:py:mod:`neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.dequantize_cast_optimizer`
==========================================================================================

.. py:module:: neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.dequantize_cast_optimizer

.. autoapi-nested-parse::

   Dequantize Cast Graph Rerewriter.



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

Classes
~~~~~~~

.. autoapisummary::

   neural_compressor.adaptor.tf_utils.graph_rewriter.bf16.dequantize_cast_optimizer.DequantizeCastOptimizer




.. py:class:: DequantizeCastOptimizer(model)




   Remove the Cast OP and set Dequantize output to B16 if the Cast OP output is BF16.