:py:mod:`neural_compressor.experimental.pruning`
================================================

.. py:module:: neural_compressor.experimental.pruning

.. autoapi-nested-parse::

   Pruning module.



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

Classes
~~~~~~~

.. autoapisummary::

   neural_compressor.experimental.pruning.Pruning
   neural_compressor.experimental.pruning.TfPruningCallback




.. py:class:: Pruning(conf_fname_or_obj=None)




   This is base class of pruning object.

      Since DL use cases vary in the accuracy metrics (Top-1, MAP, ROC etc.), loss criteria
      (<1% or <0.1% etc.) and pruning objectives (performance, memory footprint etc.).
      Pruning class provides a flexible configuration interface via YAML for users to specify
      these parameters.

   :param conf_fname_or_obj: The path to the YAML configuration file or
                             PruningConf class containing accuracy goal, pruning objective and related
                             dataloaders etc.
   :type conf_fname_or_obj: string or obj

   .. attribute:: conf

      A config dict object. Contains pruning setting parameters.

   .. attribute:: pruners

      A list of Pruner object.


.. py:class:: TfPruningCallback(nc_model, input_model, hooks)




   Class that contains callback functions.

   :param nc_model: A neural compression model object.
   :param hooks: A dict. Contains pure-defined hooks.