TensorRT
7.2.2.3
|
Slices an input tensor into an output tensor based on the offset and strides. More...
#include <NvInfer.h>
Public Member Functions | |
virtual void | setStart (Dims start)=0 |
Set the start offset that the slice layer uses to create the output slice. More... | |
virtual Dims | getStart () const =0 |
Get the start offset for the slice layer. More... | |
virtual void | setSize (Dims size)=0 |
Set the dimensions of the output slice. More... | |
virtual Dims | getSize () const =0 |
Get dimensions of the output slice. More... | |
virtual void | setStride (Dims stride)=0 |
Set the stride for computing the output slice data. More... | |
virtual Dims | getStride () const =0 |
Get the stride for the output slice. More... | |
virtual void | setMode (SliceMode mode)=0 |
Set the slice mode. More... | |
virtual SliceMode | getMode () const =0 |
Get the slice mode. More... | |
void | setInput (int32_t index, ITensor &tensor) _TENSORRT_OVERRIDE=0 |
Append or replace an input of this layer with a specific tensor. 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 int32_t | getNbInputs () const =0 |
Get the number of inputs of a layer. | |
virtual ITensor * | getInput (int32_t index) const =0 |
Get the layer input corresponding to the given index. More... | |
virtual int32_t | getNbOutputs () const =0 |
Get the number of outputs of a layer. | |
virtual ITensor * | getOutput (int32_t index) const =0 |
Get the layer output corresponding to the given index. 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 (int32_t index, DataType dataType)=0 |
Set the output type of this layer. More... | |
virtual DataType | getOutputType (int32_t index) const =0 |
get the output type of this layer More... | |
virtual bool | outputTypeIsSet (int32_t index) const =0 |
whether the output type has been set for this layer More... | |
virtual void | resetOutputType (int32_t index)=0 |
reset the output type for this layer More... | |
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. Dynamic slice specifies one or more of start, size or stride as ITensors, by using ILayer::setTensor to add a second, third, or fourth 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 input (third 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 Int32 shape tensors if not specified via Dims.
Furthermore, if the slice layer must produce a shape tensor, then start, size, and stride must be build time constants, i.e. as static Dims, or be computable by constant folding.
For example using slice on a tensor: input = {{0, 2, 4}, {1, 3, 5}} start = {1, 0} size = {1, 2} stride = {1, 2} output = {{1, 5}}
|
pure virtual |
Get the slice mode.
|
pure virtual |
|
pure virtual |
|
pure virtual |
|
pure virtual |
Append or replace an input of this layer with a specific tensor.
index | the index of the input to modify. |
tensor | the new input tensor |
For a slice layer, the values 0-3 are valid. The values 1-3 override start, size or stride dimensions, respectively. Conversely, this input tensor can be overridden via appropriate set call. The indices are as follows:
If this function is called with a value greater than 0, then the function getNbInputs() changes from returning 1 to index + 1.
Implements nvinfer1::ILayer.
|
pure virtual |
Set the slice mode.
|
pure virtual |
Set the dimensions of the output slice.
size | The dimensions of the output slice. |
If the third input is set, it is reset to null.
|
pure virtual |
Set the start offset that the slice layer uses to create the output slice.
start | The start offset to read data from the input tensor. |
If the second input is set, it is reset to null.
|
pure virtual |
Set the stride for computing the output slice data.
stride | The dimensions of the stride to compute the values to store in the output slice. |
If the fourth input is set, it is reset to null.