TensorRT 10.6.0
nvinfer1::ISliceLayer Class Reference

Slices an input tensor into an output tensor based on the offset and strides. More...

#include <NvInfer.h>

Inheritance diagram for nvinfer1::ISliceLayer:
nvinfer1::ILayer nvinfer1::INoCopy

Public Member Functions

void setStart (Dims const &start) noexcept
 Set the start offset that the slice layer uses to create the output slice. More...
 
Dims getStart () const noexcept
 Get the start offset for the slice layer. More...
 
void setSize (Dims const &size) noexcept
 Set the dimensions of the output slice. More...
 
Dims getSize () const noexcept
 Get dimensions of the output slice. More...
 
void setStride (Dims const &stride) noexcept
 Set the stride for computing the output slice data. More...
 
Dims getStride () const noexcept
 Get the stride for the output slice. More...
 
void setMode (SampleMode mode) noexcept
 Set the slice mode. More...
 
SampleMode getMode () const noexcept
 Get the slice mode. More...
 
void setAxes (Dims const &axes) noexcept
 Set the axes for this ISliceLayer. More...
 
Dims getAxes () const noexcept
 Get the axes for this ISliceLayer. 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 (char const *name) noexcept
 Set the name of a layer. More...
 
char const * getName () const noexcept
 Return the name of a layer. More...
 
int32_t getNbInputs () const noexcept
 Get the number of inputs of a layer. More...
 
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. More...
 
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 preferred or required computational precision of this layer in a weakly-typed network. 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 in a weakly-typed network. 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...
 
void setMetadata (char const *metadata) noexcept
 Set the metadata for this layer. More...
 
char const * getMetadata () const noexcept
 Get the metadata of the layer. More...
 

Protected Member Functions

virtual ~ISliceLayer () noexcept=default
 
- Protected Member Functions inherited from nvinfer1::ILayer
virtual ~ILayer () noexcept=default
 
- Protected Member Functions inherited from nvinfer1::INoCopy
 INoCopy ()=default
 
virtual ~INoCopy ()=default
 
 INoCopy (INoCopy const &other)=delete
 
INoCopyoperator= (INoCopy const &other)=delete
 
 INoCopy (INoCopy &&other)=delete
 
INoCopyoperator= (INoCopy &&other)=delete
 

Protected Attributes

apiv::VSliceLayer * mImpl
 
- Protected Attributes inherited from nvinfer1::ILayer
apiv::VLayer * mLayer
 

Detailed Description

Slices an input tensor into an output tensor based on the offset and strides.

The slice layer has two variants, static and dynamic. Static slice specifies the start, size, and stride dimensions at layer creation time via Dims and can use the get/set accessor functions of the ISliceLayer. Static slice layers can also optionally specify axes through the get/set accessor functions of the ISliceLayer. Dynamic slice specifies one or more of start, size, stride, or axes as ITensors, by using ILayer::setInput to add a second, third, fourth, or sixth input respectively. The corresponding Dims are used if an input is missing or null.

An application can determine if the ISliceLayer has a dynamic output shape based on whether the size or axes input is present and non-null.

The slice layer selects for each dimension a start location from within the input tensor, and copies elements to the output tensor using the specified stride across the input tensor. Start, size, and stride tensors must be 1D tensors of type Int32 or Int64 if not specified via Dims.

An example of using slice on a tensor: input = {{0, 2, 4}, {1, 3, 5}} start = {1, 0} size = {1, 2} stride = {1, 2} output = {{1, 5}}

If axes are provided then starts, ends, and strides must have the same length as axes and specifies a subset of dimensions to slice. If axes are not provided, starts, ends, and strides must be of the same length as the rank of the input tensor.

An example of using slice on a tensor with axes specified: input = {{0, 2, 4}, {1, 3, 5}} start = {1} size = {2} stride = {1} axes = {1} output = {{2, 4}, {3, 5}}

When the sampleMode is kCLAMP or kREFLECT, for each input dimension, if its size is 0 then the corresponding output dimension must be 0 too.

When the sampleMode is kFILL, the fifth input to the slice layer is used to determine the value to fill in out-of-bound indices. It is an error to specify the fifth input in any other sampleMode.

A slice layer can produce a shape tensor if the following conditions are met:

  • start, size, and stride are build time constants, either as static Dims or as constant input tensors.
  • axes, if provided, are build time constants, either as static Dims or as a constant input tensor.
  • The number of elements in the output tensor does not exceed 2 * Dims::MAX_DIMS.

The input tensor is a shape tensor if the output is a shape tensor.

The following constraints must be satisfied to execute this layer on DLA:

  • start, size, and stride are build time constants, either as static Dims or as constant input tensors.
  • axes, if provided, are build time constants, either as static Dims or as a constant input tensor.
  • sampleMode is kDEFAULT, kWRAP, or kFILL.
  • Strides are 1 for all dimensions.
  • Slicing is not performed on the first dimension.
  • The input tensor has four dimensions.
  • For kFILL sliceMode, the fill value input is a scalar output of an IConstantLayer with value 0 that is not consumed by any other layer.
Warning
Do not inherit from this class, as doing so will break forward-compatibility of the API and ABI.

Constructor & Destructor Documentation

◆ ~ISliceLayer()

virtual nvinfer1::ISliceLayer::~ISliceLayer ( )
protectedvirtualdefaultnoexcept

Member Function Documentation

◆ getAxes()

Dims nvinfer1::ISliceLayer::getAxes ( ) const
inlinenoexcept

Get the axes for this ISliceLayer.

Returns
The axes on which the starts, ends, and strides parameters of this slice apply to.

If the sixth input is present and non-null, this function returns a Dims with nbDims = -1.

See also
setAxes

◆ getMode()

SampleMode nvinfer1::ISliceLayer::getMode ( ) const
inlinenoexcept

Get the slice mode.

See also
setMode()

◆ getSize()

Dims nvinfer1::ISliceLayer::getSize ( ) const
inlinenoexcept

Get dimensions of the output slice.

Returns
The output dimension, or an invalid Dims structure.

If the third input is present and non-null, this function returns a Dims with nbDims = -1.

See also
setSize

◆ getStart()

Dims nvinfer1::ISliceLayer::getStart ( ) const
inlinenoexcept

Get the start offset for the slice layer.

Returns
The start offset, or an invalid Dims structure.

If the second input is present and non-null, this function returns a Dims with nbDims = -1.

See also
setStart

◆ getStride()

Dims nvinfer1::ISliceLayer::getStride ( ) const
inlinenoexcept

Get the stride for the output slice.

Returns
The slicing stride, or an invalid Dims structure.

If the fourth input is present and non-null, this function returns a Dims with nbDims = -1.

See also
setStride

◆ setAxes()

void nvinfer1::ISliceLayer::setAxes ( Dims const &  axes)
inlinenoexcept

Set the axes for this ISliceLayer.

Parameters
axesThe axes on which the starts, ends, and strides parameters of the slice apply to.

If a sixth input had been used to create this layer, that input is reset to null by this method.

See also
getAxes

◆ setInput()

void nvinfer1::ILayer::setInput ( int32_t  index,
ITensor tensor 
)
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 slice layer, the values 0-4 are valid. The indices are as follows:

  • 0: Tensor to be sliced.
  • 1: The start tensor to begin slicing, as a 1D tensor of type Int32 or Int64.
  • 2: The size tensor of the resulting slice, as a 1D tensor of type Int32 or Int64.
  • 3: The stride of the slicing operation, as a 1D tensor of type Int32 or Int64.
  • 4: Value for the kFILL slice mode. The fill value data type should either be the same or be implicitly convertible to the input data type. Implicit data type conversion is supported among kFLOAT, kHALF, kINT8, and kFP8 data types. This input is disallowed for other modes.
  • 5: The axes tensor indicating the corresponding axes that start, size, and stride should apply to, as a 1D tensor or type Int32 or Int64. Negative values for axes indicate indexing from the back of the input tensor. Values must be unique and be within the interval of [-rank(input), rank(input)-1].

Using the corresponding setter resets the input to null.

If this function is called with a value greater than 0, then the function getNbInputs() changes from returning 1 to index + 1.

◆ setMode()

void nvinfer1::ISliceLayer::setMode ( SampleMode  mode)
inlinenoexcept

Set the slice mode.

See also
getMode()

◆ setSize()

void nvinfer1::ISliceLayer::setSize ( Dims const &  size)
inlinenoexcept

Set the dimensions of the output slice.

Parameters
sizeThe dimensions of the output slice.

If a third input had been used to create this layer, that input is reset to null by this method.

See also
getSize

◆ setStart()

void nvinfer1::ISliceLayer::setStart ( Dims const &  start)
inlinenoexcept

Set the start offset that the slice layer uses to create the output slice.

Parameters
startThe start offset to read data from the input tensor.

If a second input had been used to create this layer, that input is reset to null by this method.

See also
getStart

◆ setStride()

void nvinfer1::ISliceLayer::setStride ( Dims const &  stride)
inlinenoexcept

Set the stride for computing the output slice data.

Parameters
strideThe dimensions of the stride to compute the values to store in the output slice.

If a fourth input had been used to create this layer, that input is reset to null by this method.

See also
getStride

Member Data Documentation

◆ mImpl

apiv::VSliceLayer* nvinfer1::ISliceLayer::mImpl
protected

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

  Copyright © 2024 NVIDIA Corporation
  Privacy Policy | Manage My Privacy | Do Not Sell or Share My Data | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact