:py:mod:`neural_compressor.experimental.pytorch_pruner.prune_utils`
===================================================================

.. py:module:: neural_compressor.experimental.pytorch_pruner.prune_utils

.. autoapi-nested-parse::

   Prune utils.



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


Functions
~~~~~~~~~

.. autoapisummary::

   neural_compressor.experimental.pytorch_pruner.prune_utils.check_config
   neural_compressor.experimental.pytorch_pruner.prune_utils.reset_non_value_to_default
   neural_compressor.experimental.pytorch_pruner.prune_utils.process_and_check_config
   neural_compressor.experimental.pytorch_pruner.prune_utils.process_config
   neural_compressor.experimental.pytorch_pruner.prune_utils.parse_to_prune
   neural_compressor.experimental.pytorch_pruner.prune_utils.parse_not_to_prune



.. py:function:: check_config(prune_config)

   Functions that check key-value is valid to run Pruning object.

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

   :returns: None if everything is correct.

   :raises AssertionError.:


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

   Functions that add up undefined configurations.

   If some configurations are not defined in the configuration, set it to a default value.

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


.. py:function:: process_and_check_config(val)

   Functions which converts a initial configuration object to a Pruning configuration.

   Copy parameters and add some non-define parameters to a new Pruning configuration object.

   :param val: A dict directly read from a config file.

   :returns: A dict whose contents which are regularized for a Pruning object.


.. py:function:: process_config(config)

   Obtain a config dict object from a config file.

   :param config: A string. The path to configuration file.

   :returns: A config dict object.


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

   Keep target pruned layers.


.. py:function:: parse_not_to_prune(modules, config)

   Drop non pruned layers.