Function: bundle_load_from_mem

Function Usage

Loads offline model data from memory if variables need to be dynamically updated during model execution. The model workspace is managed by the system.

This API must be used with other APIs to dynamically update variables. For details, see the description in acl.mdl.bundle_load_from_file.

Prototype

C Prototype

        
             aclError aclmdlBundleLoadFromMem(const void *model,  size_t modelSize, uint32_t *bundleId)

Python Function

        
             bundle_id, ret = acl.mdl.bundle_load_from_mem(model, model_size)

Parameters

Parameter	Description
model	Int, pointer address for storing model data. The model file is built in graph mode. Call aclgrphBundleBuildModel to compile the model, call aclgrphBundleSaveModel to save the model, and then read the saved the .om model file to the memory. For details about the graph APIs, see Graph Development. Allocate memory on the host or device based on where the application runs. For details about the memory allocation APIs, see Memory Management.
model_size	Int, size of the model data in the memory, in bytes.

Parameter

Description

model

Int, pointer address for storing model data.

The model file is built in graph mode. Call aclgrphBundleBuildModel to compile the model, call aclgrphBundleSaveModel to save the model, and then read the saved the .om model file to the memory. For details about the graph APIs, see Graph Development.

Allocate memory on the host or device based on where the application runs. For details about the memory allocation APIs, see Memory Management.

model_size

Int, size of the model data in the memory, in bytes.

Returns

Return Value	Description
bundle_id	Int. After the system successfully loads the model, bundle_id is returned as the flag for identifying the model in subsequent operations.
ret	Int, error code. 0 indicates success, and other values indicate failure.

Parent topic: Model Loading and Unloading