A convolution layer in a network definition. More...

#include <NvInfer.h>

Inheritance diagram for nvinfer1::IConvolutionLayer:

Public Member Functions
virtual void	setKernelSize (DimsHW kernelSize)=0
	Set the HW kernel size of the convolution. More...

virtual DimsHW	getKernelSize () const =0
	Get the HW kernel size of the convolution. More...

virtual void	setNbOutputMaps (int nbOutputMaps)=0
	Set the number of output maps for the convolution. More...

virtual int	getNbOutputMaps () const =0
	Get the number of output maps for the convolution. More...

virtual void	setStride (DimsHW stride)=0
	Get the stride of the convolution. More...

virtual DimsHW	getStride () const =0
	Get the stride of the convolution.

virtual void	setPadding (DimsHW padding)=0
	Set the padding of the convolution. More...

virtual DimsHW	getPadding () const =0
	Get the padding of the convolution. More...

virtual void	setNbGroups (int nbGroups)=0
	Set the number of groups for a convolution. More...

virtual int	getNbGroups () const =0
	Set the number of groups for a convolution. More...

virtual void	setKernelWeights (Weights weights)=0
	Set the kernel weights for the convolution. More...

virtual Weights	getKernelWeights () const =0
	Get the kernel weights for the convolution. More...

virtual void	setBiasWeights (Weights weights)=0
	Set the bias weights for the convolution. More...

virtual Weights	getBiasWeights () const =0
	Get the bias weights for the convolution. More...

virtual void	setDilation (DimsHW dims)=0
	Set the dilation for a convolution. More...

virtual DimsHW	getDilation () const =0
	Get the dilation for a convolution. More...

Public Member Functions inherited from nvinfer1::ILayer
virtual LayerType	getType () const =0
	Return the type of a layer. More...

virtual void	setName (const char *name)=0
	Set the name of a layer. More...

virtual const char *	getName () const =0
	Return the name of a layer. More...

virtual int	getNbInputs () const =0
	Get the number of inputs of a layer.

virtual ITensor *	getInput (int index) const =0
	Get the layer input corresponding to the given index. More...

virtual int	getNbOutputs () const =0
	Get the number of outputs of a layer.

virtual ITensor *	getOutput (int index) const =0
	Get the layer output corresponding to the given index. More...

Detailed Description

A convolution layer in a network definition.

This layer performs a correlation operation between 3-dimensional filter with a 4-dimensional tensor to produce another 4-dimensional tensor.

The HW output size of the convolution is set according to the INetworkCustomDimensions set in INetworkDefinition::setCustomConvolutionDimensions().

An optional bias argument is supported, which adds a per-channel constant to each value in the output.

Member Function Documentation

virtual Weights nvinfer1::IConvolutionLayer::getBiasWeights ( ) const

pure virtual

Get the bias weights for the convolution.

See Also: setBiasWeights()

virtual DimsHW nvinfer1::IConvolutionLayer::getDilation ( ) const

pure virtual

Get the dilation for a convolution.

See Also: setDilation()

virtual DimsHW nvinfer1::IConvolutionLayer::getKernelSize ( ) const

pure virtual

Get the HW kernel size of the convolution.

See Also: setKernelSize()

virtual Weights nvinfer1::IConvolutionLayer::getKernelWeights ( ) const

pure virtual

Get the kernel weights for the convolution.

See Also: setKernelWeights()

virtual int nvinfer1::IConvolutionLayer::getNbGroups ( ) const

pure virtual

Set the number of groups for a convolution.

See Also: setNbGroups()

virtual int nvinfer1::IConvolutionLayer::getNbOutputMaps ( ) const

pure virtual

Get the number of output maps for the convolution.

See Also: setNbOutputMaps()

virtual DimsHW nvinfer1::IConvolutionLayer::getPadding ( ) const

pure virtual

Get the padding of the convolution.

See Also: setPadding()

virtual void nvinfer1::IConvolutionLayer::setBiasWeights ( Weights weights )

pure virtual

Set the bias weights for the convolution.

Bias is optional. To omit bias, set the count value of the weights structure to zero.

The bias is applied per-channel, so the number of weights (if non-zero) must be equal to the number of output feature maps.

See Also: getBiasWeights()

virtual void nvinfer1::IConvolutionLayer::setDilation ( DimsHW dims )

pure virtual

Set the dilation for a convolution.

Default: (1,1)

See Also: getDilation()

virtual void nvinfer1::IConvolutionLayer::setKernelSize ( DimsHW kernelSize )

pure virtual

Set the HW kernel size of the convolution.

See Also: getKernelSize()

virtual void nvinfer1::IConvolutionLayer::setKernelWeights ( Weights weights )

pure virtual

Set the kernel weights for the convolution.

The weights are specified as a contiguous array in GKCRS order, where G is the number of groups, K the number of output feature maps, C the number of input channels, and R and S are the height and width of the filter.

See Also: getKernelWeights()

virtual void nvinfer1::IConvolutionLayer::setNbGroups ( int nbGroups )

pure virtual

Set the number of groups for a convolution.

The input tensor channels are divided into nbGroups groups, and a convolution is executed for each group, using a filter per group. The results of the group convolutions are concatenated to form the output.

Note: When using groups in int8 mode, the size of the groups (i.e. the channel count divided by the group count) must be a multiple of 4 for both input and output.

Default: 1