Python tensorflow.python.keras.layers.Conv2D() Examples

The following are 18 code examples of tensorflow.python.keras.layers.Conv2D(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module tensorflow.python.keras.layers , or try the search function .
Example #1
Source Project: ImageAI   Author: OlafenwaMoses   File: resnet50.py    License: MIT License 6 votes vote down vote up
def resnet_module(input, channel_depth, strided_pool=False ):
    residual_input = input
    stride = 1

    if(strided_pool):
        stride = 2
        residual_input = Conv2D(channel_depth, kernel_size=1, strides=stride, padding="same")(residual_input)
        residual_input = BatchNormalization()(residual_input)

    input = Conv2D(int(channel_depth/4), kernel_size=1, strides=stride, padding="same")(input)
    input = BatchNormalization()(input)
    input = Activation("relu")(input)

    input = Conv2D(int(channel_depth / 4), kernel_size=3, strides=1, padding="same")(input)
    input = BatchNormalization()(input)
    input = Activation("relu")(input)

    input = Conv2D(channel_depth, kernel_size=1, strides=1, padding="same")(input)
    input = BatchNormalization()(input)

    input = add([input, residual_input])
    input = Activation("relu")(input)

    return input 
Example #2
Source Project: ImageAI   Author: OlafenwaMoses   File: resnet50.py    License: MIT License 6 votes vote down vote up
def resnet_first_block_first_module(input, channel_depth):
    residual_input = input
    stride = 1

    residual_input = Conv2D(channel_depth, kernel_size=1, strides=1, padding="same")(residual_input)
    residual_input = BatchNormalization()(residual_input)

    input = Conv2D(int(channel_depth/4), kernel_size=1, strides=stride, padding="same")(input)
    input = BatchNormalization()(input)
    input = Activation("relu")(input)

    input = Conv2D(int(channel_depth / 4), kernel_size=3, strides=stride, padding="same")(input)
    input = BatchNormalization()(input)
    input = Activation("relu")(input)

    input = Conv2D(channel_depth, kernel_size=1, strides=stride, padding="same")(input)
    input = BatchNormalization()(input)

    input = add([input, residual_input])
    input = Activation("relu")(input)

    return input 
Example #3
Source Project: ImageAI   Author: OlafenwaMoses   File: densenet.py    License: MIT License 6 votes vote down vote up
def __transition_block(ip, nb_filter, compression=1.0, weight_decay=1e-4):
    ''' Apply BatchNorm, Relu 1x1, Conv2D, optional compression, dropout and Maxpooling2D
    Args:
        ip: keras tensor
        nb_filter: number of filters
        compression: calculated as 1 - reduction. Reduces the number of feature maps
                    in the transition block.
        dropout_rate: dropout rate
        weight_decay: weight decay factor
    Returns: keras tensor, after applying batch_norm, relu-conv, dropout, maxpool
    '''
    concat_axis = 1 if K.image_data_format() == 'channels_first' else -1

    x = BatchNormalization(axis=concat_axis, epsilon=1.1e-5)(ip)
    x = Activation('relu')(x)
    x = Conv2D(int(nb_filter * compression), (1, 1), kernel_initializer='he_normal', padding='same', use_bias=False,
               kernel_regularizer=l2(weight_decay))(x)
    x = AveragePooling2D((2, 2), strides=(2, 2))(x)

    return x 
Example #4
Source Project: ImageAI   Author: OlafenwaMoses   File: squeezenet.py    License: MIT License 6 votes vote down vote up
def squeezenet_fire_module(input, input_channel_small=16, input_channel_large=64):

    channel_axis = 3

    input = Conv2D(input_channel_small, (1,1), padding="valid" )(input)
    input = Activation("relu")(input)

    input_branch_1 = Conv2D(input_channel_large, (1,1), padding="valid" )(input)
    input_branch_1 = Activation("relu")(input_branch_1)

    input_branch_2 = Conv2D(input_channel_large, (3, 3), padding="same")(input)
    input_branch_2 = Activation("relu")(input_branch_2)

    input = concatenate([input_branch_1, input_branch_2], axis=channel_axis)

    return input 
Example #5
Source Project: ImageAI   Author: OlafenwaMoses   File: densenet.py    License: MIT License 5 votes vote down vote up
def __conv_block(ip, nb_filter, bottleneck=False, dropout_rate=None, weight_decay=1e-4):
    ''' Apply BatchNorm, Relu, 3x3 Conv2D, optional bottleneck block and dropout
    Args:
        ip: Input keras tensor
        nb_filter: number of filters
        bottleneck: add bottleneck block
        dropout_rate: dropout rate
        weight_decay: weight decay factor
    Returns: keras tensor with batch_norm, relu and convolution2d added (optional bottleneck)
    '''
    concat_axis = 1 if K.image_data_format() == 'channels_first' else -1

    x = BatchNormalization(axis=concat_axis, epsilon=1.1e-5)(ip)
    x = Activation('relu')(x)

    if bottleneck:
        inter_channel = nb_filter * 4  # Obtained from https://github.com/liuzhuang13/DenseNet/blob/master/densenet.lua

        x = Conv2D(inter_channel, (1, 1), kernel_initializer='he_normal', padding='same', use_bias=False,
                   kernel_regularizer=l2(weight_decay))(x)
        x = BatchNormalization(axis=concat_axis, epsilon=1.1e-5)(x)
        x = Activation('relu')(x)

    x = Conv2D(nb_filter, (3, 3), kernel_initializer='he_normal', padding='same', use_bias=False)(x)
    if dropout_rate:
        x = Dropout(dropout_rate)(x)

    return x 
Example #6
Source Project: camera-trap-classifier   Author: marco-willi   File: small_cnn.py    License: MIT License 5 votes vote down vote up
def architecture(inputs):
    """ Architecture of model """

    conv1 = Conv2D(32, kernel_size=(3, 3),
                   activation='relu')(inputs)
    max1 = MaxPooling2D(pool_size=(2, 2))(conv1)
    conv2 = Conv2D(32, (3, 3), activation='relu')(max1)
    max2 = MaxPooling2D(pool_size=(2, 2))(conv2)
    conv3 = Conv2D(64, (3, 3), activation='relu')(max2)
    max3 = MaxPooling2D(pool_size=(2, 2))(conv3)
    flat1 = Flatten()(max3)
    dense1 = Dense(64, activation='relu')(flat1)
    drop1 = Dropout(0.5)(dense1)

    return drop1 
Example #7
Source Project: alpha-zero-general   Author: suragnair   File: RTSNNet.py    License: MIT License 5 votes vote down vote up
def __init__(self, game, encoder):
        """
        NNet model, copied from Othello NNet, with reduced fully connected layers fc1 and fc2 and reduced nnet_args.num_channels
        :param game: game configuration
        :param encoder: Encoder, used to encode game boards
        """
        from rts.src.config_class import CONFIG

        # game params
        self.board_x, self.board_y, num_encoders = game.getBoardSize()
        self.action_size = game.getActionSize()

        """
        num_encoders = CONFIG.nnet_args.encoder.num_encoders
        """
        num_encoders = encoder.num_encoders

        # Neural Net
        self.input_boards = Input(shape=(self.board_x, self.board_y, num_encoders))  # s: batch_size x board_x x board_y x num_encoders

        x_image = Reshape((self.board_x, self.board_y, num_encoders))(self.input_boards)  # batch_size  x board_x x board_y x num_encoders
        h_conv1 = Activation('relu')(BatchNormalization(axis=3)(Conv2D(CONFIG.nnet_args.num_channels, 3, padding='same', use_bias=False)(x_image)))  # batch_size  x board_x x board_y x num_channels
        h_conv2 = Activation('relu')(BatchNormalization(axis=3)(Conv2D(CONFIG.nnet_args.num_channels, 3, padding='same', use_bias=False)(h_conv1)))  # batch_size  x board_x x board_y x num_channels
        h_conv3 = Activation('relu')(BatchNormalization(axis=3)(Conv2D(CONFIG.nnet_args.num_channels, 3, padding='valid', use_bias=False)(h_conv2)))  # batch_size  x (board_x-2) x (board_y-2) x num_channels
        h_conv4 = Activation('relu')(BatchNormalization(axis=3)(Conv2D(CONFIG.nnet_args.num_channels, 3, padding='valid', use_bias=False)(h_conv3)))  # batch_size  x (board_x-4) x (board_y-4) x num_channels
        h_conv4_flat = Flatten()(h_conv4)
        s_fc1 = Dropout(CONFIG.nnet_args.dropout)(Activation('relu')(BatchNormalization(axis=1)(Dense(256, use_bias=False)(h_conv4_flat))))  # batch_size x 1024
        s_fc2 = Dropout(CONFIG.nnet_args.dropout)(Activation('relu')(BatchNormalization(axis=1)(Dense(128, use_bias=False)(s_fc1))))  # batch_size x 1024
        self.pi = Dense(self.action_size, activation='softmax', name='pi')(s_fc2)  # batch_size x self.action_size
        self.v = Dense(1, activation='tanh', name='v')(s_fc2)  # batch_size x 1

        self.model = Model(inputs=self.input_boards, outputs=[self.pi, self.v])
        self.model.compile(loss=['categorical_crossentropy', 'mean_squared_error'], optimizer=Adam(CONFIG.nnet_args.lr)) 
Example #8
Source Project: progressive-neural-architecture-search   Author: titu1994   File: ops.py    License: MIT License 5 votes vote down vote up
def __init__(self, filters, strides):
        '''
        Performs a Pointwise Conv to preserve the stride and number of channels,
        or simply adds an identity connection.
        '''
        super(Identity, self).__init__()

        if strides == (2, 2):
            self.op = Conv2D(filters, (1, 1), strides, padding='same',
                             kernel_initializer='he_uniform')
        else:
            self.op = lambda x: x 
Example #9
Source Project: progressive-neural-architecture-search   Author: titu1994   File: ops.py    License: MIT License 5 votes vote down vote up
def __init__(self, filters, kernel, strides):
        '''
        Constructs a Spatial Convolution - Batch Normalization - Relu block.
        '''
        super(Convolution, self).__init__()

        self.conv = Conv2D(filters, kernel, strides=strides, padding='same',
                           kernel_initializer='he_uniform')
        self.bn = BatchNormalization() 
Example #10
Source Project: ImageAI   Author: OlafenwaMoses   File: inceptionv3.py    License: MIT License 4 votes vote down vote up
def conv2d_bn(x,
              filters,
              num_row,
              num_col,
              padding='same',
              strides=(1, 1),
              name=None):
    """Utility function to apply conv + BN.

    # Arguments
        x: input tensor.
        filters: filters in `Conv2D`.
        num_row: height of the convolution kernel.
        num_col: width of the convolution kernel.
        padding: padding mode in `Conv2D`.
        strides: strides in `Conv2D`.
        name: name of the ops; will become `name + '_conv'`
            for the convolution and `name + '_bn'` for the
            batch norm layer.

    # Returns
        Output tensor after applying `Conv2D` and `BatchNormalization`.
    """
    if name is not None:
        bn_name = name + '_bn'
        conv_name = name + '_conv'
    else:
        bn_name = None
        conv_name = None
    if K.image_data_format() == 'channels_first':
        bn_axis = 1
    else:
        bn_axis = 3
    x = Conv2D(
        filters, (num_row, num_col),
        strides=strides,
        padding=padding,
        use_bias=False,
        name=conv_name)(x)
    x = BatchNormalization(axis=bn_axis, scale=False, name=bn_name)(x)
    x = Activation('relu', name=name)(x)
    return x 
Example #11
Source Project: training_results_v0.5   Author: mlperf   File: resnet_model.py    License: Apache License 2.0 4 votes vote down vote up
def identity_block(input_tensor, kernel_size, filters, stage, block):
  """The identity block is the block that has no conv layer at shortcut.

  # Arguments
      input_tensor: input tensor
      kernel_size: default 3, the kernel size of
          middle conv layer at main path
      filters: list of integers, the filters of 3 conv layer at main path
      stage: integer, current stage label, used for generating layer names
      block: 'a','b'..., current block label, used for generating layer names

  # Returns
      Output tensor for the block.
  """
  filters1, filters2, filters3 = filters
  if backend.image_data_format() == 'channels_last':
    bn_axis = 3
  else:
    bn_axis = 1
  conv_name_base = 'res' + str(stage) + block + '_branch'
  bn_name_base = 'bn' + str(stage) + block + '_branch'

  x = layers.Conv2D(filters1, (1, 1),
                    kernel_initializer='he_normal',
                    kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    bias_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    name=conv_name_base + '2a')(input_tensor)
  x = layers.BatchNormalization(axis=bn_axis,
                                momentum=BATCH_NORM_DECAY,
                                epsilon=BATCH_NORM_EPSILON,
                                name=bn_name_base + '2a')(x)
  x = layers.Activation('relu')(x)

  x = layers.Conv2D(filters2, kernel_size,
                    padding='same',
                    kernel_initializer='he_normal',
                    kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    bias_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    name=conv_name_base + '2b')(x)
  x = layers.BatchNormalization(axis=bn_axis,
                                momentum=BATCH_NORM_DECAY,
                                epsilon=BATCH_NORM_EPSILON,
                                name=bn_name_base + '2b')(x)
  x = layers.Activation('relu')(x)

  x = layers.Conv2D(filters3, (1, 1),
                    kernel_initializer='he_normal',
                    kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    bias_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    name=conv_name_base + '2c')(x)
  x = layers.BatchNormalization(axis=bn_axis,
                                momentum=BATCH_NORM_DECAY,
                                epsilon=BATCH_NORM_EPSILON,
                                name=bn_name_base + '2c')(x)

  x = layers.add([x, input_tensor])
  x = layers.Activation('relu')(x)
  return x 
Example #12
Source Project: tpu_models   Author: artyompal   File: resnet_model.py    License: Apache License 2.0 4 votes vote down vote up
def identity_block(input_tensor, kernel_size, filters, stage, block):
  """The identity block is the block that has no conv layer at shortcut.

  Args:
      input_tensor: input tensor
      kernel_size: default 3, the kernel size of
          middle conv layer at main path
      filters: list of integers, the filters of 3 conv layer at main path
      stage: integer, current stage label, used for generating layer names
      block: 'a','b'..., current block label, used for generating layer names

  Returns:
      Output tensor for the block.
  """
  filters1, filters2, filters3 = filters
  if backend.image_data_format() == 'channels_last':
    bn_axis = 3
  else:
    bn_axis = 1
  conv_name_base = 'res' + str(stage) + block + '_branch'
  bn_name_base = 'bn' + str(stage) + block + '_branch'

  x = layers.Conv2D(filters1, (1, 1), use_bias=False,
                    kernel_initializer='he_normal',
                    kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    name=conv_name_base + '2a')(input_tensor)
  x = layers.BatchNormalization(axis=bn_axis,
                                momentum=BATCH_NORM_DECAY,
                                epsilon=BATCH_NORM_EPSILON,
                                name=bn_name_base + '2a')(x)
  x = layers.Activation('relu')(x)

  x = layers.Conv2D(filters2, kernel_size, use_bias=False,
                    padding='same',
                    kernel_initializer='he_normal',
                    kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    name=conv_name_base + '2b')(x)
  x = layers.BatchNormalization(axis=bn_axis,
                                momentum=BATCH_NORM_DECAY,
                                epsilon=BATCH_NORM_EPSILON,
                                name=bn_name_base + '2b')(x)
  x = layers.Activation('relu')(x)

  x = layers.Conv2D(filters3, (1, 1), use_bias=False,
                    kernel_initializer='he_normal',
                    kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    name=conv_name_base + '2c')(x)
  x = layers.BatchNormalization(axis=bn_axis,
                                momentum=BATCH_NORM_DECAY,
                                epsilon=BATCH_NORM_EPSILON,
                                name=bn_name_base + '2c')(x)

  x = layers.add([x, input_tensor])
  x = layers.Activation('relu')(x)
  return x 
Example #13
Source Project: ml-on-gcp   Author: GoogleCloudPlatform   File: resnet_model.py    License: Apache License 2.0 4 votes vote down vote up
def identity_block(input_tensor, kernel_size, filters, stage, block):
  """The identity block is the block that has no conv layer at shortcut.

  # Arguments
      input_tensor: input tensor
      kernel_size: default 3, the kernel size of
          middle conv layer at main path
      filters: list of integers, the filters of 3 conv layer at main path
      stage: integer, current stage label, used for generating layer names
      block: 'a','b'..., current block label, used for generating layer names

  # Returns
      Output tensor for the block.
  """
  filters1, filters2, filters3 = filters
  if backend.image_data_format() == 'channels_last':
    bn_axis = 3
  else:
    bn_axis = 1
  conv_name_base = 'res' + str(stage) + block + '_branch'
  bn_name_base = 'bn' + str(stage) + block + '_branch'

  x = layers.Conv2D(filters1, (1, 1), use_bias=False,
                    kernel_initializer='he_normal',
                    kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    name=conv_name_base + '2a')(input_tensor)
  x = layers.BatchNormalization(axis=bn_axis,
                                momentum=BATCH_NORM_DECAY,
                                epsilon=BATCH_NORM_EPSILON,
                                name=bn_name_base + '2a')(x)
  x = layers.Activation('relu')(x)

  x = layers.Conv2D(filters2, kernel_size,
                    padding='same', use_bias=False,
                    kernel_initializer='he_normal',
                    kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    name=conv_name_base + '2b')(x)
  x = layers.BatchNormalization(axis=bn_axis,
                                momentum=BATCH_NORM_DECAY,
                                epsilon=BATCH_NORM_EPSILON,
                                name=bn_name_base + '2b')(x)
  x = layers.Activation('relu')(x)

  x = layers.Conv2D(filters3, (1, 1), use_bias=False,
                    kernel_initializer='he_normal',
                    kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    name=conv_name_base + '2c')(x)
  x = layers.BatchNormalization(axis=bn_axis,
                                momentum=BATCH_NORM_DECAY,
                                epsilon=BATCH_NORM_EPSILON,
                                name=bn_name_base + '2c')(x)

  x = layers.add([x, input_tensor])
  x = layers.Activation('relu')(x)
  return x 
Example #14
def identity_building_block(input_tensor,
                            kernel_size,
                            filters,
                            stage,
                            block,
                            training=None):
  """The identity block is the block that has no conv layer at shortcut.

  Arguments:
    input_tensor: input tensor
    kernel_size: default 3, the kernel size of
        middle conv layer at main path
    filters: list of integers, the filters of 3 conv layer at main path
    stage: integer, current stage label, used for generating layer names
    block: current block label, used for generating layer names
    training: Only used if training keras model with Estimator.  In other
      scenarios it is handled automatically.

  Returns:
    Output tensor for the block.
  """
  filters1, filters2 = filters
  if backend.image_data_format() == 'channels_last':
    bn_axis = 3
  else:
    bn_axis = 1
  conv_name_base = 'res' + str(stage) + block + '_branch'
  bn_name_base = 'bn' + str(stage) + block + '_branch'

  x = layers.Conv2D(filters1, kernel_size,
                    padding='same', use_bias=False,
                    kernel_initializer='he_normal',
                    kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    name=conv_name_base + '2a')(input_tensor)
  x = layers.BatchNormalization(
      axis=bn_axis, momentum=BATCH_NORM_DECAY, epsilon=BATCH_NORM_EPSILON,
      name=bn_name_base + '2a')(x, training=training)
  x = layers.Activation('relu')(x)

  x = layers.Conv2D(filters2, kernel_size,
                    padding='same', use_bias=False,
                    kernel_initializer='he_normal',
                    kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    name=conv_name_base + '2b')(x)
  x = layers.BatchNormalization(
      axis=bn_axis, momentum=BATCH_NORM_DECAY, epsilon=BATCH_NORM_EPSILON,
      name=bn_name_base + '2b')(x, training=training)

  x = layers.add([x, input_tensor])
  x = layers.Activation('relu')(x)
  return x 
Example #15
Source Project: mnist_digits_classification   Author: aliakbar09a   File: conv_network.py    License: MIT License 4 votes vote down vote up
def model(train_x, train_y, test_x, test_y, epoch):
    '''

    :param train_x: train features
    :param train_y: train labels
    :param test_x:  test features
    :param test_y: test labels
    :param epoch: no. of epochs
    :return:
    '''
    conv_model = Sequential()
    # first layer with input shape (img_rows, img_cols, 1) and 12 filters
    conv_model.add(Conv2D(12, kernel_size=(3, 3), activation='relu',
                          input_shape=(img_rows, img_cols, 1)))
    # second layer with 12 filters
    conv_model.add(Conv2D(12, kernel_size=(3, 3), activation='relu'))
    # third layer with 12 filers
    conv_model.add(Conv2D(12, kernel_size=(3, 3), activation='relu'))
    # flatten layer
    conv_model.add(Flatten())
    # adding a Dense layer
    conv_model.add(Dense(100, activation='relu'))
    # adding the final Dense layer with softmax
    conv_model.add(Dense(num_classes, activation='softmax'))

    # compile the model
    conv_model.compile(optimizer=keras.optimizers.Adadelta(),
                       loss='categorical_crossentropy',
                       metrics=['accuracy'])
    print("\n Training the Convolution Neural Network on MNIST data\n")
    # fit the model
    conv_model.fit(train_x, train_y, batch_size=128, epochs=epoch,
                   validation_split=0.1, verbose=2)
    predicted_train_y = conv_model.predict(train_x)
    train_accuracy = (sum(np.argmax(predicted_train_y, axis=1)
                          == np.argmax(train_y, axis=1))/(float(len(train_y))))
    print('Train accuracy : ', train_accuracy)
    predicted_test_y = conv_model.predict(test_x)
    test_accuracy = (sum(np.argmax(predicted_test_y, axis=1)
                         == np.argmax(test_y, axis=1))/(float(len(test_y))))
    print('Test accuracy : ', test_accuracy)
    CNN_accuracy = {'train_accuracy': train_accuracy,
                    'test_accuracy': test_accuracy, 'epoch': epoch}
    return conv_model, CNN_accuracy 
Example #16
Source Project: g-tensorflow-models   Author: generalized-iou   File: resnet_model.py    License: Apache License 2.0 4 votes vote down vote up
def identity_block(input_tensor, kernel_size, filters, stage, block):
  """The identity block is the block that has no conv layer at shortcut.

  # Arguments
      input_tensor: input tensor
      kernel_size: default 3, the kernel size of
          middle conv layer at main path
      filters: list of integers, the filters of 3 conv layer at main path
      stage: integer, current stage label, used for generating layer names
      block: 'a','b'..., current block label, used for generating layer names

  # Returns
      Output tensor for the block.
  """
  filters1, filters2, filters3 = filters
  if backend.image_data_format() == 'channels_last':
    bn_axis = 3
  else:
    bn_axis = 1
  conv_name_base = 'res' + str(stage) + block + '_branch'
  bn_name_base = 'bn' + str(stage) + block + '_branch'

  x = layers.Conv2D(filters1, (1, 1), use_bias=False,
                    kernel_initializer='he_normal',
                    kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    name=conv_name_base + '2a')(input_tensor)
  x = layers.BatchNormalization(axis=bn_axis,
                                momentum=BATCH_NORM_DECAY,
                                epsilon=BATCH_NORM_EPSILON,
                                name=bn_name_base + '2a')(x)
  x = layers.Activation('relu')(x)

  x = layers.Conv2D(filters2, kernel_size,
                    padding='same', use_bias=False,
                    kernel_initializer='he_normal',
                    kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    name=conv_name_base + '2b')(x)
  x = layers.BatchNormalization(axis=bn_axis,
                                momentum=BATCH_NORM_DECAY,
                                epsilon=BATCH_NORM_EPSILON,
                                name=bn_name_base + '2b')(x)
  x = layers.Activation('relu')(x)

  x = layers.Conv2D(filters3, (1, 1), use_bias=False,
                    kernel_initializer='he_normal',
                    kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    name=conv_name_base + '2c')(x)
  x = layers.BatchNormalization(axis=bn_axis,
                                momentum=BATCH_NORM_DECAY,
                                epsilon=BATCH_NORM_EPSILON,
                                name=bn_name_base + '2c')(x)

  x = layers.add([x, input_tensor])
  x = layers.Activation('relu')(x)
  return x 
Example #17
Source Project: models   Author: tensorflow   File: resnet_cifar_model.py    License: Apache License 2.0 4 votes vote down vote up
def identity_building_block(input_tensor,
                            kernel_size,
                            filters,
                            stage,
                            block,
                            training=None):
  """The identity block is the block that has no conv layer at shortcut.

  Arguments:
    input_tensor: input tensor
    kernel_size: default 3, the kernel size of
        middle conv layer at main path
    filters: list of integers, the filters of 3 conv layer at main path
    stage: integer, current stage label, used for generating layer names
    block: current block label, used for generating layer names
    training: Only used if training keras model with Estimator.  In other
      scenarios it is handled automatically.

  Returns:
    Output tensor for the block.
  """
  filters1, filters2 = filters
  if backend.image_data_format() == 'channels_last':
    bn_axis = 3
  else:
    bn_axis = 1
  conv_name_base = 'res' + str(stage) + block + '_branch'
  bn_name_base = 'bn' + str(stage) + block + '_branch'

  x = layers.Conv2D(filters1, kernel_size,
                    padding='same', use_bias=False,
                    kernel_initializer='he_normal',
                    kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    name=conv_name_base + '2a')(input_tensor)
  x = layers.BatchNormalization(
      axis=bn_axis, momentum=BATCH_NORM_DECAY, epsilon=BATCH_NORM_EPSILON,
      name=bn_name_base + '2a')(x, training=training)
  x = layers.Activation('relu')(x)

  x = layers.Conv2D(filters2, kernel_size,
                    padding='same', use_bias=False,
                    kernel_initializer='he_normal',
                    kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    name=conv_name_base + '2b')(x)
  x = layers.BatchNormalization(
      axis=bn_axis, momentum=BATCH_NORM_DECAY, epsilon=BATCH_NORM_EPSILON,
      name=bn_name_base + '2b')(x, training=training)

  x = layers.add([x, input_tensor])
  x = layers.Activation('relu')(x)
  return x 
Example #18
Source Project: class-balanced-loss   Author: richardaecn   File: resnet_model.py    License: MIT License 4 votes vote down vote up
def identity_block(input_tensor, kernel_size, filters, stage, block):
  """The identity block is the block that has no conv layer at shortcut.

  # Arguments
      input_tensor: input tensor
      kernel_size: default 3, the kernel size of
          middle conv layer at main path
      filters: list of integers, the filters of 3 conv layer at main path
      stage: integer, current stage label, used for generating layer names
      block: 'a','b'..., current block label, used for generating layer names

  # Returns
      Output tensor for the block.
  """
  filters1, filters2, filters3 = filters
  if backend.image_data_format() == 'channels_last':
    bn_axis = 3
  else:
    bn_axis = 1
  conv_name_base = 'res' + str(stage) + block + '_branch'
  bn_name_base = 'bn' + str(stage) + block + '_branch'

  x = layers.Conv2D(filters1, (1, 1),
                    kernel_initializer='he_normal',
                    kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    bias_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    name=conv_name_base + '2a')(input_tensor)
  x = layers.BatchNormalization(axis=bn_axis,
                                momentum=BATCH_NORM_DECAY,
                                epsilon=BATCH_NORM_EPSILON,
                                name=bn_name_base + '2a')(x)
  x = layers.Activation('relu')(x)

  x = layers.Conv2D(filters2, kernel_size,
                    padding='same',
                    kernel_initializer='he_normal',
                    kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    bias_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    name=conv_name_base + '2b')(x)
  x = layers.BatchNormalization(axis=bn_axis,
                                momentum=BATCH_NORM_DECAY,
                                epsilon=BATCH_NORM_EPSILON,
                                name=bn_name_base + '2b')(x)
  x = layers.Activation('relu')(x)

  x = layers.Conv2D(filters3, (1, 1),
                    kernel_initializer='he_normal',
                    kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    bias_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
                    name=conv_name_base + '2c')(x)
  x = layers.BatchNormalization(axis=bn_axis,
                                momentum=BATCH_NORM_DECAY,
                                epsilon=BATCH_NORM_EPSILON,
                                name=bn_name_base + '2c')(x)

  x = layers.add([x, input_tensor])
  x = layers.Activation('relu')(x)
  return x