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

#include <NvInfer.h>

Inheritance diagram for nvinfer1::IPoolingLayer:

Public Member Functions
virtual void	setPoolingType (PoolingType type)=0
	Set the type of activation to be performed. More...

virtual PoolingType	getPoolingType () const =0
	Get the type of activation to be performed. More...

virtual void	setWindowSize (DimsHW windowSize)=0
	Set the window size for pooling. More...

virtual DimsHW	getWindowSize () const =0
	Get the window size for pooling. More...

virtual void	setStride (DimsHW stride)=0
	Set the stride for pooling. More...

virtual DimsHW	getStride () const =0
	Get the stride for pooling. More...

virtual void	setPadding (DimsHW padding)=0
	Set the padding for pooling. More...

virtual DimsHW	getPadding () const =0
	Get the padding for pooling. More...

virtual void	setBlendFactor (float blendFactor)=0
	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...

virtual float	getBlendFactor () const =0
	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...

virtual void	setAverageCountExcludesPadding (bool exclusive)=0
	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...

virtual bool	getAverageCountExcludesPadding () const =0
	Get whether exclusive pooling uses as a denominator the overlap area betwen the window and the unpadded input. More...

virtual void	setPrePadding (Dims padding)=0
	Set the pre-padding. More...

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

virtual void	setPostPadding (Dims padding)=0
	Set the post-padding. More...

virtual Dims	getPostPadding () const =0
	Get the 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	setWindowSizeNd (Dims windowSize)=0
	Set the multi-dimension window size for pooling. More...

virtual Dims	getWindowSizeNd () const =0
	Get the multi-dimension window size for pooling. More...

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

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

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

virtual Dims	getPaddingNd () const =0
	Get the multi-dimension padding for pooling. 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...

virtual void	setInput (int index, ITensor &tensor)=0
	replace an input of this layer with a specific tensor 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 (int index, DataType dataType)=0
	Set the output type of this layer. More...

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

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

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

Detailed Description

A Pooling layer in a network definition.

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

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

Member Function Documentation

◆ getAverageCountExcludesPadding()

virtual bool nvinfer1::IPoolingLayer::getAverageCountExcludesPadding ( ) const

pure virtual

Get whether exclusive pooling uses as a denominator the overlap area betwen the window and the unpadded input.

See also: setAverageCountExcludesPadding()

◆ getBlendFactor()

virtual float nvinfer1::IPoolingLayer::getBlendFactor ( ) const

pure virtual

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()

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

pure virtual

Get the padding for pooling.

Default: 0

See also: setPadding()

◆ getPaddingMode()

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

pure virtual

Get the padding mode.

Default: kEXPLICIT_ROUND_DOWN

See also: setPaddingMode()

◆ getPaddingNd()

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

pure virtual

Get the multi-dimension padding for pooling.

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

See also: setPaddingNd()

◆ getPoolingType()

virtual PoolingType nvinfer1::IPoolingLayer::getPoolingType ( ) const

pure virtual

Get the type of activation to be performed.

See also: setPoolingType(), PoolingType

◆ getPostPadding()

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

pure virtual

Get the padding.

See also: setPadding()

◆ getPrePadding()

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

pure virtual

Get the pre-padding.

See also: setPrePadding()

◆ getStride()

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

pure virtual

Get the stride for pooling.

See also: setStride()

◆ getStrideNd()

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

pure virtual

Get the multi-dimension stride for pooling.

See also: setStrideNd()

◆ getWindowSize()

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

pure virtual

Get the window size for pooling.

See also: setWindowSize()

◆ getWindowSizeNd()

virtual Dims nvinfer1::IPoolingLayer::getWindowSizeNd ( ) const

pure virtual

Get the multi-dimension window size for pooling.

See also: setWindowSizeNd()

◆ setAverageCountExcludesPadding()

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

pure virtual

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

See also: getAverageCountExcludesPadding()

◆ setBlendFactor()

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

pure virtual

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.

See also: getBlendFactor()

◆ setPadding()

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

pure virtual

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()

◆ setPaddingMode()

virtual void nvinfer1::IPoolingLayer::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()

◆ setPaddingNd()

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

pure virtual

Set the multi-dimension padding for pooling.

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 [0,7].

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

◆ setPoolingType()

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

pure virtual

Set the type of activation to be performed.

DLA only supports kMAX and kAVERAGE.

See also: getPoolingType(), PoolingType

◆ setPostPadding()

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

pure virtual

Set the post-padding.

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

Default: (0,0)

If executing this layer on DLA, both height and width of padding must be in the range [0,15].

See also: getPadding()

◆ setPrePadding()

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

pure virtual

Set the pre-padding.

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

Default: 0

If executing this layer on DLA, both height and width of padding must be in the range [0,15].

See also: getPadding()

◆ setStride()

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

pure virtual

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()

◆ setStrideNd()

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

pure virtual

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()

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

pure virtual

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()

◆ setWindowSizeNd()

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

pure virtual

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

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()