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

#include <NvInfer.h>

Inheritance diagram for nvinfer1::IPoolingLayer:

Public Member Functions
void	setPoolingType (PoolingType type) noexcept
	Set the type of activation to be performed. More...

PoolingType	getPoolingType () const noexcept
	Get the type of activation to be performed. More...

TRT_DEPRECATED void	setWindowSize (DimsHW windowSize) noexcept
	Set the window size for pooling. More...

TRT_DEPRECATED DimsHW	getWindowSize () const noexcept
	Get the window size for pooling. More...

TRT_DEPRECATED void	setStride (DimsHW stride) noexcept
	Set the stride for pooling. More...

TRT_DEPRECATED DimsHW	getStride () const noexcept
	Get the stride for pooling. More...

TRT_DEPRECATED void	setPadding (DimsHW padding) noexcept
	Set the padding for pooling. More...

TRT_DEPRECATED DimsHW	getPadding () const noexcept
	Get the padding for pooling. More...

void	setBlendFactor (float blendFactor) noexcept
	Set the blending factor for the max_average_blend mode: max_average_blendPool = (1-blendFactor)maxPool + blendFactoravgPool blendFactor is a user value in [0,1] with the default value of 0.0 This value only applies for the kMAX_AVERAGE_BLEND mode. More...

float	getBlendFactor () const noexcept
	Get the blending factor for the max_average_blend mode: max_average_blendPool = (1-blendFactor)maxPool + blendFactoravgPool blendFactor is a user value in [0,1] with the default value of 0.0 In modes other than kMAX_AVERAGE_BLEND, blendFactor is ignored. More...

void	setAverageCountExcludesPadding (bool exclusive) noexcept
	Set whether average pooling uses as a denominator the overlap area between the window and the unpadded input. If this is not set, the denominator is the overlap between the pooling window and the padded input. More...

bool	getAverageCountExcludesPadding () const noexcept
	Get whether average pooling uses as a denominator the overlap area between the window and the unpadded input. More...

void	setPrePadding (Dims padding) noexcept
	Set the multi-dimension pre-padding for pooling. More...

Dims	getPrePadding () const noexcept
	Get the pre-padding. More...

void	setPostPadding (Dims padding) noexcept
	Set the multi-dimension post-padding for pooling. More...

Dims	getPostPadding () const noexcept
	Get the padding. More...

void	setPaddingMode (PaddingMode paddingMode) noexcept
	Set the padding mode. More...

PaddingMode	getPaddingMode () const noexcept
	Get the padding mode. More...

void	setWindowSizeNd (Dims windowSize) noexcept
	Set the multi-dimension window size for pooling. More...

Dims	getWindowSizeNd () const noexcept
	Get the multi-dimension window size for pooling. More...

void	setStrideNd (Dims stride) noexcept
	Set the multi-dimension stride for pooling. More...

Dims	getStrideNd () const noexcept
	Get the multi-dimension stride for pooling. More...

void	setPaddingNd (Dims padding) noexcept
	Set the multi-dimension padding for pooling. More...

Dims	getPaddingNd () const noexcept
	Get the multi-dimension padding for pooling. More...

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

void	setName (const char *name) noexcept
	Set the name of a layer. More...

const char *	getName () const noexcept
	Return the name of a layer. More...

int32_t	getNbInputs () const noexcept
	Get the number of inputs of a layer.

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

int32_t	getNbOutputs () const noexcept
	Get the number of outputs of a layer.

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

void	setInput (int32_t index, ITensor &tensor) noexcept
	Replace an input of this layer with a specific tensor. More...

void	setPrecision (DataType dataType) noexcept
	Set the computational precision of this layer. More...

DataType	getPrecision () const noexcept
	get the computational precision of this layer More...

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

void	resetPrecision () noexcept
	reset the computational precision for this layer More...

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

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

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

void	resetOutputType (int32_t index) noexcept
	reset the output type for this layer More...

Protected Attributes
apiv::VPoolingLayer *	mImpl

Protected Attributes inherited from nvinfer1::ILayer
apiv::VLayer *	mLayer

Additional Inherited Members
Protected Member Functions inherited from nvinfer1::INoCopy
	INoCopy (const INoCopy &other)=delete

INoCopy &	operator= (const INoCopy &other)=delete

	INoCopy (INoCopy &&other)=delete

INoCopy &	operator= (INoCopy &&other)=delete

Detailed Description

A Pooling layer in a network definition.

The layer applies a reduction operation within a window over the input.

Warning: When running pooling layer with DeviceType::kDLA in Int8 mode, the dynamic ranges for input and output tensors must be equal.; Do not inherit from this class, as doing so will break forward-compatibility of the API and ABI.

Member Function Documentation

◆ getAverageCountExcludesPadding()

bool nvinfer1::IPoolingLayer::getAverageCountExcludesPadding ( ) const

inlinenoexcept

Get whether average pooling uses as a denominator the overlap area between the window and the unpadded input.

See also: setAverageCountExcludesPadding()

◆ getBlendFactor()

float nvinfer1::IPoolingLayer::getBlendFactor ( ) const

inlinenoexcept

Get the blending factor for the max_average_blend mode: max_average_blendPool = (1-blendFactor)*maxPool + blendFactor*avgPool blendFactor is a user value in [0,1] with the default value of 0.0 In modes other than kMAX_AVERAGE_BLEND, blendFactor is ignored.

See also: setBlendFactor()

◆ getPadding()

TRT_DEPRECATED DimsHW nvinfer1::IPoolingLayer::getPadding ( ) const

inlinenoexcept

Get the padding for pooling.

Default: 0

See also: setPadding()

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

◆ getPaddingMode()

PaddingMode nvinfer1::IPoolingLayer::getPaddingMode ( ) const

inlinenoexcept

Get the padding mode.

Default: kEXPLICIT_ROUND_DOWN

See also: setPaddingMode()

◆ getPaddingNd()

Dims nvinfer1::IPoolingLayer::getPaddingNd ( ) const

inlinenoexcept

Get the multi-dimension padding for pooling.

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

See also: setPaddingNd()

◆ getPoolingType()

PoolingType nvinfer1::IPoolingLayer::getPoolingType ( ) const

inlinenoexcept

Get the type of activation to be performed.

See also: setPoolingType(), PoolingType

◆ getPostPadding()

Dims nvinfer1::IPoolingLayer::getPostPadding ( ) const

inlinenoexcept

Get the padding.

See also: setPostPadding()

◆ getPrePadding()

Dims nvinfer1::IPoolingLayer::getPrePadding ( ) const

inlinenoexcept

Get the pre-padding.

See also: setPrePadding()

◆ getStride()

TRT_DEPRECATED DimsHW nvinfer1::IPoolingLayer::getStride ( ) const

inlinenoexcept

Get the stride for pooling.

See also: setStride()

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

◆ getStrideNd()

Dims nvinfer1::IPoolingLayer::getStrideNd ( ) const

inlinenoexcept

Get the multi-dimension stride for pooling.

See also: setStrideNd()

◆ getWindowSize()

TRT_DEPRECATED DimsHW nvinfer1::IPoolingLayer::getWindowSize ( ) const

inlinenoexcept

Get the window size for pooling.

See also: setWindowSize()

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

◆ getWindowSizeNd()

Dims nvinfer1::IPoolingLayer::getWindowSizeNd ( ) const

inlinenoexcept

Get the multi-dimension window size for pooling.

See also: setWindowSizeNd()

◆ setAverageCountExcludesPadding()

void nvinfer1::IPoolingLayer::setAverageCountExcludesPadding ( bool exclusive )

inlinenoexcept

Set whether average pooling uses as a denominator the overlap area between the window and the unpadded input. If this is not set, the denominator is the overlap between the pooling window and the padded input.

Default: true

Note: DLA supports only inclusive padding, and thus when executing this layer on DLA, this must be explicitly set to false.

See also: getAverageCountExcludesPadding()

◆ setBlendFactor()

void nvinfer1::IPoolingLayer::setBlendFactor ( float blendFactor )

inlinenoexcept

Set the blending factor for the max_average_blend mode: max_average_blendPool = (1-blendFactor)*maxPool + blendFactor*avgPool blendFactor is a user value in [0,1] with the default value of 0.0 This value only applies for the kMAX_AVERAGE_BLEND mode.

Since DLA does not support kMAX_AVERAGE_BLEND, blendFactor is ignored on the DLA.

See also: getBlendFactor()

◆ setPadding()

TRT_DEPRECATED void nvinfer1::IPoolingLayer::setPadding ( DimsHW padding )

inlinenoexcept

Set the padding for pooling.

Default: 0

If executing this layer on DLA, both height and width of padding must be in the range [0,7].

See also: getPadding()

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

◆ setPaddingMode()

void nvinfer1::IPoolingLayer::setPaddingMode ( PaddingMode paddingMode )

inlinenoexcept

Set the padding mode.

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

Default: kEXPLICIT_ROUND_DOWN

See also: getPaddingMode()

◆ setPaddingNd()

void nvinfer1::IPoolingLayer::setPaddingNd ( Dims padding )

inlinenoexcept

Set the multi-dimension padding for pooling.

The input will be padded by this number of elements in each dimension. Padding is symmetric. Padding value depends on pooling type, -inf is used for max pooling and zero padding for average pooling.

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 [0,7].

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

◆ setPoolingType()

void nvinfer1::IPoolingLayer::setPoolingType ( PoolingType type )

inlinenoexcept

Set the type of activation to be performed.

DLA only supports kMAX and kAVERAGE pooling types.

See also: getPoolingType(), PoolingType

◆ setPostPadding()

void nvinfer1::IPoolingLayer::setPostPadding ( Dims padding )

inlinenoexcept

Set the multi-dimension post-padding for pooling.

The end of the input will be padded by this number of elements in each dimension. Padding value depends on pooling type, -inf is used for max pooling and zero padding for average pooling.

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 [0,7].

See also: getPostPadding()

◆ setPrePadding()

void nvinfer1::IPoolingLayer::setPrePadding ( Dims padding )

inlinenoexcept

Set the multi-dimension pre-padding for pooling.

The start of the input will be padded by this number of elements in each dimension. Padding value depends on pooling type, -inf is used for max pooling and zero padding for average pooling.

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 [0,7].

See also: getPrePadding()

◆ setStride()

TRT_DEPRECATED void nvinfer1::IPoolingLayer::setStride ( DimsHW stride )

inlinenoexcept

Set the stride for pooling.

Default: 1

If executing this layer on DLA, both height and width of stride must be in the range [1,16].

See also: getStride()

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

◆ setStrideNd()

void nvinfer1::IPoolingLayer::setStrideNd ( Dims stride )

inlinenoexcept

Set the multi-dimension stride for pooling.

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 [1,16].

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

◆ setWindowSize()

TRT_DEPRECATED void nvinfer1::IPoolingLayer::setWindowSize ( DimsHW windowSize )

inlinenoexcept

Set the window size for pooling.

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

See also: getWindowSize()

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

◆ setWindowSizeNd()

void nvinfer1::IPoolingLayer::setWindowSizeNd ( Dims windowSize )

inlinenoexcept

Set the multi-dimension window size for pooling.

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

See also: getWindowSizeNd() setWindowSize() getWindowSize()

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

NvInfer.h

Public Member Functions

Protected Attributes

Additional Inherited Members

Detailed Description

Member Function Documentation

◆ getAverageCountExcludesPadding()

◆ getBlendFactor()

◆ getPadding()

◆ getPaddingMode()

◆ getPaddingNd()

◆ getPoolingType()

◆ getPostPadding()

◆ getPrePadding()

◆ getStride()

◆ getStrideNd()

◆ getWindowSize()

◆ getWindowSizeNd()

◆ setAverageCountExcludesPadding()

◆ setBlendFactor()

◆ setPadding()

◆ setPaddingMode()

◆ setPaddingNd()

◆ setPoolingType()

◆ setPostPadding()

◆ setPrePadding()

◆ setStride()

◆ setStrideNd()

◆ setWindowSize()

◆ setWindowSizeNd()