TensorRT  8.0.0
nvinfer1::IDeconvolutionLayer Class Reference

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

#include <NvInfer.h>

Inheritance diagram for nvinfer1::IDeconvolutionLayer:
nvinfer1::ILayer nvinfer1::INoCopy

Public Member Functions

TRT_DEPRECATED void setKernelSize (DimsHW kernelSize) noexcept
 Set the HW kernel size of the convolution. More...
 
TRT_DEPRECATED DimsHW getKernelSize () const noexcept
 Get the HW kernel size of the deconvolution. More...
 
void setNbOutputMaps (int32_t nbOutputMaps) noexcept
 Set the number of output feature maps for the deconvolution. More...
 
int32_t getNbOutputMaps () const noexcept
 Get the number of output feature maps for the deconvolution. More...
 
TRT_DEPRECATED void setStride (DimsHW stride) noexcept
 Get the stride of the deconvolution. More...
 
TRT_DEPRECATED DimsHW getStride () const noexcept
 Get the stride of the deconvolution. More...
 
TRT_DEPRECATED void setPadding (DimsHW padding) noexcept
 Set the padding of the deconvolution. More...
 
TRT_DEPRECATED DimsHW getPadding () const noexcept
 Get the padding of the deconvolution. More...
 
void setNbGroups (int32_t nbGroups) noexcept
 Set the number of groups for a deconvolution. More...
 
int32_t getNbGroups () const noexcept
 Get the number of groups for a deconvolution. More...
 
void setKernelWeights (Weights weights) noexcept
 Set the kernel weights for the deconvolution. More...
 
Weights getKernelWeights () const noexcept
 Get the kernel weights for the deconvolution. More...
 
void setBiasWeights (Weights weights) noexcept
 Set the bias weights for the deconvolution. More...
 
Weights getBiasWeights () const noexcept
 Get the bias weights for the deconvolution. More...
 
void setPrePadding (Dims padding) noexcept
 Set the multi-dimension pre-padding of the deconvolution. More...
 
Dims getPrePadding () const noexcept
 Get the pre-padding. More...
 
void setPostPadding (Dims padding) noexcept
 Set the multi-dimension post-padding of the deconvolution. 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 setKernelSizeNd (Dims kernelSize) noexcept
 Set the multi-dimension kernel size of the deconvolution. More...
 
Dims getKernelSizeNd () const noexcept
 Get the multi-dimension kernel size of the deconvolution. More...
 
void setStrideNd (Dims stride) noexcept
 Set the multi-dimension stride of the deconvolution. More...
 
Dims getStrideNd () const noexcept
 Get the multi-dimension stride of the deconvolution. More...
 
void setPaddingNd (Dims padding) noexcept
 Set the multi-dimension padding of the deconvolution. More...
 
Dims getPaddingNd () const noexcept
 Get the multi-dimension padding of the deconvolution. More...
 
void setDilationNd (Dims dilation) noexcept
 Set the multi-dimension dilation of the deconvolution. More...
 
Dims getDilationNd () const noexcept
 Get the multi-dimension dilation of the deconvolution. More...
 
void setInput (int32_t index, ITensor &tensor) noexcept
 Append or replace an input of this layer with a specific tensor. 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.
 
ITensorgetInput (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.
 
ITensorgetOutput (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::VDeconvolutionLayermImpl
 
- Protected Attributes inherited from nvinfer1::ILayer
apiv::VLayermLayer
 

Additional Inherited Members

- Protected Member Functions inherited from nvinfer1::INoCopy
 INoCopy (const INoCopy &other)=delete
 
INoCopyoperator= (const INoCopy &other)=delete
 
 INoCopy (INoCopy &&other)=delete
 
INoCopyoperator= (INoCopy &&other)=delete
 

Detailed Description

A deconvolution layer in a network definition.

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

Member Function Documentation

◆ getBiasWeights()

Weights nvinfer1::IDeconvolutionLayer::getBiasWeights ( ) const
inlinenoexcept

Get the bias weights for the deconvolution.

See also
getBiasWeights()

◆ getDilationNd()

Dims nvinfer1::IDeconvolutionLayer::getDilationNd ( ) const
inlinenoexcept

Get the multi-dimension dilation of the deconvolution.

See also
setDilationNd()

◆ getKernelSize()

TRT_DEPRECATED DimsHW nvinfer1::IDeconvolutionLayer::getKernelSize ( ) const
inlinenoexcept

Get the HW kernel size of the deconvolution.

See also
setKernelSize()
Deprecated:
Superseded by getKernelSizeNd and will be removed in TensorRT 9.0.

◆ getKernelSizeNd()

Dims nvinfer1::IDeconvolutionLayer::getKernelSizeNd ( ) const
inlinenoexcept

Get the multi-dimension kernel size of the deconvolution.

See also
setKernelSizeNd()

◆ getKernelWeights()

Weights nvinfer1::IDeconvolutionLayer::getKernelWeights ( ) const
inlinenoexcept

Get the kernel weights for the deconvolution.

See also
setNbGroups()

◆ getNbGroups()

int32_t nvinfer1::IDeconvolutionLayer::getNbGroups ( ) const
inlinenoexcept

Get the number of groups for a deconvolution.

See also
setNbGroups()

◆ getNbOutputMaps()

int32_t nvinfer1::IDeconvolutionLayer::getNbOutputMaps ( ) const
inlinenoexcept

Get the number of output feature maps for the deconvolution.

See also
setNbOutputMaps()

◆ getPadding()

TRT_DEPRECATED DimsHW nvinfer1::IDeconvolutionLayer::getPadding ( ) const
inlinenoexcept

Get the padding of the deconvolution.

Default: (0, 0)

See also
setPadding()
Deprecated:
Superseded by getPaddingNd and will be removed in TensorRT 9.0.

◆ getPaddingMode()

PaddingMode nvinfer1::IDeconvolutionLayer::getPaddingMode ( ) const
inlinenoexcept

Get the padding mode.

Default: kEXPLICIT_ROUND_DOWN

See also
setPaddingMode()

◆ getPaddingNd()

Dims nvinfer1::IDeconvolutionLayer::getPaddingNd ( ) const
inlinenoexcept

Get the multi-dimension padding of the deconvolution.

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

See also
setPaddingNd()

◆ getPostPadding()

Dims nvinfer1::IDeconvolutionLayer::getPostPadding ( ) const
inlinenoexcept

Get the padding.

See also
setPostPadding()

◆ getPrePadding()

Dims nvinfer1::IDeconvolutionLayer::getPrePadding ( ) const
inlinenoexcept

Get the pre-padding.

See also
setPrePadding()

◆ getStride()

TRT_DEPRECATED DimsHW nvinfer1::IDeconvolutionLayer::getStride ( ) const
inlinenoexcept

Get the stride of the deconvolution.

Default: (1,1)

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

◆ getStrideNd()

Dims nvinfer1::IDeconvolutionLayer::getStrideNd ( ) const
inlinenoexcept

Get the multi-dimension stride of the deconvolution.

See also
setStrideNd()

◆ setBiasWeights()

void nvinfer1::IDeconvolutionLayer::setBiasWeights ( Weights  weights)
inlinenoexcept

Set the bias weights for the deconvolution.

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

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

See also
getBiasWeights()

◆ setDilationNd()

void nvinfer1::IDeconvolutionLayer::setDilationNd ( Dims  dilation)
inlinenoexcept

Set the multi-dimension dilation of the deconvolution.

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

See also
getDilationNd()

◆ setInput()

void nvinfer1::ILayer::setInput
inlinenoexcept

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

Parameters
indexthe index of the input to modify.
tensorthe new input tensor

For a IDeconvolutionLayer, 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

◆ setKernelSize()

TRT_DEPRECATED void nvinfer1::IDeconvolutionLayer::setKernelSize ( DimsHW  kernelSize)
inlinenoexcept

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], or the combinations of [64, 96, 128] in one dimension and 1 in the other dimensions, i.e. [1x64] or [64x1] are valid, but not [64x64].

See also
getKernelSize()
Deprecated:
Superseded by setKernelSizeNd and will be removed in TensorRT 9.0.

◆ setKernelSizeNd()

void nvinfer1::IDeconvolutionLayer::setKernelSizeNd ( Dims  kernelSize)
inlinenoexcept

Set the multi-dimension kernel size of the deconvolution.

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() setKernelSize() getKernelSize()

◆ setKernelWeights()

void nvinfer1::IDeconvolutionLayer::setKernelWeights ( Weights  weights)
inlinenoexcept

Set the kernel weights for the deconvolution.

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

See also
getWeights()

◆ setNbGroups()

void nvinfer1::IDeconvolutionLayer::setNbGroups ( int32_t  nbGroups)
inlinenoexcept

Set the number of groups for a deconvolution.

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

If executing this layer on DLA, nbGroups must be one

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()

◆ setNbOutputMaps()

void nvinfer1::IDeconvolutionLayer::setNbOutputMaps ( int32_t  nbOutputMaps)
inlinenoexcept

Set the number of output feature maps for the deconvolution.

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

See also
getNbOutputMaps()

◆ setPadding()

TRT_DEPRECATED void nvinfer1::IDeconvolutionLayer::setPadding ( DimsHW  padding)
inlinenoexcept

Set the padding of the deconvolution.

The output will be trimmed by this number of elements on each side in the height and width directions. In other words, it resembles the inverse of a convolution layer with this padding size. Padding is symmetric, and negative padding is not supported.

Default: (0,0)

If executing this layer on DLA, both height and width of padding must be 0.

See also
getPadding()
Deprecated:
Superseded by setPaddingNd and will be removed in TensorRT 9.0.

◆ setPaddingMode()

void nvinfer1::IDeconvolutionLayer::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::IDeconvolutionLayer::setPaddingNd ( Dims  padding)
inlinenoexcept

Set the multi-dimension padding of the deconvolution.

The output will be trimmed by this number of elements on both sides of every dimension. In other words, it resembles the inverse of a convolution layer with this padding size. Padding is symmetric, and negative padding is not supported.

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

If executing this layer on DLA, padding must be 0.

See also
getPaddingNd() setPadding() getPadding()

◆ setPostPadding()

void nvinfer1::IDeconvolutionLayer::setPostPadding ( Dims  padding)
inlinenoexcept

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

The output will be trimmed by this number of elements on the end of every dimension. In other words, it resembles the inverse of a convolution layer with this padding size. Negative padding is not supported.

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

If executing this layer on DLA, padding must be 0.

See also
getPostPadding()

◆ setPrePadding()

void nvinfer1::IDeconvolutionLayer::setPrePadding ( Dims  padding)
inlinenoexcept

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

The output will be trimmed by this number of elements on the start of every dimension. In other words, it resembles the inverse of a convolution layer with this padding size. Negative padding is not supported.

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

If executing this layer on DLA, padding must be 0.

See also
getPrePadding()

◆ setStride()

TRT_DEPRECATED void nvinfer1::IDeconvolutionLayer::setStride ( DimsHW  stride)
inlinenoexcept

Get the stride of the deconvolution.

If executing this layer on DLA, both height and width of stride must be in the range [1,32] or the combinations of [64, 96, 128] in one dimension and 1 in the other dimensions, i.e. [1x64] or [64x1] are valid, but not [64x64].

See also
setStride()
Deprecated:
Superseded by setStrideNd and will be removed in TensorRT 9.0.

◆ setStrideNd()

void nvinfer1::IDeconvolutionLayer::setStrideNd ( Dims  stride)
inlinenoexcept

Set the multi-dimension stride of the deconvolution.

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 [1-32].

See also
getStrideNd() setStride() getStride()

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