Python keras_frcnn.FixedBatchNormalization.FixedBatchNormalization() Examples

The following are 30 code examples of keras_frcnn.FixedBatchNormalization.FixedBatchNormalization(). 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 keras_frcnn.FixedBatchNormalization , or try the search function .
Example #1
Source File: resnet.py    From keras-frcnn with Apache License 2.0 5 votes vote down vote up 
def conv_block(input_tensor, kernel_size, filters, stage, block, strides=(2, 2), trainable=True):
    '''conv_block is the block that has a conv layer at shortcut
    # Arguments
            input_tensor: input tensor
            kernel_size: defualt 3, the kernel size of middle conv layer at main path
            filters: list of integers, the nb_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
    Note that from stage 3, the first conv layer at main path is with subsample=(2,2)
    And the shortcut should have subsample=(2,2) as well
    '''
    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = Convolution2D(nb_filter1, 1, 1, subsample=strides, name=conv_name_base + '2a', trainable=trainable)(input_tensor)
    x = FixedBatchNormalization(trainable=False,axis=bn_axis, name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter2, kernel_size, kernel_size, border_mode='same', name=conv_name_base + '2b', trainable=trainable)(x)
    x = FixedBatchNormalization(trainable=False,axis=bn_axis, name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter3, 1, 1, name=conv_name_base + '2c', trainable=trainable)(x)
    x = FixedBatchNormalization(trainable=False,axis=bn_axis, name=bn_name_base + '2c')(x)

    shortcut = Convolution2D(nb_filter3, 1, 1, subsample=strides, name=conv_name_base + '1', trainable=trainable)(input_tensor)
    shortcut = FixedBatchNormalization(trainable=False,axis=bn_axis, name=bn_name_base + '1')(shortcut)

    x = merge([x, shortcut], mode='sum')
    x = Activation('relu')(x)
    return x
Example #2
Source File: resnet101.py    From keras-faster-rcnn with Apache License 2.0 5 votes vote down vote up 
def identity_block(input_tensor, kernel_size, filters, stage, block, trainable=True):
    nb_filter1, nb_filter2, nb_filter3 = filters

    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = Convolution2D(nb_filter1, (1, 1), name=conv_name_base + '2a', trainable=trainable)(input_tensor)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter2, (kernel_size, kernel_size), padding='same', name=conv_name_base + '2b',
                      trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter3, (1, 1), name=conv_name_base + '2c', trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)

    x = Add()([x, input_tensor])
    x = Activation('relu')(x)
    return x
Example #3
Source File: resnet101.py    From keras-faster-rcnn with Apache License 2.0 5 votes vote down vote up 
def identity_block_td(input_tensor, kernel_size, filters, stage, block, trainable=True):
    # identity block time distributed

    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = TimeDistributed(Convolution2D(nb_filter1, (1, 1), trainable=trainable, kernel_initializer='normal'),
                        name=conv_name_base + '2a')(input_tensor)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(
        Convolution2D(nb_filter2, (kernel_size, kernel_size), trainable=trainable, kernel_initializer='normal',
                      padding='same'), name=conv_name_base + '2b')(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter3, (1, 1), trainable=trainable, kernel_initializer='normal'),
                        name=conv_name_base + '2c')(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2c')(x)

    x = Add()([x, input_tensor])
    x = Activation('relu')(x)

    return x
Example #4
Source File: resnet101.py    From keras-faster-rcnn with Apache License 2.0 5 votes vote down vote up 
def conv_block(input_tensor, kernel_size, filters, stage, block, strides=(2, 2), trainable=True):
    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = Convolution2D(nb_filter1, (1, 1), strides=strides, name=conv_name_base + '2a', trainable=trainable)(
        input_tensor)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter2, (kernel_size, kernel_size), padding='same', name=conv_name_base + '2b',
                      trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter3, (1, 1), name=conv_name_base + '2c', trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)

    shortcut = Convolution2D(nb_filter3, (1, 1), strides=strides, name=conv_name_base + '1', trainable=trainable)(
        input_tensor)
    shortcut = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '1')(shortcut)

    x = Add()([x, shortcut])
    x = Activation('relu')(x)
    return x
Example #5
Source File: resnet101.py    From keras-faster-rcnn with Apache License 2.0 5 votes vote down vote up 
def conv_block_td(input_tensor, kernel_size, filters, stage, block, input_shape, strides=(2, 2), trainable=True):
    # conv block time distributed

    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = TimeDistributed(
        Convolution2D(nb_filter1, (1, 1), strides=strides, trainable=trainable, kernel_initializer='normal'),
        input_shape=input_shape, name=conv_name_base + '2a')(input_tensor)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter2, (kernel_size, kernel_size), padding='same', trainable=trainable,
                                      kernel_initializer='normal'), name=conv_name_base + '2b')(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter3, (1, 1), kernel_initializer='normal'), name=conv_name_base + '2c',
                        trainable=trainable)(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2c')(x)

    shortcut = TimeDistributed(
        Convolution2D(nb_filter3, (1, 1), strides=strides, trainable=trainable, kernel_initializer='normal'),
        name=conv_name_base + '1')(input_tensor)
    shortcut = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '1')(shortcut)

    x = Add()([x, shortcut])
    x = Activation('relu')(x)
    return x
Example #6
Source File: resnet.py    From keras-faster-rcnn with Apache License 2.0 5 votes vote down vote up 
def identity_block_td(input_tensor, kernel_size, filters, stage, block, trainable=True):

    # identity block time distributed

    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = TimeDistributed(Convolution2D(nb_filter1, (1, 1), trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '2a')(input_tensor)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter2, (kernel_size, kernel_size), trainable=trainable, kernel_initializer='normal',padding='same'), name=conv_name_base + '2b')(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter3, (1, 1), trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '2c')(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2c')(x)

    x = Add()([x, input_tensor])
    x = Activation('relu')(x)

    return x
Example #7
Source File: resnet.py    From keras-faster-rcnn with Apache License 2.0 5 votes vote down vote up 
def conv_block(input_tensor, kernel_size, filters, stage, block, strides=(2, 2), trainable=True):

    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = Convolution2D(nb_filter1, (1, 1), strides=strides, name=conv_name_base + '2a', trainable=trainable)(input_tensor)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter2, (kernel_size, kernel_size), padding='same', name=conv_name_base + '2b', trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter3, (1, 1), name=conv_name_base + '2c', trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)

    shortcut = Convolution2D(nb_filter3, (1, 1), strides=strides, name=conv_name_base + '1', trainable=trainable)(input_tensor)
    shortcut = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '1')(shortcut)

    x = Add()([x, shortcut])
    x = Activation('relu')(x)
    return x
Example #8
Source File: resnet.py    From keras-faster-rcnn with Apache License 2.0 5 votes vote down vote up 
def conv_block_td(input_tensor, kernel_size, filters, stage, block, input_shape, strides=(2, 2), trainable=True):

    # conv block time distributed

    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = TimeDistributed(Convolution2D(nb_filter1, (1, 1), strides=strides, trainable=trainable, kernel_initializer='normal'), input_shape=input_shape, name=conv_name_base + '2a')(input_tensor)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter2, (kernel_size, kernel_size), padding='same', trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '2b')(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter3, (1, 1), kernel_initializer='normal'), name=conv_name_base + '2c', trainable=trainable)(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2c')(x)

    shortcut = TimeDistributed(Convolution2D(nb_filter3, (1, 1), strides=strides, trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '1')(input_tensor)
    shortcut = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '1')(shortcut)

    x = Add()([x, shortcut])
    x = Activation('relu')(x)
    return x
Example #9
Source File: resnet.py    From keras-frcnn with Apache License 2.0 5 votes vote down vote up 
def identity_block(input_tensor, kernel_size, filters, stage, block, trainable=True):

    '''The identity_block is the block that has no conv layer at shortcut
    # Arguments
            input_tensor: input tensor
            kernel_size: defualt 3, the kernel size of middle conv layer at main path
            filters: list of integers, the nb_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
    '''
    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = Convolution2D(nb_filter1, 1, 1, name=conv_name_base + '2a', trainable=trainable)(input_tensor)
    x = FixedBatchNormalization(trainable=False,axis=bn_axis, name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter2, kernel_size, kernel_size, border_mode='same', name=conv_name_base + '2b', trainable=trainable)(x)
    x = FixedBatchNormalization(trainable=False,axis=bn_axis, name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter3, 1, 1, name=conv_name_base + '2c', trainable=trainable)(x)
    x = FixedBatchNormalization(trainable=False,axis=bn_axis, name=bn_name_base + '2c')(x)

    x = merge([x, input_tensor], mode='sum')
    x = Activation('relu')(x)
    return x
Example #10
Source File: resnet.py    From keras-frcnn with Apache License 2.0 5 votes vote down vote up 
def identity_block_td(input_tensor, kernel_size, filters, stage, block, trainable=True):
    '''The identity_block is the block that has no conv layer at shortcut
    # Arguments
            input_tensor: input tensor
            kernel_size: defualt 3, the kernel size of middle conv layer at main path
            filters: list of integers, the nb_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
    '''
    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'


    x = TimeDistributed(Convolution2D(nb_filter1, 1, 1, trainable=trainable, init='normal'), name=conv_name_base + '2a')(input_tensor)
    x = TimeDistributed(FixedBatchNormalization(trainable=False,axis=bn_axis), name=bn_name_base + '2a')(x)

    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter2, kernel_size, kernel_size, trainable=trainable, init='normal',border_mode='same'), name=conv_name_base + '2b')(x)
    x = TimeDistributed(FixedBatchNormalization(trainable=False,axis=bn_axis), name=bn_name_base + '2b')(x)

    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter3, 1, 1, trainable=trainable, init='normal'), name=conv_name_base + '2c')(x)
    x = TimeDistributed(FixedBatchNormalization(trainable=False,axis=bn_axis), name=bn_name_base + '2c')(x)


    x = merge([x, input_tensor], mode='sum')
    x = Activation('relu')(x)

    return x
Example #11
Source File: resnet.py    From FasterRCNN_KERAS with Apache License 2.0 5 votes vote down vote up 
def identity_block_td(input_tensor, kernel_size, filters, stage, block, trainable=True):

    # identity block time distributed

    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = TimeDistributed(Convolution2D(nb_filter1, (1, 1), trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '2a')(input_tensor)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter2, (kernel_size, kernel_size), trainable=trainable, kernel_initializer='normal',padding='same'), name=conv_name_base + '2b')(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter3, (1, 1), trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '2c')(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2c')(x)

    x = Add()([x, input_tensor])
    x = Activation('relu')(x)

    return x
Example #12
Source File: resnet.py    From keras-frcnn with Apache License 2.0 5 votes vote down vote up 
def conv_block_td(input_tensor, kernel_size, filters, stage, block, strides=(2, 2), trainable=True):
    '''conv_block is the block that has a conv layer at shortcut
    # Arguments
            input_tensor: input tensor
            kernel_size: defualt 3, the kernel size of middle conv layer at main path
            filters: list of integers, the nb_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
    Note that from stage 3, the first conv layer at main path is with subsample=(2,2)
    And the shortcut should have subsample=(2,2) as well
    '''
    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = TimeDistributed(Convolution2D(nb_filter1, 1, 1, subsample=strides, trainable=trainable, init='normal'), name=conv_name_base + '2a')(input_tensor)
    x = TimeDistributed(FixedBatchNormalization(trainable=False,axis=bn_axis), name=bn_name_base + '2a')(x)

    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter2, kernel_size, kernel_size, border_mode='same', trainable=trainable, init='normal'), name=conv_name_base + '2b')(x)
    x = TimeDistributed(FixedBatchNormalization(trainable=False,axis=bn_axis), name=bn_name_base + '2b')(x)

    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter3, 1, 1, init='normal'), name=conv_name_base + '2c', trainable=trainable)(x)
    x = TimeDistributed(FixedBatchNormalization(trainable=False,axis=bn_axis), name=bn_name_base + '2c')(x)

    shortcut = TimeDistributed(Convolution2D(nb_filter3, 1, 1, subsample=strides, trainable=trainable, init='normal'), name=conv_name_base + '1')(input_tensor)
    shortcut = TimeDistributed(FixedBatchNormalization(trainable=False,axis=bn_axis), name=bn_name_base + '1')(shortcut)


    x = merge([x, shortcut], mode='sum')
    x = Activation('relu')(x)
    return x
Example #13
Source File: resnet.py    From ssbm_fox_detector with MIT License 5 votes vote down vote up 
def identity_block(input_tensor, kernel_size, filters, stage, block, trainable=True):

    nb_filter1, nb_filter2, nb_filter3 = filters
    
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = Convolution2D(nb_filter1, (1, 1), name=conv_name_base + '2a', trainable=trainable)(input_tensor)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter2, (kernel_size, kernel_size), padding='same', name=conv_name_base + '2b', trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter3, (1, 1), name=conv_name_base + '2c', trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)

    x = Add()([x, input_tensor])
    x = Activation('relu')(x)
    return x
Example #14
Source File: resnet.py    From ssbm_fox_detector with MIT License 5 votes vote down vote up 
def identity_block_td(input_tensor, kernel_size, filters, stage, block, trainable=True):

    # identity block time distributed

    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = TimeDistributed(Convolution2D(nb_filter1, (1, 1), trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '2a')(input_tensor)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter2, (kernel_size, kernel_size), trainable=trainable, kernel_initializer='normal',padding='same'), name=conv_name_base + '2b')(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter3, (1, 1), trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '2c')(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2c')(x)

    x = Add()([x, input_tensor])
    x = Activation('relu')(x)

    return x
Example #15
Source File: resnet.py    From ssbm_fox_detector with MIT License 5 votes vote down vote up 
def conv_block(input_tensor, kernel_size, filters, stage, block, strides=(2, 2), trainable=True):

    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = Convolution2D(nb_filter1, (1, 1), strides=strides, name=conv_name_base + '2a', trainable=trainable)(input_tensor)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter2, (kernel_size, kernel_size), padding='same', name=conv_name_base + '2b', trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter3, (1, 1), name=conv_name_base + '2c', trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)

    shortcut = Convolution2D(nb_filter3, (1, 1), strides=strides, name=conv_name_base + '1', trainable=trainable)(input_tensor)
    shortcut = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '1')(shortcut)

    x = Add()([x, shortcut])
    x = Activation('relu')(x)
    return x
Example #16
Source File: resnet.py    From ssbm_fox_detector with MIT License 5 votes vote down vote up 
def conv_block_td(input_tensor, kernel_size, filters, stage, block, input_shape, strides=(2, 2), trainable=True):

    # conv block time distributed

    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = TimeDistributed(Convolution2D(nb_filter1, (1, 1), strides=strides, trainable=trainable, kernel_initializer='normal'), input_shape=input_shape, name=conv_name_base + '2a')(input_tensor)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter2, (kernel_size, kernel_size), padding='same', trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '2b')(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter3, (1, 1), kernel_initializer='normal'), name=conv_name_base + '2c', trainable=trainable)(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2c')(x)

    shortcut = TimeDistributed(Convolution2D(nb_filter3, (1, 1), strides=strides, trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '1')(input_tensor)
    shortcut = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '1')(shortcut)

    x = Add()([x, shortcut])
    x = Activation('relu')(x)
    return x
Example #17
Source File: resnet.py    From ZSD_Release with MIT License 5 votes vote down vote up 
def identity_block(input_tensor, kernel_size, filters, stage, block, trainable=True):

    nb_filter1, nb_filter2, nb_filter3 = filters
    
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = Convolution2D(nb_filter1, (1, 1), name=conv_name_base + '2a', trainable=trainable)(input_tensor)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter2, (kernel_size, kernel_size), padding='same', name=conv_name_base + '2b', trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter3, (1, 1), name=conv_name_base + '2c', trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)

    x = Add()([x, input_tensor])
    x = Activation('relu')(x)
    return x
Example #18
Source File: resnet.py    From ZSD_Release with MIT License 5 votes vote down vote up 
def identity_block_td(input_tensor, kernel_size, filters, stage, block, trainable=True):

    # identity block time distributed

    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = TimeDistributed(Convolution2D(nb_filter1, (1, 1), trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '2a')(input_tensor)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter2, (kernel_size, kernel_size), trainable=trainable, kernel_initializer='normal',padding='same'), name=conv_name_base + '2b')(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter3, (1, 1), trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '2c')(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2c')(x)

    x = Add()([x, input_tensor])
    x = Activation('relu')(x)

    return x
Example #19
Source File: resnet.py    From ZSD_Release with MIT License 5 votes vote down vote up 
def conv_block(input_tensor, kernel_size, filters, stage, block, strides=(2, 2), trainable=True):

    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = Convolution2D(nb_filter1, (1, 1), strides=strides, name=conv_name_base + '2a', trainable=trainable)(input_tensor)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter2, (kernel_size, kernel_size), padding='same', name=conv_name_base + '2b', trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter3, (1, 1), name=conv_name_base + '2c', trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)

    shortcut = Convolution2D(nb_filter3, (1, 1), strides=strides, name=conv_name_base + '1', trainable=trainable)(input_tensor)
    shortcut = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '1')(shortcut)

    x = Add()([x, shortcut])
    x = Activation('relu')(x)
    return x
Example #20
Source File: resnet.py    From ZSD_Release with MIT License 5 votes vote down vote up 
def conv_block_td(input_tensor, kernel_size, filters, stage, block, input_shape, strides=(2, 2), trainable=True):

    # conv block time distributed

    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = TimeDistributed(Convolution2D(nb_filter1, (1, 1), strides=strides, trainable=trainable, kernel_initializer='normal'), input_shape=input_shape, name=conv_name_base + '2a')(input_tensor)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter2, (kernel_size, kernel_size), padding='same', trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '2b')(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter3, (1, 1), kernel_initializer='normal'), name=conv_name_base + '2c', trainable=trainable)(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2c')(x)

    shortcut = TimeDistributed(Convolution2D(nb_filter3, (1, 1), strides=strides, trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '1')(input_tensor)
    shortcut = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '1')(shortcut)

    x = Add()([x, shortcut])
    x = Activation('relu')(x)
    return x
Example #21
Source File: resnet.py    From Keras-FasterRCNN with MIT License 5 votes vote down vote up 
def conv_block(input_tensor, kernel_size, filters, stage, block, strides=(2, 2), trainable=True):

    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = Convolution2D(nb_filter1, (1, 1), strides=strides, name=conv_name_base + '2a', trainable=trainable)(input_tensor)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter2, (kernel_size, kernel_size), padding='same', name=conv_name_base + '2b', trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter3, (1, 1), name=conv_name_base + '2c', trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)

    shortcut = Convolution2D(nb_filter3, (1, 1), strides=strides, name=conv_name_base + '1', trainable=trainable)(input_tensor)
    shortcut = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '1')(shortcut)

    x = Add()([x, shortcut])
    x = Activation('relu')(x)
    return x
Example #22
Source File: resnet.py    From keras-frcnn with Apache License 2.0 5 votes vote down vote up 
def identity_block(input_tensor, kernel_size, filters, stage, block, trainable=True):

    nb_filter1, nb_filter2, nb_filter3 = filters
    
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = Convolution2D(nb_filter1, (1, 1), name=conv_name_base + '2a', trainable=trainable)(input_tensor)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter2, (kernel_size, kernel_size), padding='same', name=conv_name_base + '2b', trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter3, (1, 1), name=conv_name_base + '2c', trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)

    x = Add()([x, input_tensor])
    x = Activation('relu')(x)
    return x
Example #23
Source File: resnet.py    From keras-frcnn with Apache License 2.0 5 votes vote down vote up 
def identity_block_td(input_tensor, kernel_size, filters, stage, block, trainable=True):

    # identity block time distributed

    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = TimeDistributed(Convolution2D(nb_filter1, (1, 1), trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '2a')(input_tensor)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter2, (kernel_size, kernel_size), trainable=trainable, kernel_initializer='normal',padding='same'), name=conv_name_base + '2b')(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter3, (1, 1), trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '2c')(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2c')(x)

    x = Add()([x, input_tensor])
    x = Activation('relu')(x)

    return x
Example #24
Source File: resnet.py    From keras-frcnn with Apache License 2.0 5 votes vote down vote up 
def conv_block(input_tensor, kernel_size, filters, stage, block, strides=(2, 2), trainable=True):

    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = Convolution2D(nb_filter1, (1, 1), strides=strides, name=conv_name_base + '2a', trainable=trainable)(input_tensor)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter2, (kernel_size, kernel_size), padding='same', name=conv_name_base + '2b', trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter3, (1, 1), name=conv_name_base + '2c', trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)

    shortcut = Convolution2D(nb_filter3, (1, 1), strides=strides, name=conv_name_base + '1', trainable=trainable)(input_tensor)
    shortcut = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '1')(shortcut)

    x = Add()([x, shortcut])
    x = Activation('relu')(x)
    return x
Example #25
Source File: resnet.py    From keras-frcnn with Apache License 2.0 5 votes vote down vote up 
def conv_block_td(input_tensor, kernel_size, filters, stage, block, input_shape, strides=(2, 2), trainable=True):

    # conv block time distributed

    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = TimeDistributed(Convolution2D(nb_filter1, (1, 1), strides=strides, trainable=trainable, kernel_initializer='normal'), input_shape=input_shape, name=conv_name_base + '2a')(input_tensor)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter2, (kernel_size, kernel_size), padding='same', trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '2b')(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter3, (1, 1), kernel_initializer='normal'), name=conv_name_base + '2c', trainable=trainable)(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2c')(x)

    shortcut = TimeDistributed(Convolution2D(nb_filter3, (1, 1), strides=strides, trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '1')(input_tensor)
    shortcut = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '1')(shortcut)

    x = Add()([x, shortcut])
    x = Activation('relu')(x)
    return x
Example #26
Source File: resnet.py    From FasterRCNN_KERAS with Apache License 2.0 5 votes vote down vote up 
def conv_block_td(input_tensor, kernel_size, filters, stage, block, input_shape, strides=(2, 2), trainable=True):

    # conv block time distributed

    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = TimeDistributed(Convolution2D(nb_filter1, (1, 1), strides=strides, trainable=trainable, kernel_initializer='normal'), input_shape=input_shape, name=conv_name_base + '2a')(input_tensor)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter2, (kernel_size, kernel_size), padding='same', trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '2b')(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter3, (1, 1), kernel_initializer='normal'), name=conv_name_base + '2c', trainable=trainable)(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2c')(x)

    shortcut = TimeDistributed(Convolution2D(nb_filter3, (1, 1), strides=strides, trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '1')(input_tensor)
    shortcut = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '1')(shortcut)

    x = Add()([x, shortcut])
    x = Activation('relu')(x)
    return x
Example #27
Source File: resnet.py    From Keras-FasterRCNN with MIT License 5 votes vote down vote up 
def identity_block(input_tensor, kernel_size, filters, stage, block, trainable=True):

    nb_filter1, nb_filter2, nb_filter3 = filters
    
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = Convolution2D(nb_filter1, (1, 1), name=conv_name_base + '2a', trainable=trainable)(input_tensor)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter2, (kernel_size, kernel_size), padding='same', name=conv_name_base + '2b', trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter3, (1, 1), name=conv_name_base + '2c', trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)

    x = Add()([x, input_tensor])
    x = Activation('relu')(x)
    return x
Example #28
Source File: resnet.py    From Keras-FasterRCNN with MIT License 5 votes vote down vote up 
def identity_block_td(input_tensor, kernel_size, filters, stage, block, trainable=True):

    # identity block time distributed

    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = TimeDistributed(Convolution2D(nb_filter1, (1, 1), trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '2a')(input_tensor)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter2, (kernel_size, kernel_size), trainable=trainable, kernel_initializer='normal',padding='same'), name=conv_name_base + '2b')(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter3, (1, 1), trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '2c')(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2c')(x)

    x = Add()([x, input_tensor])
    x = Activation('relu')(x)

    return x
Example #29
Source File: resnet.py    From FasterRCNN_KERAS with Apache License 2.0 5 votes vote down vote up 
def conv_block(input_tensor, kernel_size, filters, stage, block, strides=(2, 2), trainable=True):

    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = Convolution2D(nb_filter1, (1, 1), strides=strides, name=conv_name_base + '2a', trainable=trainable)(input_tensor)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter2, (kernel_size, kernel_size), padding='same', name=conv_name_base + '2b', trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = Convolution2D(nb_filter3, (1, 1), name=conv_name_base + '2c', trainable=trainable)(x)
    x = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)

    shortcut = Convolution2D(nb_filter3, (1, 1), strides=strides, name=conv_name_base + '1', trainable=trainable)(input_tensor)
    shortcut = FixedBatchNormalization(axis=bn_axis, name=bn_name_base + '1')(shortcut)

    x = Add()([x, shortcut])
    x = Activation('relu')(x)
    return x
Example #30
Source File: resnet.py    From Keras-FasterRCNN with MIT License 5 votes vote down vote up 
def conv_block_td(input_tensor, kernel_size, filters, stage, block, input_shape, strides=(2, 2), trainable=True):

    # conv block time distributed

    nb_filter1, nb_filter2, nb_filter3 = filters
    if K.image_dim_ordering() == 'tf':
        bn_axis = 3
    else:
        bn_axis = 1

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = TimeDistributed(Convolution2D(nb_filter1, (1, 1), strides=strides, trainable=trainable, kernel_initializer='normal'), input_shape=input_shape, name=conv_name_base + '2a')(input_tensor)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter2, (kernel_size, kernel_size), padding='same', trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '2b')(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = TimeDistributed(Convolution2D(nb_filter3, (1, 1), kernel_initializer='normal'), name=conv_name_base + '2c', trainable=trainable)(x)
    x = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '2c')(x)

    shortcut = TimeDistributed(Convolution2D(nb_filter3, (1, 1), strides=strides, trainable=trainable, kernel_initializer='normal'), name=conv_name_base + '1')(input_tensor)
    shortcut = TimeDistributed(FixedBatchNormalization(axis=bn_axis), name=bn_name_base + '1')(shortcut)

    x = Add()([x, shortcut])
    x = Activation('relu')(x)
    return x