2
    x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
    x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
    C2 = x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')
    # Stage 3
    x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
    C3 = x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')
    # Stage 4
    x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
    block_count = {"resnet50": 5, "resnet101": 22}[architecture]
    for i in range(block_count):
        x = identity_block(x, 3, [256, 256, 1024], stage=4, block=chr(98 + i))
    C4 = x
    # Stage 5
    if stage5:
        x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
        x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
        C5 = x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')
    else:
        C5 = None
    return [C1, C2, C3, C4, C5]


############################################################
#  Proposal Layer
############################################################ 

def resblock_body(x, num_filters, num_blocks):
    '''A series of resblocks starting with a downsampling Convolution2D'''
    # Darknet uses left and top padding instead of 'same' mode
    x = ZeroPadding2D(((1, 0), (1, 0)))(x)
    x = DarknetConv2D_BN_Leaky(num_filters, (3, 3), strides=(2, 2))(x)
    for i in range(num_blocks):
        y = compose(
            DarknetConv2D_BN_Leaky(num_filters // 2, (1, 1)),
            DarknetConv2D_BN_Leaky(num_filters, (3, 3)))(x)
        x = Add()([x, y])
    return x 

def resblock_body(x, num_filters, num_blocks):
    x = ZeroPadding2D(((1,0),(1,0)))(x)
    x = DarknetConv2D_BN_Leaky(num_filters, (3,3), strides=(2,2))(x)
    for i in range(num_blocks):
        y = DarknetConv2D_BN_Leaky(num_filters//2, (1,1))(x)
        y = DarknetConv2D_BN_Leaky(num_filters, (3,3))(y)
        x = Add()([x,y])
    return x

#---------------------------------------------------#
#   darknet53 的主体部分
#---------------------------------------------------# 

def resblock_body(x, num_filters, num_blocks):
    '''A series of resblocks starting with a downsampling Convolution2D'''
    # Darknet uses left and top padding instead of 'same' mode
    x = ZeroPadding2D(((1,0),(1,0)))(x)
    x = DarknetConv2D_BN_Leaky(num_filters, (3,3), strides=(2,2))(x)
    for i in range(num_blocks):
        y = compose(
                DarknetConv2D_BN_Leaky(num_filters//2, (1,1)),
                DarknetConv2D_BN_Leaky(num_filters, (3,3)))(x)
        x = Add()([x,y])
    return x 

def residual_conv(prev, level, pad=1, lvl=1, sub_lvl=1, modify_stride=False):
    lvl = str(lvl)
    sub_lvl = str(sub_lvl)
    names = ["conv" + lvl + "_" + sub_lvl + "_1x1_reduce",
             "conv" + lvl + "_" + sub_lvl + "_1x1_reduce_bn",
             "conv" + lvl + "_" + sub_lvl + "_3x3",
             "conv" + lvl + "_" + sub_lvl + "_3x3_bn",
             "conv" + lvl + "_" + sub_lvl + "_1x1_increase",
             "conv" + lvl + "_" + sub_lvl + "_1x1_increase_bn"]
    if modify_stride is False:
        prev = Conv2D(64 * level, (1, 1), strides=(1, 1), name=names[0],
                      use_bias=False)(prev)
    elif modify_stride is True:
        prev = Conv2D(64 * level, (1, 1), strides=(2, 2), name=names[0],
                      use_bias=False)(prev)

    prev = BN(name=names[1])(prev)
    prev = Activation('relu')(prev)

    prev = ZeroPadding2D(padding=(pad, pad))(prev)
    prev = Conv2D(64 * level, (3, 3), strides=(1, 1), dilation_rate=pad,
                  name=names[2], use_bias=False)(prev)

    prev = BN(name=names[3])(prev)
    prev = Activation('relu')(prev)
    prev = Conv2D(256 * level, (1, 1), strides=(1, 1), name=names[4],
                  use_bias=False)(prev)
    prev = BN(name=names[5])(prev)
    return prev