dlpy.blocks.ResBlock_Caffe

class dlpy.blocks.ResBlock_Caffe(kernel_sizes=3, n_filters=(16, 16), strides=None, batch_norm_first=False, conv_short_cut=False)

Bases: dlpy.blocks.ResBlock

Residual block for Residual Network with batch normalization.

Parameters:

kernel_sizes : iter-of-ints, optional

Kernel size of the convolution filters.
Default: 3

n_filters : iter-of-ints, optional

List of numbers of filter in each convolution layers.
Default: (16, 16)

strides : iter-of-ints, optional

List of stride in each convolution layers.

batch_norm_first : bool, optional

Specify whether to add batch normal layer before conv layer.
Default: False

conv_short_cut : bool, optional

Set to True, if there is short cut in the convolution layer
Default: False

Returns:

ResBlock_Caffe

__init__(kernel_sizes=3, n_filters=(16, 16), strides=None, batch_norm_first=False, conv_short_cut=False)

Initialize self. See help(type(self)) for accurate signature.

Methods

__init__([kernel_sizes, n_filters, strides, …])	Initialize self.
add_layers()	Add the layers for the block
compile(src_layer[, block_num])	Compile the block structure into DLPy layer definitions.
count_instances()
get_number_of_instances()