neural_compressor.compression.pruner
====================================

.. py:module:: neural_compressor.compression.pruner

.. autoapi-nested-parse::

   Pruning init.



Subpackages
-----------

.. toctree::
   :maxdepth: 1

   /autoapi/neural_compressor/compression/pruner/model_slim/index
   /autoapi/neural_compressor/compression/pruner/patterns/index
   /autoapi/neural_compressor/compression/pruner/pruners/index
   /autoapi/neural_compressor/compression/pruner/wanda/index


Submodules
----------

.. toctree::
   :maxdepth: 1

   /autoapi/neural_compressor/compression/pruner/criteria/index
   /autoapi/neural_compressor/compression/pruner/pruning/index
   /autoapi/neural_compressor/compression/pruner/regs/index
   /autoapi/neural_compressor/compression/pruner/schedulers/index
   /autoapi/neural_compressor/compression/pruner/tf_criteria/index
   /autoapi/neural_compressor/compression/pruner/utils/index


Functions
---------

.. autoapisummary::

   neural_compressor.compression.pruner.save
   neural_compressor.compression.pruner.prepare_pruning


Package Contents
----------------

.. py:function:: save(obj: object, f, pickle_module=None, pickle_protocol=None, _use_new_zipfile_serialization=None)

   A rewrite function for torch save.

   :param obj:
   :param f:
   :param pickle_module:
   :param pickle_protocol:
   :param _use_new_zipfile_serialization:
   :return:


.. py:function:: prepare_pruning(model, config, optimizer=None, dataloader=None, loss_func=None, framework='pytorch', device: str = None)

   Get registered pruning class, wrapper the model and optimizer to support all the pruning functionality.

   Get a pruning object from PRUNINGS.

   :param modules: A dict {"module_name": Tensor} that stores the pruning modules' weights.
   :param config: A config dict object that contains the pruners information.

   :returns: A pruning object.

   Raises: AssertionError: Currently only support prunings that have been registered in PRUNINGS.