Skip to content

D
Docs

OpenHarmony / Docs
1 年多 前同步成功

通知 159
Star 292
Fork 28
D
Docs
未验证 提交 399d92ac 编写于 作者: Z zengyawen 提交者： Gitee
浏览文件
操作

add nativeapis 

Signed-off-by: Nzengyawen <zengyawen1@huawei.com>
上级 d4116b12
隐藏空白更改
内联 并排
Showing with 35 addition and 34 deletion
en/application-dev/reference/native-apis/neural__network__runtime__type_8h.md
浏览文件 @ 399d92ac
# neural_network_runtime.h # neural_network_runtime_type.h
## Overview ## 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. Defines the structure and enumeration for Neural Network Runtime.
**Since:** **Since:**
9 9
...@@ -16,38 +16,39 @@ Defines the Neural Network Runtime APIs. The AI inference framework uses the Nat ...@@ -16,38 +16,39 @@ Defines the Neural Network Runtime APIs. The AI inference framework uses the Nat
## Summary ## Summary
### Functions ### Structs
| Name | Description | | Name | Description |
| -------- | -------- | | -------- | -------- |
| [OH_NNModel_Construct](_neural_nework_runtime.md#oh_nnmodel_construct) (void) | Creates a model instance of the [OH_NNModel](_neural_nework_runtime.md#oh_nnmodel) type and uses other APIs provided by OH_NNModel to construct the model instance. | | [OH_NN_UInt32Array](_o_h___n_n___u_int32_array.md) | This structure is used to store a 32-bit unsigned integer array. |
| [OH_NNModel_AddTensor](_neural_nework_runtime.md#oh_nnmodel_addtensor) ([OH_NNModel](_neural_nework_runtime.md#oh_nnmodel) \*model, const [OH_NN_Tensor](_o_h___n_n___tensor.md) \*tensor) | Adds a tensor to a model instance. | | [OH_NN_QuantParam](_o_h___n_n___quant_param.md) | Quantization information. |
| [OH_NNModel_SetTensorData](_neural_nework_runtime.md#oh_nnmodel_settensordata) ([OH_NNModel](_neural_nework_runtime.md#oh_nnmodel) \*model, uint32_t index, const void \*dataBuffer, size_t length) | Sets the tensor value. | | [OH_NN_Tensor](_o_h___n_n___tensor.md) | Defines the tensor structure. |
| [OH_NNModel_AddOperation](_neural_nework_runtime.md#oh_nnmodel_addoperation) ([OH_NNModel](_neural_nework_runtime.md#oh_nnmodel) \*model, [OH_NN_OperationType](_neural_nework_runtime.md#oh_nn_operationtype) op, const [OH_NN_UInt32Array](_o_h___n_n___u_int32_array.md) \*paramIndices, const [OH_NN_UInt32Array](_o_h___n_n___u_int32_array.md) \*inputIndices, const [OH_NN_UInt32Array](_o_h___n_n___u_int32_array.md) \*outputIndices) | Adds an operator to a model instance. | | [OH_NN_Memory](_o_h___n_n___memory.md) | Defines the memory structure. |
| [OH_NNModel_SpecifyInputsAndOutputs](_neural_nework_runtime.md#oh_nnmodel_specifyinputsandoutputs) ([OH_NNModel](_neural_nework_runtime.md#oh_nnmodel) \*model, const [OH_NN_UInt32Array](_o_h___n_n___u_int32_array.md) \*inputIndices, const [OH_NN_UInt32Array](_o_h___n_n___u_int32_array.md) \*outputIndices) | Specifies the inputs and outputs of a model. |
| [OH_NNModel_Finish](_neural_nework_runtime.md#oh_nnmodel_finish) ([OH_NNModel](_neural_nework_runtime.md#oh_nnmodel) \*model) | Completes model composition. |
| [OH_NNModel_Destroy](_neural_nework_runtime.md#oh_nnmodel_destroy) ([OH_NNModel](_neural_nework_runtime.md#oh_nnmodel) \*\*model) | Releases a model instance. | ### Types
| [OH_NNModel_GetAvailableOperations](_neural_nework_runtime.md#oh_nnmodel_getavailableoperations) ([OH_NNModel](_neural_nework_runtime.md#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](_neural_nework_runtime.md#oh_nncompilation_construct) (const [OH_NNModel](_neural_nework_runtime.md#oh_nnmodel) \*model) | Creates a compilation instance of the [OH_NNCompilation](_neural_nework_runtime.md#oh_nncompilation) type. | | Name | Description |
| [OH_NNCompilation_SetDevice](_neural_nework_runtime.md#oh_nncompilation_setdevice) ([OH_NNCompilation](_neural_nework_runtime.md#oh_nncompilation) \*compilation, size_t deviceID) | Specifies the device for model compilation and computing. | | -------- | -------- |
| [OH_NNCompilation_SetCache](_neural_nework_runtime.md#oh_nncompilation_setcache) ([OH_NNCompilation](_neural_nework_runtime.md#oh_nncompilation) \*compilation, const char \*cachePath, uint32_t version) | Set the cache directory and version of the compiled model. | | [OH_NNModel](_neural_nework_runtime.md#oh_nnmodel) | Defines the handles of models for Neural Network Runtime. |
| [OH_NNCompilation_SetPerformanceMode](_neural_nework_runtime.md#oh_nncompilation_setperformancemode) ([OH_NNCompilation](_neural_nework_runtime.md#oh_nncompilation) \*compilation, [OH_NN_PerformanceMode](_neural_nework_runtime.md#oh_nn_performancemode) performanceMode) | Sets the performance mode for model computing. | | [OH_NNCompilation](_neural_nework_runtime.md#oh_nncompilation) | Defines the compiler handle for Neural Network Runtime. |
| [OH_NNCompilation_SetPriority](_neural_nework_runtime.md#oh_nncompilation_setpriority) ([OH_NNCompilation](_neural_nework_runtime.md#oh_nncompilation) \*compilation, [OH_NN_Priority](_neural_nework_runtime.md#oh_nn_priority) priority) | Sets the model computing priority. | | [OH_NNExecutor](_neural_nework_runtime.md#oh_nnexecutor) | Defines the executor handle for Neural Network Runtime. |
| [OH_NNCompilation_EnableFloat16](_neural_nework_runtime.md#oh_nncompilation_enablefloat16) ([OH_NNCompilation](_neural_nework_runtime.md#oh_nncompilation) \*compilation, bool enableFloat16) | Enables float16 for computing. | | [OH_NN_UInt32Array](_neural_nework_runtime.md#oh_nn_uint32array) | This structure is used to store a 32-bit unsigned integer array. |
| [OH_NNCompilation_Build](_neural_nework_runtime.md#oh_nncompilation_build) ([OH_NNCompilation](_neural_nework_runtime.md#oh_nncompilation) \*compilation) | Compiles a model. | | [OH_NN_QuantParam](_neural_nework_runtime.md#oh_nn_quantparam) | Quantization information. |
| [OH_NNCompilation_Destroy](_neural_nework_runtime.md#oh_nncompilation_destroy) ([OH_NNCompilation](_neural_nework_runtime.md#oh_nncompilation) \*\*compilation) | Releases the **Compilation** object. | | [OH_NN_Tensor](_neural_nework_runtime.md#oh_nn_tensor) | Defines the tensor structure. |
| [OH_NNExecutor_Construct](_neural_nework_runtime.md#oh_nnexecutor_construct) ([OH_NNCompilation](_neural_nework_runtime.md#oh_nncompilation) \*compilation) | [OH_NNExecutor](_neural_nework_runtime.md#oh_nnexecutor) \*<br/>Creates an executor instance of the [OH_NNExecutor](_neural_nework_runtime.md#oh_nnexecutor) type. | | [OH_NN_Memory](_neural_nework_runtime.md#oh_nn_memory) | Defines the memory structure. |
| [OH_NNExecutor_SetInput](_neural_nework_runtime.md#oh_nnexecutor_setinput) ([OH_NNExecutor](_neural_nework_runtime.md#oh_nnexecutor) \*executor, uint32_t inputIndex, const [OH_NN_Tensor](_o_h___n_n___tensor.md) \*tensor, const void \*dataBuffer, size_t length) | Sets the single input data for a model. |
| [OH_NNExecutor_SetOutput](_neural_nework_runtime.md#oh_nnexecutor_setoutput) ([OH_NNExecutor](_neural_nework_runtime.md#oh_nnexecutor) \*executor, uint32_t outputIndex, void \*dataBuffer, size_t length) | Sets the buffer for a single output of a model. |
| [OH_NNExecutor_GetOutputShape](_neural_nework_runtime.md#oh_nnexecutor_getoutputshape) ([OH_NNExecutor](_neural_nework_runtime.md#oh_nnexecutor) \*executor, uint32_t outputIndex, int32_t \*\*shape, uint32_t \*shapeLength) | Obtains the dimension information about the output tensor. | ### Enums
| [OH_NNExecutor_Run](_neural_nework_runtime.md#oh_nnexecutor_run) ([OH_NNExecutor](_neural_nework_runtime.md#oh_nnexecutor) \*executor) | Performs inference. |
| [OH_NNExecutor_AllocateInputMemory](_neural_nework_runtime.md#oh_nnexecutor_allocateinputmemory) ([OH_NNExecutor](_neural_nework_runtime.md#oh_nnexecutor) \*executor, uint32_t inputIndex, size_t length) | Allocates shared memory to a single input on a device. | | Name | Description |
| [OH_NNExecutor_AllocateOutputMemory](_neural_nework_runtime.md#oh_nnexecutor_allocateoutputmemory) ([OH_NNExecutor](_neural_nework_runtime.md#oh_nnexecutor) \*executor, uint32_t outputIndex, size_t length) | Allocates shared memory to a single output on a device. | | -------- | -------- |
| [OH_NNExecutor_DestroyInputMemory](_neural_nework_runtime.md#oh_nnexecutor_destroyinputmemory) ([OH_NNExecutor](_neural_nework_runtime.md#oh_nnexecutor) \*executor, uint32_t inputIndex, [OH_NN_Memory](_o_h___n_n___memory.md) \*\*memory) | Releases the input memory to which the [OH_NN_Memory](_o_h___n_n___memory.md) instance points. | | [OH_NN_PerformanceMode](_neural_nework_runtime.md#oh_nn_performancemode) {<br/>OH_NN_PERFORMANCE_NONE = 0, OH_NN_PERFORMANCE_LOW = 1, OH_NN_PERFORMANCE_MEDIUM = 2, OH_NN_PERFORMANCE_HIGH = 3,<br/>OH_NN_PERFORMANCE_EXTREME = 4<br/>} | Defines the hardware performance mode. |
| [OH_NNExecutor_DestroyOutputMemory](_neural_nework_runtime.md#oh_nnexecutor_destroyoutputmemory) ([OH_NNExecutor](_neural_nework_runtime.md#oh_nnexecutor) \*executor, uint32_t outputIndex, [OH_NN_Memory](_o_h___n_n___memory.md) \*\*memory) | Releases the output memory to which the [OH_NN_Memory](_o_h___n_n___memory.md) instance points. | | [OH_NN_Priority](_neural_nework_runtime.md#oh_nn_priority) { OH_NN_PRIORITY_NONE = 0, OH_NN_PRIORITY_LOW = 1, OH_NN_PRIORITY_MEDIUM = 2, OH_NN_PRIORITY_HIGH = 3 } | Defines the model inference task priority. |
| [OH_NNExecutor_SetInputWithMemory](_neural_nework_runtime.md#oh_nnexecutor_setinputwithmemory) ([OH_NNExecutor](_neural_nework_runtime.md#oh_nnexecutor) \*executor, uint32_t inputIndex, const [OH_NN_Tensor](_o_h___n_n___tensor.md) \*tensor, const [OH_NN_Memory](_o_h___n_n___memory.md) \*memory) | Specifies the hardware shared memory pointed to by the [OH_NN_Memory](_o_h___n_n___memory.md) instance as the shared memory used by a single input. | | [OH_NN_ReturnCode](_neural_nework_runtime.md#oh_nn_returncode) {<br/>OH_NN_SUCCESS = 0, OH_NN_FAILED = 1, OH_NN_INVALID_PARAMETER = 2, OH_NN_MEMORY_ERROR = 3,<br/>OH_NN_OPERATION_FORBIDDEN = 4, OH_NN_NULL_PTR = 5, OH_NN_INVALID_FILE = 6, OH_NN_UNAVALIDABLE_DEVICE = 7,<br/>OH_NN_INVALID_PATH = 8<br/>} | Defines error codes for Neural Network Runtime. |
| [OH_NNExecutor_SetOutputWithMemory](_neural_nework_runtime.md#oh_nnexecutor_setoutputwithmemory) ([OH_NNExecutor](_neural_nework_runtime.md#oh_nnexecutor) \*executor, uint32_t outputIndex, const [OH_NN_Memory](_o_h___n_n___memory.md) \*memory) | Specifies the hardware shared memory pointed to by the [OH_NN_Memory](_o_h___n_n___memory.md) instance as the shared memory used by a single output. | | [OH_NN_FuseType](_neural_nework_runtime.md#oh_nn_fusetype) : int8_t { OH_NN_FUSED_NONE = 0, OH_NN_FUSED_RELU = 1, OH_NN_FUSED_RELU6 = 2 } | Defines activation function types in the fusion operator for Neural Network Runtime. |
| [OH_NNExecutor_Destroy](_neural_nework_runtime.md#oh_nnexecutor_destroy) ([OH_NNExecutor](_neural_nework_runtime.md#oh_nnexecutor) \*\*executor) | Destroys an executor instance to release the memory occupied by the executor. | | [OH_NN_Format](_neural_nework_runtime.md#oh_nn_format) { OH_NN_FORMAT_NONE = 0, OH_NN_FORMAT_NCHW = 1, OH_NN_FORMAT_NHWC = 2 } | Defines the layout type of tensor data. |
| [OH_NNDevice_GetAllDevicesID](_neural_nework_runtime.md#oh_nndevice_getalldevicesid) (const size_t \*\*allDevicesID, uint32_t \*deviceCount) | Obtains the ID of the device connected to Neural Network Runtime. | | [OH_NN_DeviceType](_neural_nework_runtime.md#oh_nn_devicetype) { OH_NN_OTHERS = 0, OH_NN_CPU = 1, OH_NN_GPU = 2, OH_NN_ACCELERATOR = 3 } | Defines device types supported by Neural Network Runtime. |
| [OH_NNDevice_GetName](_neural_nework_runtime.md#oh_nndevice_getname) (size_t deviceID, const char \*\*name) | Obtains the name of the specified device. | | [OH_NN_DataType](_neural_nework_runtime.md#oh_nn_datatype) {<br/>OH_NN_UNKNOWN = 0, OH_NN_BOOL = 1, OH_NN_INT8 = 2, OH_NN_INT16 = 3,<br/>OH_NN_INT32 = 4, OH_NN_INT64 = 5, OH_NN_UINT8 = 6, OH_NN_UINT16 = 7,<br/>OH_NN_UINT32 = 8, OH_NN_UINT64 = 9, OH_NN_FLOAT16 = 10, OH_NN_FLOAT32 = 11,<br/>OH_NN_FLOAT64 = 12<br/>} | Defines tensor data types supported by Neural Network Runtime. |
| [OH_NNDevice_GetType](_neural_nework_runtime.md#oh_nndevice_gettype) (size_t deviceID, [OH_NN_DeviceType](_neural_nework_runtime.md#oh_nn_devicetype) \*deviceType) | Obtains the type information of the specified device. | | [OH_NN_OperationType](_neural_nework_runtime.md#oh_nn_operationtype) {<br/>OH_NN_OPS_ADD = 1, OH_NN_OPS_AVG_POOL = 2, OH_NN_OPS_BATCH_NORM = 3, OH_NN_OPS_BATCH_TO_SPACE_ND = 4,<br/>OH_NN_OPS_BIAS_ADD = 5, OH_NN_OPS_CAST = 6, OH_NN_OPS_CONCAT = 7, OH_NN_OPS_CONV2D = 8,<br/>OH_NN_OPS_CONV2D_TRANSPOSE = 9, OH_NN_OPS_DEPTHWISE_CONV2D_NATIVE = 10, OH_NN_OPS_DIV = 11, OH_NN_OPS_ELTWISE = 12,<br/>OH_NN_OPS_EXPAND_DIMS = 13, OH_NN_OPS_FILL = 14, OH_NN_OPS_FULL_CONNECTION = 15, OH_NN_OPS_GATHER = 16,<br/>OH_NN_OPS_HSWISH = 17, OH_NN_OPS_LESS_EQUAL = 18, OH_NN_OPS_MATMUL = 19, OH_NN_OPS_MAXIMUM = 20,<br/>OH_NN_OPS_MAX_POOL = 21, OH_NN_OPS_MUL = 22, OH_NN_OPS_ONE_HOT = 23, OH_NN_OPS_PAD = 24,<br/>OH_NN_OPS_POW = 25, OH_NN_OPS_SCALE = 26, OH_NN_OPS_SHAPE = 27, OH_NN_OPS_SIGMOID = 28,<br/>OH_NN_OPS_SLICE = 29, OH_NN_OPS_SOFTMAX = 30, OH_NN_OPS_SPACE_TO_BATCH_ND = 31, OH_NN_OPS_SPLIT = 32,<br/>OH_NN_OPS_SQRT = 33, OH_NN_OPS_SQUARED_DIFFERENCE = 34, OH_NN_OPS_SQUEEZE = 35, OH_NN_OPS_STACK = 36,<br/>OH_NN_OPS_STRIDED_SLICE = 37, OH_NN_OPS_SUB = 38, OH_NN_OPS_TANH = 39, OH_NN_OPS_TILE = 40,<br/>OH_NN_OPS_TRANSPOSE = 41, OH_NN_OPS_REDUCE_MEAN = 42, OH_NN_OPS_RESIZE_BILINEAR = 43, OH_NN_OPS_RSQRT = 44,<br/>OH_NN_OPS_RESHAPE = 45, OH_NN_OPS_PRELU = 46, OH_NN_OPS_RELU = 47, OH_NN_OPS_RELU6 = 48,<br/>OH_NN_OPS_LAYER_NORM = 49, OH_NN_OPS_REDUCE_PROD = 50, OH_NN_OPS_REDUCE_ALL = 51, OH_NN_OPS_QUANT_DTYPE_CAST = 52,<br/>OH_NN_OPS_TOP_K = 53, OH_NN_OPS_ARG_MAX = 54, OH_NN_OPS_UNSQUEEZE = 55, OH_NN_OPS_GELU = 56<br/>} | Defines operator types supported by Neural Network Runtime. |
| [OH_NN_TensorType](_neural_nework_runtime.md#oh_nn_tensortype) {<br/>OH_NN_TENSOR = 0, OH_NN_ADD_ACTIVATIONTYPE = 1, OH_NN_AVG_POOL_KERNEL_SIZE = 2, OH_NN_AVG_POOL_STRIDE = 3,<br/>OH_NN_AVG_POOL_PAD_MODE = 4, OH_NN_AVG_POOL_PAD = 5, OH_NN_AVG_POOL_ACTIVATION_TYPE = 6, OH_NN_BATCH_NORM_EPSILON = 7,<br/>OH_NN_BATCH_TO_SPACE_ND_BLOCKSIZE = 8, OH_NN_BATCH_TO_SPACE_ND_CROPS = 9, OH_NN_CONCAT_AXIS = 10, OH_NN_CONV2D_STRIDES = 11,<br/>OH_NN_CONV2D_PAD = 12, OH_NN_CONV2D_DILATION = 13, OH_NN_CONV2D_PAD_MODE = 14, OH_NN_CONV2D_ACTIVATION_TYPE = 15,<br/>OH_NN_CONV2D_GROUP = 16, OH_NN_CONV2D_TRANSPOSE_STRIDES = 17, OH_NN_CONV2D_TRANSPOSE_PAD = 18, OH_NN_CONV2D_TRANSPOSE_DILATION = 19,<br/>OH_NN_CONV2D_TRANSPOSE_OUTPUT_PADDINGS = 20, OH_NN_CONV2D_TRANSPOSE_PAD_MODE = 21, OH_NN_CONV2D_TRANSPOSE_ACTIVATION_TYPE = 22, OH_NN_CONV2D_TRANSPOSE_GROUP = 23,<br/>OH_NN_DEPTHWISE_CONV2D_NATIVE_STRIDES = 24, OH_NN_DEPTHWISE_CONV2D_NATIVE_PAD = 25, OH_NN_DEPTHWISE_CONV2D_NATIVE_DILATION = 26, OH_NN_DEPTHWISE_CONV2D_NATIVE_PAD_MODE = 27,<br/>OH_NN_DEPTHWISE_CONV2D_NATIVE_ACTIVATION_TYPE = 28, OH_NN_DIV_ACTIVATIONTYPE = 29, OH_NN_ELTWISE_MODE = 30, OH_NN_FULL_CONNECTION_AXIS = 31,<br/>OH_NN_FULL_CONNECTION_ACTIVATIONTYPE = 32, OH_NN_MATMUL_TRANSPOSE_A = 33, OH_NN_MATMUL_TRANSPOSE_B = 34, OH_NN_MATMUL_ACTIVATION_TYPE = 35,<br/>OH_NN_MAX_POOL_KERNEL_SIZE = 36, OH_NN_MAX_POOL_STRIDE = 37, OH_NN_MAX_POOL_PAD_MODE = 38, OH_NN_MAX_POOL_PAD = 39,<br/>OH_NN_MAX_POOL_ACTIVATION_TYPE = 40, OH_NN_MUL_ACTIVATION_TYPE = 41, OH_NN_ONE_HOT_AXIS = 42, OH_NN_PAD_CONSTANT_VALUE = 43,<br/>OH_NN_SCALE_ACTIVATIONTYPE = 44, OH_NN_SCALE_AXIS = 45, OH_NN_SOFTMAX_AXIS = 46, OH_NN_SPACE_TO_BATCH_ND_BLOCK_SHAPE = 47,<br/>OH_NN_SPACE_TO_BATCH_ND_PADDINGS = 48, OH_NN_SPLIT_AXIS = 49, OH_NN_SPLIT_OUTPUT_NUM = 50, OH_NN_SPLIT_SIZE_SPLITS = 51,<br/>OH_NN_SQUEEZE_AXIS = 52, OH_NN_STACK_AXIS = 53, OH_NN_STRIDED_SLICE_BEGIN_MASK = 54, OH_NN_STRIDED_SLICE_END_MASK = 55,<br/>OH_NN_STRIDED_SLICE_ELLIPSIS_MASK = 56, OH_NN_STRIDED_SLICE_NEW_AXIS_MASK = 57, OH_NN_STRIDED_SLICE_SHRINK_AXIS_MASK = 58, OH_NN_SUB_ACTIVATIONTYPE = 59,<br/>OH_NN_REDUCE_MEAN_KEEP_DIMS = 60, OH_NN_RESIZE_BILINEAR_NEW_HEIGHT = 61, OH_NN_RESIZE_BILINEAR_NEW_WIDTH = 62, OH_NN_RESIZE_BILINEAR_PRESERVE_ASPECT_RATIO = 63,<br/>OH_NN_RESIZE_BILINEAR_COORDINATE_TRANSFORM_MODE = 64, OH_NN_RESIZE_BILINEAR_EXCLUDE_OUTSIDE = 65, OH_NN_LAYER_NORM_BEGIN_NORM_AXIS = 66, OH_NN_LAYER_NORM_EPSILON = 67,<br/>OH_NN_LAYER_NORM_BEGIN_PARAM_AXIS = 68, OH_NN_LAYER_NORM_ELEMENTWISE_AFFINE = 69, OH_NN_REDUCE_PROD_KEEP_DIMS = 70, OH_NN_REDUCE_ALL_KEEP_DIMS = 71,<br/>OH_NN_QUANT_DTYPE_CAST_SRC_T = 72, OH_NN_QUANT_DTYPE_CAST_DST_T = 73, OH_NN_TOP_K_SORTED = 74, OH_NN_ARG_MAX_AXIS = 75,<br/>OH_NN_ARG_MAX_KEEPDIMS = 76, OH_NN_UNSQUEEZE_AXIS = 77<br/>} | Enumerates the tensor data types. |
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或