org.bytedeco.tensorrt.nvinfer

Class IConvolutionLayer

java.lang.Object

org.bytedeco.javacpp.Pointer

org.bytedeco.tensorrt.nvinfer.INoCopy

org.bytedeco.tensorrt.nvinfer.ILayer

org.bytedeco.tensorrt.nvinfer.IConvolutionLayer

All Implemented Interfaces:

AutoCloseable

@Namespace(value="nvinfer1")
 @NoOffset
 @Properties(inherit=nvinfer.class)
public class IConvolutionLayer
extends ILayer

\class IConvolutionLayer \brief 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.

Nested Class Summary

Nested classes/interfaces inherited from class org.bytedeco.javacpp.Pointer

Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter

Field Summary

Fields inherited from class org.bytedeco.javacpp.Pointer

address, capacity, limit, position

Constructor Summary

Constructors

Constructor and Description
IConvolutionLayer(Pointer p) Pointer cast constructor.

Method Summary

Modifier and Type	Method and Description
Weights	getBiasWeights() \brief Get the bias weights for the convolution.
DimsHW	getDilation() Deprecated. Superseded by getDilationNd. Deprecated prior to TensorRT 8.0 and will be removed in 9.0
Dims32	getDilationNd() \brief Get the multi-dimension dilation of the convolution.
DimsHW	getKernelSize() Deprecated. Superseded by getKernelSizeNd. Deprecated prior to TensorRT 8.0 and will be removed in 9.0
Dims32	getKernelSizeNd() \brief Get the multi-dimension kernel size of the convolution.
Weights	getKernelWeights() \brief Get the kernel weights of the convolution.
int	getNbGroups() \brief Get the number of groups of the convolution.
int	getNbOutputMaps() \brief Get the number of output maps for the convolution.
DimsHW	getPadding() Deprecated. Superseded by getPaddingNd. Deprecated prior to TensorRT 8.0 and will be removed in 9.0
nvinfer.PaddingMode	getPaddingMode() \brief Get the padding mode.
Dims32	getPaddingNd() \brief Get the multi-dimension padding of the convolution.
Dims32	getPostPadding() \brief Get the post-padding.
Dims32	getPrePadding() \brief Get the pre-padding.
DimsHW	getStride() Deprecated. Superseded by getStrideNd. Deprecated prior to TensorRT 8.0 and will be removed in 9.0
Dims32	getStrideNd() \brief Get the multi-dimension stride of the convolution.
void	setBiasWeights(Weights weights) \brief Set the bias weights for the convolution.
void	setDilation(DimsHW dilation) Deprecated. Superseded by setDilationNd. Deprecated prior to TensorRT 8.0 and will be removed in 9.0
void	setDilationNd(Dims32 dilation) \brief Set the multi-dimension dilation of the convolution.
void	setKernelSize(DimsHW kernelSize) Deprecated. Superseded by setKernelSizeNd. Deprecated prior to TensorRT 8.0 and will be removed in 9.0
void	setKernelSizeNd(Dims32 kernelSize) \brief Set the multi-dimension kernel size of the convolution.
void	setKernelWeights(Weights weights) \brief Set the kernel weights for the convolution.
void	setNbGroups(int nbGroups) \brief Set the number of groups for a convolution.
void	setNbOutputMaps(int nbOutputMaps) \brief Set the number of output maps for the convolution.
void	setPadding(DimsHW padding) Deprecated. Superseded by setPaddingNd. Deprecated prior to TensorRT 8.0 and will be removed in 9.0
void	setPaddingMode(int paddingMode)
void	setPaddingMode(nvinfer.PaddingMode paddingMode) \brief Set the padding mode.
void	setPaddingNd(Dims32 padding) \brief Set the multi-dimension padding of the convolution.
void	setPostPadding(Dims32 padding) \brief Set the multi-dimension post-padding of the convolution.
void	setPrePadding(Dims32 padding) \brief Set the multi-dimension pre-padding of the convolution.
void	setStride(DimsHW stride) Deprecated. Superseded by setStrideNd. Deprecated prior to TensorRT 8.0 and will be removed in 9.0
void	setStrideNd(Dims32 stride) \brief Set the multi-dimension stride of the convolution.

Methods inherited from class org.bytedeco.tensorrt.nvinfer.ILayer

getInput, getMetadata, getName, getNbInputs, getNbOutputs, getOutput, getOutputType, getPrecision, getType, outputTypeIsSet, precisionIsSet, resetOutputType, resetPrecision, setInput, setMetadata, setMetadata, setName, setName, setOutputType, setOutputType, setPrecision, setPrecision

Methods inherited from class org.bytedeco.javacpp.Pointer

address, asBuffer, asByteBuffer, availablePhysicalBytes, calloc, capacity, capacity, close, deallocate, deallocate, deallocateReferences, deallocator, deallocator, equals, fill, formatBytes, free, getDirectBufferAddress, getPointer, getPointer, getPointer, getPointer, hashCode, interruptDeallocatorThread, isNull, isNull, limit, limit, malloc, maxBytes, maxPhysicalBytes, memchr, memcmp, memcpy, memmove, memset, offsetAddress, offsetof, offsetof, parseBytes, physicalBytes, physicalBytesInaccurate, position, position, put, realloc, referenceCount, releaseReference, retainReference, setNull, sizeof, sizeof, toString, totalBytes, totalCount, totalPhysicalBytes, withDeallocator, zero

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Constructor Detail

IConvolutionLayer

public IConvolutionLayer(Pointer p)

Pointer cast constructor. Invokes Pointer(Pointer).

Method Detail

setKernelSize

@Deprecated
 @NoException(value=true)
public void setKernelSize(@ByVal
                                                                DimsHW kernelSize)

Deprecated. Superseded by setKernelSizeNd. Deprecated prior to TensorRT 8.0 and will be removed in 9.0

\brief 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()

getKernelSize

@Deprecated
 @ByVal
 @NoException(value=true)
public DimsHW getKernelSize()

Deprecated. Superseded by getKernelSizeNd. Deprecated prior to TensorRT 8.0 and will be removed in 9.0

\brief Get the HW kernel size of the convolution.

See Also:

setKernelSize()

setNbOutputMaps

@NoException(value=true)
public void setNbOutputMaps(int nbOutputMaps)

\brief 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

@NoException(value=true)
public int getNbOutputMaps()

\brief Get the number of output maps for the convolution.

See Also:

setNbOutputMaps()

setStride

@Deprecated
 @NoException(value=true)
public void setStride(@ByVal
                                                            DimsHW stride)

Deprecated. Superseded by setStrideNd. Deprecated prior to TensorRT 8.0 and will be removed in 9.0

\brief 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()

getStride

@Deprecated
 @ByVal
 @NoException(value=true)
public DimsHW getStride()

Deprecated. Superseded by getStrideNd. Deprecated prior to TensorRT 8.0 and will be removed in 9.0

\brief Get the stride of the convolution.

setPadding

@Deprecated
 @NoException(value=true)
public void setPadding(@ByVal
                                                             DimsHW padding)

Deprecated. Superseded by setPaddingNd. Deprecated prior to TensorRT 8.0 and will be removed in 9.0

\brief 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()

getPadding

@Deprecated
 @ByVal
 @NoException(value=true)
public DimsHW getPadding()

Deprecated. Superseded by getPaddingNd. Deprecated prior to TensorRT 8.0 and will be removed in 9.0

\brief Get the padding of the convolution. If the padding is asymmetric, the pre-padding is returned.

See Also:

setPadding()

setNbGroups

@NoException(value=true)
public void setNbGroups(int nbGroups)

\brief Set the number of groups for a convolution. The input tensor channels are divided into \p 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

@NoException(value=true)
public int getNbGroups()

\brief Get the number of groups of the convolution.

See Also:

setNbGroups()

setKernelWeights

@NoException(value=true)
public void setKernelWeights(@ByVal
                                                      Weights weights)

\brief Set the kernel weights for the convolution. The weights are specified as a contiguous array in \p GKCRS order, where \p G is the number of groups, \p K the number of output feature maps, \p C the number of input channels, and \p R and \p S are the height and width of the filter.

See Also:

getKernelWeights()

getKernelWeights

@ByVal
 @NoException(value=true)
public Weights getKernelWeights()

\brief Get the kernel weights of the convolution.

See Also:

setKernelWeights()

setBiasWeights

@NoException(value=true)
public void setBiasWeights(@ByVal
                                                    Weights weights)

\brief 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

@ByVal
 @NoException(value=true)
public Weights getBiasWeights()

\brief Get the bias weights for the convolution.

See Also:

setBiasWeights()

setDilation

@Deprecated
 @NoException(value=true)
public void setDilation(@ByVal
                                                              DimsHW dilation)

Deprecated. Superseded by setDilationNd. Deprecated prior to TensorRT 8.0 and will be removed in 9.0

\brief 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()

getDilation

@Deprecated
 @ByVal
 @NoException(value=true)
public DimsHW getDilation()

Deprecated. Superseded by getDilationNd. Deprecated prior to TensorRT 8.0 and will be removed in 9.0

\brief Get the dilation for a convolution.

See Also:

setDilation()

setPrePadding

@NoException(value=true)
public void setPrePadding(@ByVal @Cast(value="nvinfer1::Dims*")
                                                   Dims32 padding)

\brief 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

@ByVal
 @Cast(value="nvinfer1::Dims*")
 @NoException(value=true)
public Dims32 getPrePadding()

\brief Get the pre-padding.

See Also:

setPrePadding()

setPostPadding

@NoException(value=true)
public void setPostPadding(@ByVal @Cast(value="nvinfer1::Dims*")
                                                    Dims32 padding)

\brief 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

@ByVal
 @Cast(value="nvinfer1::Dims*")
 @NoException(value=true)
public Dims32 getPostPadding()

\brief Get the post-padding.

See Also:

setPostPadding()

setPaddingMode

@NoException(value=true)
public void setPaddingMode(nvinfer.PaddingMode paddingMode)

\brief Set the padding mode. Padding mode takes precedence if both setPaddingMode and setPre/PostPadding are used. Default: kEXPLICIT_ROUND_DOWN

See Also:

getPaddingMode()

setPaddingMode

@NoException(value=true)
public void setPaddingMode(@Cast(value="nvinfer1::PaddingMode")
                                                    int paddingMode)

getPaddingMode

@NoException(value=true)
public nvinfer.PaddingMode getPaddingMode()

\brief Get the padding mode. Default: kEXPLICIT_ROUND_DOWN

See Also:

setPaddingMode()

setKernelSizeNd

@NoException(value=true)
public void setKernelSizeNd(@ByVal @Cast(value="nvinfer1::Dims*")
                                                     Dims32 kernelSize)

\brief 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

@ByVal
 @Cast(value="nvinfer1::Dims*")
 @NoException(value=true)
public Dims32 getKernelSizeNd()

\brief Get the multi-dimension kernel size of the convolution.

See Also:

setKernelSizeNd()

setStrideNd

@NoException(value=true)
public void setStrideNd(@ByVal @Cast(value="nvinfer1::Dims*")
                                                 Dims32 stride)

\brief 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:

setStride() getStride()

getStrideNd

@ByVal
 @Cast(value="nvinfer1::Dims*")
 @NoException(value=true)
public Dims32 getStrideNd()

\brief Get the multi-dimension stride of the convolution.

See Also:

setStrideNd()

setPaddingNd

@NoException(value=true)
public void setPaddingNd(@ByVal @Cast(value="nvinfer1::Dims*")
                                                  Dims32 padding)

\brief 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:

setPadding() getPadding()

getPaddingNd

@ByVal
 @Cast(value="nvinfer1::Dims*")
 @NoException(value=true)
public Dims32 getPaddingNd()

\brief Get the multi-dimension padding of the convolution. If the padding is asymmetric, the pre-padding is returned.

See Also:

setPaddingNd()

setDilationNd

@NoException(value=true)
public void setDilationNd(@ByVal @Cast(value="nvinfer1::Dims*")
                                                   Dims32 dilation)

\brief 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

@ByVal
 @Cast(value="nvinfer1::Dims*")
 @NoException(value=true)
public Dims32 getDilationNd()

\brief Get the multi-dimension dilation of the convolution.

See Also:

setDilation()