aclmdlLoadFromFile

Applicability

Product

Supported

Atlas A3 training products / Atlas A3 inference products

Atlas A2 training products / Atlas A2 inference products

Atlas 200I/500 A2 inference products

Atlas inference products

Atlas training products

Description

Loads offline model data from a file. The model workspace is managed by the system.

The file specified by modelPath is an offline model (offline model adapted to the Ascend AI Processor) in the format of *.om. For details about how to obtain the .om file, see "Command-Line Options" > "Basic Options" > "General Options" > "--mode" in ATC Instructions.

If the size of the OM model file is limited, this API can also load an external weight file. You need to save the weight in a separate file during model building. For example, when you use ATC to generate an .om file, set --external_weight to 1, indicating that the weight of the Const/Constant node on the original network is saved in a separate file in the weight directory. Ensure that the weight directory is at the same level as the .om file so that the API can automatically search for the weight file in the weight directory when you call this API to load the .om file. Otherwise, the weight file may fail to be loaded.

Prototype

aclError aclmdlLoadFromFile(const char *modelPath, uint32_t *modelId)

Parameters

Parameter

Input/Output

Description

modelPath

Input

Pointer to the model file path, which contains the file name. The user who runs the app must have enough permission to access the directory.

modelId

Output

Pointer to the model ID.

Returns the model ID after the model is successfully loaded. The model ID is used for model identification in subsequent operations.

Returns

0 on success; else, failure. For details, see aclError.

Restrictions

The operations of loading, executing, and unloading a model must be performed in the same context. For details about how to create a context, see or . Before loading the model file, check whether the memory space is sufficient based on the size of the model file. If the memory space is insufficient, the application will be abnormal.

See Also

For the API call sequence, see Loading a Model.

The aclmdlSetConfigOpt and aclmdlLoadWithConfig APIs are provided for model loading. Set the attributes in the configuration object passed to the API call to decide how the model will be loaded and who will manage the memory.