Function: set_config_opt

Applicability

Product	Supported (√/x)
Atlas A3 training products/Atlas A3 inference products	√
Atlas A2 training products/Atlas A2 inference products	√
Atlas training products	√
Atlas inference products	√
Atlas 200I/500 A2 inference products	√

Function Usage

Sets the value of an attribute in the configuration object for loading a model, including the model execution priority, model file directory or memory address, and memory size.

Prototype

C Prototype

aclError aclmdlSetConfigOpt(aclmdlConfigHandle *handle, aclmdlConfigAttr attr, const void *attrValue, size_t valueSize)

Python Function

ret = acl.mdl.set_config_opt(config_handle, attr, attr_value)

Parameter Description

Parameter	Description
config_handle	Int, pointer address to the configuration object for loading a model. Call acl.mdl.create_config_handle to create the pointer address in advance.
attr	Int, attribute to be set. For details about the value, see aclmdlConfigAttr.
attr_value	Int/Str, attribute value. For details about the value, see aclmdlConfigAttr.

Return Value Description

Return Value	Description
ret	Int, error code: 0 on success; else, failure.

Restrictions

This API needs to work with the following APIs to load models:

Call acl.mdl.create_config_handle to create a configuration object for loading a model.
Call acl.mdl.set_config_opt for multiple times to set the value of each attribute in the configuration object.
Call acl.mdl.load_with_config to specify the configuration information for model loading and load your model.
After the model is successfully loaded, call acl.mdl.destroy_config_handle to destroy the configuration object.

Reference

acl.mdl.set_config_opt and acl.mdl.load_with_config, however, are more complicated. The caller needs to 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.

By choosing from the following APIs, you can directly determine whether to load a model from a file or from memory and whether the memory is managed by the system or the user.

Parent topic: Model Loading and Unloading