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)¶ Residual block for Residual Network with batch normalization.
- Parameters
- kernel_sizesiter-of-ints, optional
Kernel size of the convolution filters. Default: 3
- n_filtersiter-of-ints, optional
List of numbers of filter in each convolution layers. Default: (16, 16)
- stridesiter-of-ints, optional
List of stride in each convolution layers.
- batch_norm_firstbool, optional
Specify whether to add batch normal layer before conv layer. Default: False
- conv_short_cutbool, optional
Set to True, if there is short cut in the convolution layer Default: False
- Returns
-
__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
()Attributes
can_be_last_layer
number_of_instances
type
type_desc