OH_NN_Tensor

Overview

Defines the tensor structure.

It is usually used to construct data nodes and operator parameters in a model graph. When constructing a tensor, you need to specify the data type, number of dimensions, dimension information, and quantization information.

Since: 9

Related Modules:

NeuralNeworkRuntime

Summary

Member Variables

Name Description
dataType Data type of the specified tensor. The value must be an enumerated value of OH_NN_DataType.
dimensionCount Number of dimensions of the specified tensor
dimensions Dimension information (shape) of the specified tensor
quantParam Quantization information of the specified tensor. The data type must be OH_NN_QuantParam.
type Specifies the tensor type. The value of type is related to the tensor usage. When the tensor is used as the input or output of the model, set type to OH_NN_TENSOR. When a tensor is used as an operator parameter, select any enumerated value except OH_NN_TENSOR from OH_NN_TensorType.

Member Variable Description

dataType

OH_NN_DataType OH_NN_Tensor::dataType

Description
Data type of the specified tensor. The value must be an enumerated value of OH_NN_DataType.

dimensionCount

uint32_t OH_NN_Tensor::dimensionCount

Description
Number of dimensions of the specified tensor

dimensions

const int32_t* OH_NN_Tensor::dimensions

Description
Dimension information (shape) of the specified tensor

quantParam

const OH_NN_QuantParam* OH_NN_Tensor::quantParam

Description
Quantization information of the specified tensor. The data type must be OH_NN_QuantParam.

type

OH_NN_TensorType OH_NN_Tensor::type

Description
Specifies the tensor type. The value of type is related to the tensor usage. When the tensor is used as the input or output of the model, set type to OH_NN_TENSOR. When a tensor is used as an operator parameter, select any enumerated value except OH_NN_TENSOR from OH_NN_TensorType.