`neural_compressor.pruner.utils`¶

prune utils.

Module Contents¶

`check_config`(prune_config)	Check if the configuration dict is valid for running Pruning object.
`reset_none_to_default`(obj, key, default)	Set undefined configurations to default values.
`update_params`(info)	Update parameters.
`process_weight_config`(global_config, local_configs, ...)	Process pruning configurations.
`process_yaml_config`(global_config, local_configs, ...)	Process the yaml configuration file.
`check_key_validity`(template_config, user_config)	Check the validity of keys.
`process_and_check_config`(val)	Process and check configurations.
`process_config`(config)	Obtain a config dict object from the config file.
`parse_to_prune`(config, model)	Keep target pruned layers.

neural_compressor.pruner.utils.check_config(prune_config)¶

Check if the configuration dict is valid for running Pruning object.

Parameters:: prune_config – A config dict object that contains Pruning parameters and configurations.
Returns:: None if everything is correct.
Raises:: AssertionError. –

neural_compressor.pruner.utils.reset_none_to_default(obj, key, default)¶

Set undefined configurations to default values.

Parameters:

obj – A dict{key: value}
key – A string representing the key in obj.
default – When the key is not in obj, add key by the default item in original obj.

neural_compressor.pruner.utils.process_weight_config(global_config, local_configs, default_config)¶

Process pruning configurations.

Parameters:

global_config – A config dict object that contains pruning parameters and configurations.
local_config – A config dict object that contains pruning parameters and configurations.
default_config – A config dict object that contains pruning parameters and configurations.

Returns:

A config dict object that contains pruning parameters and configurations.

Return type:

pruners_info

neural_compressor.pruner.utils.process_yaml_config(global_config, local_configs, default_config)¶

Process the yaml configuration file.

Parameters:

global_config – A config dict object that contains pruning parameters and configurations.
local_config – A config dict object that contains pruning parameters and configurations.
default_config – A config dict object that contains pruning parameters and configurations.

Returns:

A config dict object that contains pruning parameters and configurations.

Return type:

pruners_info

neural_compressor.pruner.utils.check_key_validity(template_config, user_config)¶

Check the validity of keys.

Parameters:

template_config – A default config dict object that contains pruning parameters and configurations.
user_config – A user config dict object that contains pruning parameters and configurations.

neural_compressor.pruner.utils.process_and_check_config(val)¶

Process and check configurations.

Parameters:: val – A dict that contains the layer-specific pruning configurations.

neural_compressor.pruner.utils.process_config(config)¶

Obtain a config dict object from the config file.

Parameters:: config – A string representing the path to the configuration file.
Returns:: A config dict object.

neural_compressor.pruner.utils.parse_to_prune(config, model)¶

Keep target pruned layers.

Parameters: