:py:mod:`neural_compressor.pruner.utils`
========================================

.. py:module:: neural_compressor.pruner.utils

.. autoapi-nested-parse::

   prune utils.



Module Contents
---------------


Functions
~~~~~~~~~

.. autoapisummary::

   neural_compressor.pruner.utils.check_config
   neural_compressor.pruner.utils.reset_none_to_default
   neural_compressor.pruner.utils.update_params
   neural_compressor.pruner.utils.process_weight_config
   neural_compressor.pruner.utils.process_yaml_config
   neural_compressor.pruner.utils.check_key_validity
   neural_compressor.pruner.utils.process_and_check_config
   neural_compressor.pruner.utils.process_config
   neural_compressor.pruner.utils.parse_to_prune



.. py:function:: check_config(prune_config)

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

   :param prune_config: A config dict object that contains Pruning parameters and configurations.

   :returns: None if everything is correct.

   :raises AssertionError.:


.. py:function:: reset_none_to_default(obj, key, default)

   Set undefined configurations to default values.

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


.. py:function:: update_params(info)

   Update parameters.


.. py:function:: process_weight_config(global_config, local_configs, default_config)

   Process pruning configurations.

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

   :returns: A config dict object that contains pruning parameters and configurations.
   :rtype: pruners_info


.. py:function:: process_yaml_config(global_config, local_configs, default_config)

   Process the yaml configuration file.

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

   :returns: A config dict object that contains pruning parameters and configurations.
   :rtype: pruners_info


.. py:function:: check_key_validity(template_config, user_config)

   Check the validity of keys.

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


.. py:function:: process_and_check_config(val)

   Process and check configurations.

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


.. py:function:: process_config(config)

   Obtain a config dict object from the config file.

   :param config: A string representing the path to the configuration file.

   :returns: A config dict object.


.. py:function:: parse_to_prune(config, model)

   Keep target pruned layers.

   :param config: A string representing the path to the configuration file.
   :param model: The model to be pruned.