nvinfer1::Dims Class Reference

Structure to define the dimensions of a tensor. More...

Inheritance diagram for nvinfer1::Dims:

Collaboration diagram for nvinfer1::Dims:

Public Member Functions
	__attribute__ ((deprecated)) DimensionType type[MAX_DIMS]
	The type of each dimension, provided for backwards compatibility. More...

Public Attributes
int32_t	nbDims
	The number of dimensions. More...
int32_t	d [MAX_DIMS]
	The extent of each dimension. More...

Static Public Attributes
static const int32_t	MAX_DIMS = 8
	The maximum number of dimensions supported for a tensor. More...

Detailed Description

Structure to define the dimensions of a tensor.

Note

: Currently the following formats are supported for layer inputs and outputs:

• zero or more index dimensions followed by one channel and two spatial dimensions (e.g. CHW)
• one time series dimension followed by one index dimension followed by one channel dimension (i.e. TNC)

TensorRT can also return an invalid dims structure. This structure is represented by nbDims == -1 and d[i] == 0 for all d.

TensorRT can also return an "unknown rank" dims structure. This structure is represented by nbDims == -1 and d[i] == -1 for all d.

Member Function Documentation

__attribute__()

nvinfer1::Dims::__attribute__

(

(deprecated)

)

The type of each dimension, provided for backwards compatibility.

and will be removed in TensorRT 8.0.

Member Data Documentation

MAX_DIMS

const int32_t nvinfer1::Dims::MAX_DIMS = 8

static

The maximum number of dimensions supported for a tensor.

nbDims

int32_t nvinfer1::Dims::nbDims

The number of dimensions.

d

int32_t nvinfer1::Dims::d[MAX_DIMS]

The extent of each dimension.

---

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

• NvInferRuntimeCommon.h