TensorRT  6.0.0.6
nvinfer1::IConvolutionLayer Class Referenceabstract

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

#include <NvInfer.h>

Inheritance diagram for nvinfer1::IConvolutionLayer:
nvinfer1::ILayer

Public Member Functions

virtual void setKernelSize (DimsHW kernelSize) TRTNOEXCEPT=0
 Set the HW kernel size of the convolution. More...
 
virtual DimsHW getKernelSize () const TRTNOEXCEPT=0
 Get the HW kernel size of the convolution. More...
 
virtual void setNbOutputMaps (int nbOutputMaps) TRTNOEXCEPT=0
 Set the number of output maps for the convolution. More...
 
virtual int getNbOutputMaps () const TRTNOEXCEPT=0
 Get the number of output maps for the convolution. More...
 
virtual void setStride (DimsHW stride) TRTNOEXCEPT=0
 Get the stride of the convolution. More...
 
virtual DimsHW getStride () const TRTNOEXCEPT=0
 Get the stride of the convolution.
 
virtual void setPadding (DimsHW padding) TRTNOEXCEPT=0
 Set the padding of the convolution. More...
 
virtual DimsHW getPadding () const TRTNOEXCEPT=0
 Get the padding of the convolution. If the padding is asymmetric, the pre-padding is returned. More...
 
virtual void setNbGroups (int nbGroups) TRTNOEXCEPT=0
 Set the number of groups for a convolution. More...
 
virtual int getNbGroups () const TRTNOEXCEPT=0
 Set the number of groups for a convolution. More...
 
virtual void setKernelWeights (Weights weights) TRTNOEXCEPT=0
 Set the kernel weights for the convolution. More...
 
virtual Weights getKernelWeights () const TRTNOEXCEPT=0
 Get the kernel weights for the convolution. More...
 
virtual void setBiasWeights (Weights weights) TRTNOEXCEPT=0
 Set the bias weights for the convolution. More...
 
virtual Weights getBiasWeights () const TRTNOEXCEPT=0
 Get the bias weights for the convolution. More...
 
virtual void setDilation (DimsHW dilation) TRTNOEXCEPT=0
 Set the dilation for a convolution. More...
 
virtual DimsHW getDilation () const TRTNOEXCEPT=0
 Get the dilation for a convolution. More...
 
virtual void setPrePadding (Dims padding) TRTNOEXCEPT=0
 Set the pre-padding. More...
 
virtual Dims getPrePadding () const TRTNOEXCEPT=0
 Get the pre-padding. More...
 
virtual void setPostPadding (Dims padding) TRTNOEXCEPT=0
 Set the post-padding. More...
 
virtual Dims getPostPadding () const TRTNOEXCEPT=0
 Get the post-padding. More...
 
virtual void setPaddingMode (PaddingMode paddingMode) TRTNOEXCEPT=0
 Set the padding mode. More...
 
virtual PaddingMode getPaddingMode () const TRTNOEXCEPT=0
 Get the padding mode. More...
 
virtual void setKernelSizeNd (Dims kernelSize) TRTNOEXCEPT=0
 Set the multi-dimension kernel size of the convolution. More...
 
virtual Dims getKernelSizeNd () const TRTNOEXCEPT=0
 Get the multi-dimension kernel size of the convolution. More...
 
virtual void setStrideNd (Dims stride) TRTNOEXCEPT=0
 Set the multi-dimension stride of the convolution. More...
 
virtual Dims getStrideNd () const TRTNOEXCEPT=0
 Get the multi-dimension stride of the convolution. More...
 
virtual void setPaddingNd (Dims padding) TRTNOEXCEPT=0
 Set the multi-dimension padding of the convolution. More...
 
virtual Dims getPaddingNd () const TRTNOEXCEPT=0
 Get the multi-dimension padding of the convolution. More...
 
virtual void setDilationNd (Dims dilation) TRTNOEXCEPT=0
 Set the multi-dimension dilation of the convolution. More...
 
virtual Dims getDilationNd () const TRTNOEXCEPT=0
 Get the multi-dimension dilation of the convolution. More...
 
- Public Member Functions inherited from nvinfer1::ILayer
virtual LayerType getType () const TRTNOEXCEPT=0
 Return the type of a layer. More...
 
virtual void setName (const char *name) TRTNOEXCEPT=0
 Set the name of a layer. More...
 
virtual const char * getName () const TRTNOEXCEPT=0
 Return the name of a layer. More...
 
virtual int getNbInputs () const TRTNOEXCEPT=0
 Get the number of inputs of a layer.
 
virtual ITensorgetInput (int index) const TRTNOEXCEPT=0
 Get the layer input corresponding to the given index. More...
 
virtual int getNbOutputs () const TRTNOEXCEPT=0
 Get the number of outputs of a layer.
 
virtual ITensorgetOutput (int index) const TRTNOEXCEPT=0
 Get the layer output corresponding to the given index. More...
 
virtual void setInput (int index, ITensor &tensor) TRTNOEXCEPT=0
 replace an input of this layer with a specific tensor More...
 
virtual void setPrecision (DataType dataType) TRTNOEXCEPT=0
 Set the computational precision of this layer. More...
 
virtual DataType getPrecision () const TRTNOEXCEPT=0
 get the computational precision of this layer More...
 
virtual bool precisionIsSet () const TRTNOEXCEPT=0
 whether the computational precision has been set for this layer More...
 
virtual void resetPrecision () TRTNOEXCEPT=0
 reset the computational precision for this layer More...
 
virtual void setOutputType (int index, DataType dataType) TRTNOEXCEPT=0
 Set the output type of this layer. More...
 
virtual DataType getOutputType (int index) const TRTNOEXCEPT=0
 get the output type of this layer More...
 
virtual bool outputTypeIsSet (int index) const TRTNOEXCEPT=0
 whether the output type has been set for this layer More...
 
virtual void resetOutputType (int index) TRTNOEXCEPT=0
 reset the output type for this layer 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.

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.

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

Get the multi-dimension dilation of the convolution.

See also
setDilation()
virtual DimsHW nvinfer1::IConvolutionLayer::getKernelSize ( ) const
pure virtual

Get the HW kernel size of the convolution.

See also
setKernelSize()
virtual Dims nvinfer1::IConvolutionLayer::getKernelSizeNd ( ) const
pure virtual

Get the multi-dimension kernel size of the convolution.

See also
setKernelSizeNd()
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. If the padding is asymmetric, the pre-padding is returned.

See also
setPadding()
virtual PaddingMode nvinfer1::IConvolutionLayer::getPaddingMode ( ) const
pure virtual

Get the padding mode.

Default: kEXPLICIT_ROUND_DOWN

See also
setPaddingMode()
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()
virtual Dims nvinfer1::IConvolutionLayer::getPostPadding ( ) const
pure virtual

Get the post-padding.

See also
setPostPadding()
virtual Dims nvinfer1::IConvolutionLayer::getPrePadding ( ) const
pure virtual

Get the pre-padding.

See also
setPrePadding()
virtual Dims nvinfer1::IConvolutionLayer::getStrideNd ( ) const
pure virtual

Get the multi-dimension stride of the convolution.

See also
setStrideNd()
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  dilation)
pure virtual

Set the dilation for a convolution.

Default: (1,1)

See also
getDilation()
virtual void nvinfer1::IConvolutionLayer::setDilationNd ( Dims  dilation)
pure virtual

Set the multi-dimension dilation of the convolution.

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

See also
getDilation()
virtual void nvinfer1::IConvolutionLayer::setKernelSize ( DimsHW  kernelSize)
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 [1,16].

See also
getKernelSize()
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 [1,16].

See also
getKernelSizeNd() setKernelSize() 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

See also
getNbGroups()
virtual void nvinfer1::IConvolutionLayer::setNbOutputMaps ( int  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()
virtual void nvinfer1::IConvolutionLayer::setPadding ( DimsHW  padding)
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 [0,15].

See also
getPadding()
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()
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 [0,15].

See also
getPaddingNd() setPadding() getPadding()
virtual void nvinfer1::IConvolutionLayer::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
getPostPadding()
virtual void nvinfer1::IConvolutionLayer::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
getPrePadding()
virtual void nvinfer1::IConvolutionLayer::setStride ( DimsHW  stride)
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()
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()

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