torch::nn::ConvOptions< D > Struct Template Reference

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:

• torch/csrc/api/include/torch/nn/modules/conv.h