:py:mod:`neural_compressor.experimental.data.filters.filter`
============================================================

.. py:module:: neural_compressor.experimental.data.filters.filter

.. autoapi-nested-parse::

   The base filter class for all frameworks.



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

Classes
~~~~~~~

.. autoapisummary::

   neural_compressor.experimental.data.filters.filter.TensorflowFilters
   neural_compressor.experimental.data.filters.filter.ONNXRTQLFilters
   neural_compressor.experimental.data.filters.filter.ONNXRTITFilters
   neural_compressor.experimental.data.filters.filter.PyTorchFilters
   neural_compressor.experimental.data.filters.filter.MXNetFilters
   neural_compressor.experimental.data.filters.filter.FILTERS
   neural_compressor.experimental.data.filters.filter.Filter



Functions
~~~~~~~~~

.. autoapisummary::

   neural_compressor.experimental.data.filters.filter.filter_registry



.. py:class:: TensorflowFilters




   The base filter class for Tensorflow framework.


.. py:class:: ONNXRTQLFilters




   The base filter class for ONNXRT framework QLinear mode.


.. py:class:: ONNXRTITFilters




   The base filter class for ONNXRT framework IT mode.


.. py:class:: PyTorchFilters




   The base filter class for PyTorch framework.


.. py:class:: MXNetFilters




   The base filter class for MXNet framework.


.. py:class:: FILTERS(framework)




   The filter register for all frameworks.

   :param framework: frameworks in ["tensorflow", "tensorflow_itex", "mxnet",
                     "onnxrt_qdq", "pytorch", "pytorch_ipex",
                     "pytorch_fx", "onnxrt_integerops", "keras"
                     "onnxrt_qlinearops", "onnxruntime"].
   :type framework: str


.. py:function:: filter_registry(filter_type, framework)

   Register all transform subclasses.

   :param filter_type: fILTER registration name.
   :type filter_type: str
   :param framework: support 4 framework including 'tensorflow', 'pytorch', 'mxnet', 'onnxrt'.
   :type framework: str
   :param cls: The class of register.
   :type cls: class

   :returns: The class of register.
   :rtype: cls


.. py:class:: Filter




   The base class for transform.

   __call__ method is needed when write user specific transform.