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

Inheritance diagram for nvinfer1::IConvolutionLayer:

Collaboration diagram for nvinfer1::IConvolutionLayer:

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

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

virtual void	setNbOutputMaps (int32_t nbOutputMaps)=0
	Set the number of output maps for the convolution. More...

virtual int32_t	getNbOutputMaps () const =0
	Get the number of output maps for the convolution. More...

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

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

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

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

virtual void	setNbGroups (int32_t nbGroups)=0
	Set the number of groups for a convolution. More...

virtual int32_t	getNbGroups () const =0
	Get the number of groups of the 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 of 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...

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

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

virtual void	setPrePadding (Dims padding)=0
	Set the multi-dimension pre-padding of the convolution. More...

virtual Dims	getPrePadding () const =0
	Get the pre-padding. More...

virtual void	setPostPadding (Dims padding)=0
	Set the multi-dimension post-padding of the convolution. More...

virtual Dims	getPostPadding () const =0
	Get the post-padding. More...

virtual void	setPaddingMode (PaddingMode paddingMode)=0
	Set the padding mode. More...

virtual PaddingMode	getPaddingMode () const =0
	Get the padding mode. More...

virtual void	setKernelSizeNd (Dims kernelSize)=0
	Set the multi-dimension kernel size of the convolution. More...

virtual Dims	getKernelSizeNd () const =0
	Get the multi-dimension kernel size of the convolution. More...

virtual void	setStrideNd (Dims stride)=0
	Set the multi-dimension stride of the convolution. More...

virtual Dims	getStrideNd () const =0
	Get the multi-dimension stride of the convolution. More...

virtual void	setPaddingNd (Dims padding)=0
	Set the multi-dimension padding of the convolution. More...

virtual Dims	getPaddingNd () const =0
	Get the multi-dimension padding of the convolution. More...

virtual void	setDilationNd (Dims dilation)=0
	Set the multi-dimension dilation of the convolution. More...

virtual Dims	getDilationNd () const =0
	Get the multi-dimension dilation of the convolution. More...

void	setInput (int32_t index, ITensor &tensor)=0
	Append or replace an input of this layer with a specific tensor. More...

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 int32_t	getNbInputs () const =0
	Get the number of inputs of a layer. More...

virtual ITensor *	getInput (int32_t index) const =0
	Get the layer input corresponding to the given index. More...

virtual int32_t	getNbOutputs () const =0
	Get the number of outputs of a layer. More...

virtual ITensor *	getOutput (int32_t index) const =0
	Get the layer output corresponding to the given index. More...

virtual void	setPrecision (DataType dataType)=0
	Set the computational precision of this layer. More...

virtual DataType	getPrecision () const =0
	get the computational precision of this layer More...

virtual bool	precisionIsSet () const =0
	whether the computational precision has been set for this layer More...

virtual void	resetPrecision ()=0
	reset the computational precision for this layer More...

virtual void	setOutputType (int32_t index, DataType dataType)=0
	Set the output type of this layer. More...

virtual DataType	getOutputType (int32_t index) const =0
	get the output type of this layer More...

virtual bool	outputTypeIsSet (int32_t index) const =0
	whether the output type has been set for this layer More...

virtual void	resetOutputType (int32_t index)=0
	reset the output type for this layer More...

Protected Member Functions
virtual	~IConvolutionLayer ()

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.

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

Warning: Do not inherit from this class, as doing so will break forward-compatibility of the API and ABI.

Constructor & Destructor Documentation

◆ ~IConvolutionLayer()

virtual nvinfer1::IConvolutionLayer::~IConvolutionLayer ( )

inlineprotectedvirtual

Member Function Documentation

◆ attribute() [1/8]

nvinfer1::IConvolutionLayer::__attribute__ ( (deprecated) )

pure virtual

Set the HW kernel size of the convolution.

If executing this layer on DLA, both height and width of kernel size must be in the range [1,32].

See also: getKernelSize()

Deprecated:: Superseded by setKernelSizeNd and will be removed in TensorRT 9.0.

◆ attribute() [2/8]

nvinfer1::IConvolutionLayer::__attribute__ ( (deprecated) ) const

pure virtual

Get the HW kernel size of the convolution.

See also: setKernelSize()

Deprecated:: Superseded by getKernelSizeNd and will be removed in TensorRT 9.0.

◆ setNbOutputMaps()

virtual void nvinfer1::IConvolutionLayer::setNbOutputMaps ( int32_t nbOutputMaps )

pure virtual

Set the number of output maps for the convolution.

If executing this layer on DLA, the number of output maps must be in the range [1,8192].

See also: getNbOutputMaps()

◆ getNbOutputMaps()

virtual int32_t nvinfer1::IConvolutionLayer::getNbOutputMaps ( ) const

pure virtual

Get the number of output maps for the convolution.

See also: setNbOutputMaps()

◆ attribute() [3/8]

nvinfer1::IConvolutionLayer::__attribute__ ( (deprecated) )

pure virtual

Get the stride of the convolution.

Default: (1,1)

If executing this layer on DLA, both height and width of stride must be in the range [1,8].

See also: getStride()

Deprecated:: Superseded by setStrideNd and will be removed in TensorRT 9.0.

◆ attribute() [4/8]

nvinfer1::IConvolutionLayer::__attribute__ ( (deprecated) ) const

pure virtual

Get the stride of the convolution.

Deprecated:: Superseded by getStrideNd and will be removed in TensorRT 9.0.

◆ attribute() [5/8]

nvinfer1::IConvolutionLayer::__attribute__ ( (deprecated) )

pure virtual

Set the padding of the convolution.

The input will be zero-padded by this number of elements in the height and width directions. Padding is symmetric.

Default: (0,0)

If executing this layer on DLA, both height and width of padding must be in the range [0,31], and the padding size must be less than the kernel size.

See also: getPadding()

Deprecated:: Superseded by setPaddingNd and will be removed in TensorRT 9.0.

◆ attribute() [6/8]

nvinfer1::IConvolutionLayer::__attribute__ ( (deprecated) ) const

pure virtual

Get the padding of the convolution.

If the padding is asymmetric, the pre-padding is returned.

See also: setPadding()

Deprecated:: Superseded by getPaddingNd and will be removed in TensorRT 9.0.

◆ setNbGroups()

virtual void nvinfer1::IConvolutionLayer::setNbGroups ( int32_t 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

If executing this layer on DLA, the max number of groups is 8192.

See also: getNbGroups()

◆ getNbGroups()

virtual int32_t nvinfer1::IConvolutionLayer::getNbGroups ( ) const

pure virtual

Get the number of groups of the convolution.

See also: setNbGroups()

◆ setKernelWeights()

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()

◆ getKernelWeights()

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

pure virtual

Get the kernel weights of the convolution.

See also: setKernelWeights()

◆ setBiasWeights()

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()

◆ getBiasWeights()

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

pure virtual

Get the bias weights for the convolution.

See also: setBiasWeights()

◆ attribute() [7/8]

nvinfer1::IConvolutionLayer::__attribute__ ( (deprecated) )

pure virtual

Set the dilation for a convolution.

Default: (1,1)

If executing this layer on DLA, both height and width must be in the range [1,32].

See also: getDilation()

Deprecated:: Superseded by setDilationNd and will be removed in TensorRT 9.0.

◆ attribute() [8/8]

nvinfer1::IConvolutionLayer::__attribute__ ( (deprecated) ) const

pure virtual

Get the dilation for a convolution.

See also: setDilation()

Deprecated:: Superseded by getDilationNd and will be removed in TensorRT 9.0.

◆ setPrePadding()

virtual void nvinfer1::IConvolutionLayer::setPrePadding ( Dims padding )

pure virtual

Set the multi-dimension pre-padding of the convolution.

The start of the input will be zero-padded by this number of elements in each dimension.

Default: (0, 0, ..., 0)

If executing this layer on DLA, only support 2D padding, both height and width of padding must be in the range [0,31], and the padding must be less than the kernel size.

See also: getPrePadding()

◆ getPrePadding()

virtual Dims nvinfer1::IConvolutionLayer::getPrePadding ( ) const

pure virtual

Get the pre-padding.

See also: setPrePadding()

◆ setPostPadding()

virtual void nvinfer1::IConvolutionLayer::setPostPadding ( Dims padding )

pure virtual

Set the multi-dimension post-padding of the convolution.

The end of the input will be zero-padded by this number of elements in each dimension.

Default: (0, 0, ..., 0)

If executing this layer on DLA, only support 2D padding, both height and width of padding must be in the range [0,31], and the padding must be less than the kernel size.

See also: getPostPadding()

◆ getPostPadding()

virtual Dims nvinfer1::IConvolutionLayer::getPostPadding ( ) const

pure virtual

Get the post-padding.

See also: setPostPadding()

◆ setPaddingMode()

virtual void nvinfer1::IConvolutionLayer::setPaddingMode ( PaddingMode paddingMode )

pure virtual

Set the padding mode.

Padding mode takes precedence if both setPaddingMode and setPre/PostPadding are used.

Default: kEXPLICIT_ROUND_DOWN

See also: getPaddingMode()

◆ getPaddingMode()

virtual PaddingMode nvinfer1::IConvolutionLayer::getPaddingMode ( ) const

pure virtual

Get the padding mode.

Default: kEXPLICIT_ROUND_DOWN

See also: setPaddingMode()

◆ setKernelSizeNd()

virtual void nvinfer1::IConvolutionLayer::setKernelSizeNd ( Dims kernelSize )

pure virtual

Set the multi-dimension kernel size of the convolution.

If executing this layer on DLA, only support 2D kernel size, both height and width of kernel size must be in the range [1,32].

See also: getKernelSizeNd()

◆ getKernelSizeNd()

virtual Dims nvinfer1::IConvolutionLayer::getKernelSizeNd ( ) const

pure virtual

Get the multi-dimension kernel size of the convolution.

See also: setKernelSizeNd()

◆ setStrideNd()

virtual void nvinfer1::IConvolutionLayer::setStrideNd ( Dims stride )

pure virtual

Set the multi-dimension stride of the convolution.

Default: (1, 1, ..., 1)

If executing this layer on DLA, only support 2D stride, both height and width of stride must be in the range [1,8].

See also: getStrideNd() setStride() getStride()

◆ getStrideNd()

virtual Dims nvinfer1::IConvolutionLayer::getStrideNd ( ) const

pure virtual

Get the multi-dimension stride of the convolution.

See also: setStrideNd()

◆ setPaddingNd()

virtual void nvinfer1::IConvolutionLayer::setPaddingNd ( Dims padding )

pure virtual

Set the multi-dimension padding of the convolution.

The input will be zero-padded by this number of elements in each dimension. Padding is symmetric.

Default: (0, 0, ..., 0)

If executing this layer on DLA, only support 2D padding, both height and width of padding must be in the range [0,31], and the padding must be less than the kernel size.

See also: getPaddingNd() setPadding() getPadding()

◆ getPaddingNd()

virtual Dims nvinfer1::IConvolutionLayer::getPaddingNd ( ) const

pure virtual

Get the multi-dimension padding of the convolution.

If the padding is asymmetric, the pre-padding is returned.

See also: setPaddingNd()

◆ setDilationNd()

virtual void nvinfer1::IConvolutionLayer::setDilationNd ( Dims dilation )

pure virtual

Set the multi-dimension dilation of the convolution.

Default: (1, 1, ..., 1)

If executing this layer on DLA, only support 2D padding, both height and width must be in the range [1,32].

See also: getDilation()

◆ getDilationNd()

virtual Dims nvinfer1::IConvolutionLayer::getDilationNd ( ) const

pure virtual

Get the multi-dimension dilation of the convolution.

See also: setDilation()

◆ setInput()

void nvinfer1::IConvolutionLayer::setInput	(	int32_t	index,
		ITensor &	tensor
	)

pure virtual

Append or replace an input of this layer with a specific tensor.

Parameters

index	the index of the input to modify.
tensor	the new input tensor

For a IConvolutionLayer, only index 0 is valid unless explicit precision mode is enabled. With explicit precision mode, values 0-1 are valid where value 1 overrides kernel weights. Kernel weights tensor (computed at build-time) must be an output of dequantize scale layer (i.e. a scale layer with int8 input and float output) in explicit precision network. Conversely, this input tensor can be overridden via appropriate set call.

The indices are as follows:

0: The input activation tensor.
1: The kernel weights tensor (a constant tensor).

If this function is called with a value greater than 0, then the function getNbInputs() changes

Implements nvinfer1::ILayer.

◆ getType()

virtual LayerType nvinfer1::ILayer::getType ( ) const

pure virtualinherited

Return the type of a layer.

See also: LayerType

◆ setName()

virtual void nvinfer1::ILayer::setName ( const char * name )

pure virtualinherited

Set the name of a layer.

This method copies the name string.

See also: getName()

Here is the caller graph for this function:

◆ getName()

virtual const char* nvinfer1::ILayer::getName ( ) const

pure virtualinherited

Return the name of a layer.

See also: setName()

Here is the caller graph for this function:

◆ getNbInputs()

virtual int32_t nvinfer1::ILayer::getNbInputs ( ) const

pure virtualinherited

Get the number of inputs of a layer.

◆ getInput()

virtual ITensor* nvinfer1::ILayer::getInput ( int32_t index ) const

pure virtualinherited

Get the layer input corresponding to the given index.

Parameters

index The index of the input tensor.

Returns: The input tensor, or nullptr if the index is out of range or the tensor is optional (ISliceLayer, IRNNLayer and IRNNv2Layer).

◆ getNbOutputs()

virtual int32_t nvinfer1::ILayer::getNbOutputs ( ) const

pure virtualinherited

Get the number of outputs of a layer.

Here is the caller graph for this function:

◆ getOutput()

virtual ITensor* nvinfer1::ILayer::getOutput ( int32_t index ) const

pure virtualinherited

Get the layer output corresponding to the given index.

Returns: The indexed output tensor, or nullptr if the index is out of range or the tensor is optional (IRNNLayer and IRNNv2Layer).

Here is the caller graph for this function:

◆ setPrecision()

virtual void nvinfer1::ILayer::setPrecision ( DataType dataType )

pure virtualinherited

Set the computational precision of this layer.

Setting the precision allows TensorRT to choose implementation which run at this computational precision. Layer input type would also get inferred from layer computational precision. TensorRT could still choose a non-conforming fastest implementation ignoring set layer precision. Use BuilderFlag::kSTRICT_TYPES to force choose implementations with requested precision. In case no implementation is found with requested precision, TensorRT would choose available fastest implementation. If precision is not set, TensorRT will select the layer computational precision and layer input type based on performance considerations and the flags specified to the builder.

Parameters

precision the computational precision.

See also: getPrecision() precisionIsSet() resetPrecision()

◆ getPrecision()

virtual DataType nvinfer1::ILayer::getPrecision ( ) const

pure virtualinherited

get the computational precision of this layer

Returns: the computational precision

See also: setPrecision() precisionIsSet() resetPrecision()

◆ precisionIsSet()

virtual bool nvinfer1::ILayer::precisionIsSet ( ) const

pure virtualinherited

whether the computational precision has been set for this layer

Returns: whether the computational precision has been explicitly set

See also: setPrecision() getPrecision() resetPrecision()

◆ resetPrecision()

virtual void nvinfer1::ILayer::resetPrecision ( )

pure virtualinherited

reset the computational precision for this layer

See also: setPrecision() getPrecision() precisionIsSet()

◆ setOutputType()

virtual void nvinfer1::ILayer::setOutputType	(	int32_t	index,
		DataType	dataType
	)

pure virtualinherited

Set the output type of this layer.

Setting the output type constrains TensorRT to choose implementations which generate output data with the given type. If it is not set, TensorRT will select output type based on layer computational precision. TensorRT could still choose non-conforming output type based on fastest implementation. Use BuilderFlag::kSTRICT_TYPES to force choose requested output type. In case layer precision is not specified, output type would depend on chosen implementation based on performance considerations and the flags specified to the builder.

This method cannot be used to set the data type of the second output tensor of the TopK layer. The data type of the second output tensor of the topK layer is always Int32. Also the output type of all layers that are shape operations must be DataType::kINT32, and all attempts to set the output type to some other data type will be ignored except for issuing an error message.

Note that the layer output type is generally not identical to the data type of the output tensor, as TensorRT may insert implicit reformatting operations to convert the former to the latter. Calling layer->setOutputType(i, type) has no effect on the data type of the i-th output tensor of layer, and users need to call layer->getOutput(i)->setType(type) to change the tensor data type. This is particularly relevant if the tensor is marked as a network output, since only setType() [but not setOutputType()] will affect the data representation in the corresponding output binding.

Parameters

index	the index of the output to set
dataType	the type of the output

See also: getOutputType() outputTypeIsSet() resetOutputType()

◆ getOutputType()

virtual DataType nvinfer1::ILayer::getOutputType ( int32_t index ) const

pure virtualinherited

get the output type of this layer

Parameters

index the index of the output

Returns: the output precision. If no precision has been set, DataType::kFLOAT will be returned, unless the output type is inherently DataType::kINT32.

See also: getOutputType() outputTypeIsSet() resetOutputType()

◆ outputTypeIsSet()

virtual bool nvinfer1::ILayer::outputTypeIsSet ( int32_t index ) const

pure virtualinherited

whether the output type has been set for this layer

Parameters

index the index of the output

Returns: whether the output type has been explicitly set

See also: setOutputType() getOutputType() resetOutputType()

◆ resetOutputType()

virtual void nvinfer1::ILayer::resetOutputType ( int32_t index )

pure virtualinherited

reset the output type for this layer

Parameters

index the index of the output

See also: setOutputType() getOutputType() outputTypeIsSet()

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

NvInfer.h

Public Member Functions

Protected Member Functions

Detailed Description

Constructor & Destructor Documentation

◆ ~IConvolutionLayer()

Member Function Documentation

◆ __attribute__() [1/8]

◆ __attribute__() [2/8]

◆ setNbOutputMaps()

◆ getNbOutputMaps()

◆ __attribute__() [3/8]

◆ __attribute__() [4/8]

◆ __attribute__() [5/8]

◆ __attribute__() [6/8]

◆ setNbGroups()

◆ getNbGroups()

◆ setKernelWeights()

◆ getKernelWeights()

◆ setBiasWeights()

◆ getBiasWeights()

◆ __attribute__() [7/8]

◆ __attribute__() [8/8]

◆ setPrePadding()

◆ getPrePadding()

◆ setPostPadding()

◆ getPostPadding()

◆ setPaddingMode()

◆ getPaddingMode()

◆ setKernelSizeNd()

◆ getKernelSizeNd()

◆ setStrideNd()

◆ getStrideNd()

◆ setPaddingNd()

◆ getPaddingNd()

◆ setDilationNd()

◆ getDilationNd()

◆ setInput()

◆ getType()

◆ setName()

◆ getName()

◆ getNbInputs()

◆ getInput()

◆ getNbOutputs()

◆ getOutput()

◆ setPrecision()

◆ getPrecision()

◆ precisionIsSet()

◆ resetPrecision()

◆ setOutputType()

◆ getOutputType()

◆ outputTypeIsSet()

◆ resetOutputType()

◆ attribute() [1/8]

◆ attribute() [2/8]

◆ attribute() [3/8]

◆ attribute() [4/8]

◆ attribute() [5/8]

◆ attribute() [6/8]

◆ attribute() [7/8]

◆ attribute() [8/8]