harmony 鸿蒙neural_network_runtime.h

2023-06-24
浏览 (445)

neural_network_runtime.h

Overview

Defines the Neural Network Runtime APIs. The AI inference framework uses the Native APIs provided by Neural Network Runtime to construct and compile models and perform inference and computing on acceleration hardware. Note: Currently, the APIs of Neural Network Runtime do not support multi-thread calling.

Since: 9

Related Modules:

NeuralNeworkRuntime

Summary

Functions

Name	Description
OH_NNModel_Construct (void)	Creates a model instance of the OH_NNModel type and uses other APIs provided by OH_NNModel to construct the model instance.
OH_NNModel_AddTensor (OH_NNModel model, const OH_NN_Tensor tensor)	Adds a tensor to a model instance.
OH_NNModel_SetTensorData (OH_NNModel model, uint32_t index, const void dataBuffer, size_t length)	Sets the tensor value.
OH_NNModel_AddOperation (OH_NNModel model, OH_NN_OperationType op, const OH_NN_UInt32Array paramIndices, const OH_NN_UInt32Array inputIndices, const OH_NN_UInt32Array outputIndices)	Adds an operator to a model instance.
OH_NNModel_SpecifyInputsAndOutputs (OH_NNModel model, const OH_NN_UInt32Array inputIndices, const OH_NN_UInt32Array *outputIndices)	Specifies the inputs and outputs of a model.
OH_NNModel_Finish (OH_NNModel *model)	Completes model composition.
OH_NNModel_Destroy (OH_NNModel **model)	Releases a model instance.
OH_NNModel_GetAvailableOperations (OH_NNModel model, size_t deviceID, const bool isSupported, uint32_t opCount)	Queries whether the device supports operators in the model. The support status is indicated by the Boolean value.
OH_NNCompilation_Construct (const OH_NNModel *model)	Creates a compilation instance of the OH_NNCompilation type.
OH_NNCompilation_SetDevice (OH_NNCompilation *compilation, size_t deviceID)	Specifies the device for model compilation and computing.
OH_NNCompilation_SetCache (OH_NNCompilation compilation, const char cachePath, uint32_t version)	Set the cache directory and version of the compiled model.
OH_NNCompilation_SetPerformanceMode (OH_NNCompilation *compilation, OH_NN_PerformanceMode performanceMode)	Sets the performance mode for model computing.
OH_NNCompilation_SetPriority (OH_NNCompilation *compilation, OH_NN_Priority priority)	Sets the model computing priority.
OH_NNCompilation_EnableFloat16 (OH_NNCompilation *compilation, bool enableFloat16)	Enables float16 for computing.
OH_NNCompilation_Build (OH_NNCompilation *compilation)	Compiles a model.
OH_NNCompilation_Destroy (OH_NNCompilation **compilation)	Releases the Compilation object.
OH_NNExecutor_Construct (OH_NNCompilation *compilation)	OH_NNExecutor * Creates an executor instance of the OH_NNExecutor type.
OH_NNExecutor_SetInput (OH_NNExecutor executor, uint32_t inputIndex, const OH_NN_Tensor tensor, const void *dataBuffer, size_t length)	Sets the single input data for a model.
OH_NNExecutor_SetOutput (OH_NNExecutor executor, uint32_t outputIndex, void dataBuffer, size_t length)	Sets the buffer for a single output of a model.
OH_NNExecutor_GetOutputShape (OH_NNExecutor executor, uint32_t outputIndex, int32_t shape, uint32_t shapeLength)	Obtains the dimension information about the output tensor.
OH_NNExecutor_Run (OH_NNExecutor *executor)	Performs inference.
OH_NNExecutor_AllocateInputMemory (OH_NNExecutor *executor, uint32_t inputIndex, size_t length)	Allocates shared memory to a single input on a device.
OH_NNExecutor_AllocateOutputMemory (OH_NNExecutor *executor, uint32_t outputIndex, size_t length)	Allocates shared memory to a single output on a device.
OH_NNExecutor_DestroyInputMemory (OH_NNExecutor executor, uint32_t inputIndex, OH_NN_Memory *memory)	Releases the input memory to which the OH_NN_Memory instance points.
OH_NNExecutor_DestroyOutputMemory (OH_NNExecutor executor, uint32_t outputIndex, OH_NN_Memory *memory)	Releases the output memory to which the OH_NN_Memory instance points.
OH_NNExecutor_SetInputWithMemory (OH_NNExecutor executor, uint32_t inputIndex, const OH_NN_Tensor tensor, const OH_NN_Memory *memory)	Specifies the hardware shared memory pointed to by the OH_NN_Memory instance as the shared memory used by a single input.
OH_NNExecutor_SetOutputWithMemory (OH_NNExecutor executor, uint32_t outputIndex, const OH_NN_Memory memory)	Specifies the hardware shared memory pointed to by the OH_NN_Memory instance as the shared memory used by a single output.
OH_NNExecutor_Destroy (OH_NNExecutor **executor)	Destroys an executor instance to release the memory occupied by the executor.
OH_NNDevice_GetAllDevicesID (const size_t *allDevicesID, uint32_t deviceCount)	Obtains the ID of the device connected to Neural Network Runtime.
OH_NNDevice_GetName (size_t deviceID, const char **name)	Obtains the name of the specified device.
OH_NNDevice_GetType (size_t deviceID, OH_NN_DeviceType *deviceType)	Obtains the type information of the specified device.