Caffe2 - C++ API
A deep learning, cross platform ML framework
Public Member Functions
torch::nn::ConvOptions< D > Struct Template Referenceabstract

Options for a D-dimensional convolution module. More...

#include <conv.h>

Public Member Functions

 ConvOptions (int64_t input_channels, int64_t output_channels, ExpandingArray< D > kernel_size)
 
 TORCH_ARG (int64_t, input_channels)
 The number of channels the input volumes will have. More...
 
 TORCH_ARG (int64_t, output_channels)
 The number of output channels the convolution should produce. More...
 
 TORCH_ARG (ExpandingArray< D >, kernel_size)
 The kernel size to use. More...
 
 TORCH_ARG (ExpandingArray< D >, stride)
 The stride of the convolution. More...
 
 TORCH_ARG (ExpandingArray< D >, padding)=0
 The padding to add to the input volumes. More...
 
 TORCH_ARG (ExpandingArray< D >, dilation)
 The kernel dilation. More...
 
 TORCH_ARG (ExpandingArray< D >, output_padding)=0
 For transpose convolutions, the padding to add to output volumes. More...
 
 TORCH_ARG (bool, transposed)
 If true, convolutions will be transpose convolutions (a.k.a. More...
 
 TORCH_ARG (bool, with_bias)
 Whether to add a bias after individual applications of the kernel. More...
 
 TORCH_ARG (int64_t, groups)
 The number of convolution groups. More...
 

Detailed Description

template<size_t D>
struct torch::nn::ConvOptions< D >

Options for a D-dimensional convolution module.

Definition at line 16 of file conv.h.

Member Function Documentation

template<size_t D>
torch::nn::ConvOptions< D >::TORCH_ARG ( int64_t  ,
input_channels   
)

The number of channels the input volumes will have.

Changing this parameter after construction has no effect.

template<size_t D>
torch::nn::ConvOptions< D >::TORCH_ARG ( int64_t  ,
output_channels   
)

The number of output channels the convolution should produce.

Changing this parameter after construction has no effect.

template<size_t D>
torch::nn::ConvOptions< D >::TORCH_ARG ( ExpandingArray< D ,
kernel_size   
)

The kernel size to use.

For a D-dim convolution, must be a single number or a list of D numbers. This parameter can be changed after construction.

template<size_t D>
torch::nn::ConvOptions< D >::TORCH_ARG ( ExpandingArray< D ,
stride   
)

The stride of the convolution.

For a D-dim convolution, must be a single number or a list of D numbers. This parameter can be changed after construction.

template<size_t D>
torch::nn::ConvOptions< D >::TORCH_ARG ( ExpandingArray< D ,
padding   
)
pure virtual

The padding to add to the input volumes.

For a D-dim convolution, must be a single number or a list of D numbers. This parameter can be changed after construction.

template<size_t D>
torch::nn::ConvOptions< D >::TORCH_ARG ( ExpandingArray< D ,
dilation   
)

The kernel dilation.

For a D-dim convolution, must be a single number or a list of D numbers. This parameter can be changed after construction.

template<size_t D>
torch::nn::ConvOptions< D >::TORCH_ARG ( ExpandingArray< D ,
output_padding   
)
pure virtual

For transpose convolutions, the padding to add to output volumes.

For a D-dim convolution, must be a single number or a list of D numbers. This parameter can be changed after construction.

template<size_t D>
torch::nn::ConvOptions< D >::TORCH_ARG ( bool  ,
transposed   
)

If true, convolutions will be transpose convolutions (a.k.a.

deconvolutions). Changing this parameter after construction has no effect.

template<size_t D>
torch::nn::ConvOptions< D >::TORCH_ARG ( bool  ,
with_bias   
)

Whether to add a bias after individual applications of the kernel.

Changing this parameter after construction has no effect.

template<size_t D>
torch::nn::ConvOptions< D >::TORCH_ARG ( int64_t  ,
groups   
)

The number of convolution groups.

This parameter can be changed after construction.


The documentation for this struct was generated from the following file: