OH_NN_Tensor
typedef struct OH_NN_Tensor {...} OH_NN_Tensor
Overview
Defines the tensor structure.
It is usually used to construct data nodes and operator parameters in a model diagram. When constructing a tensor, you need to specify the data type, number of dimensions, dimension information, and quantization information.
Since: 9
Deprecated from: 11
Substitute: NN_TensorDesc
Related module: NeuralNetworkRuntime
Header file: neural_network_runtime_type.h
Summary
Member Variables
| Name | Description |
|---|---|
| OH_NN_DataType dataType | Data type of the specified tensor. The value must be an enum of OH_NN_DataType. |
| uint32_t dimensionCount | Number of dimensions of the specified tensor. |
| const int32_t *dimensions | Dimension information (shape) of the specified tensor. |
| const OH_NN_QuantParam *quantParam | Quantization information of the specified tensor. The value must be an enum of OH_NN_QuantParam. |
| OH_NN_TensorType type | Type of the specified tensor. The value is related to the tensor usage. If the tensor is used as the input or output of the model, set type to OH_NN_TENSOR. If the tensor is used as an operator parameter, select an enum value other than OH_NN_TENSOR from OH_NN_TensorType. |