:py:mod:`neural_compressor.algorithm.weight_correction`
=======================================================

.. py:module:: neural_compressor.algorithm.weight_correction

.. autoapi-nested-parse::

   Build FastBiasCorrection algorithm class.



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

Classes
~~~~~~~

.. autoapisummary::

   neural_compressor.algorithm.weight_correction.WeightCorrection




.. py:class:: WeightCorrection(eps=1e-05, channel_axis=1)




   FastBiasCorrection algorithm class.

   Correct INT8 weight distribution close to FP32 weight
   r*(W_int8 + u) -> W_fp32, r is variance ratio between FP32 and INT8
   u is the difference between FP32 and INT8 channel wise, it's equal to minimize:
   round(scale_c * (W_fp32 + shift))/scale - r*(round(scale * W_fp32) + scale*u)/scale
   notice we can only change the first round: round(scale_c * (W_fp32 + shift))
   an empirical solution is to make:
   scale_c = r * scale and shift = u
   with this we don't change the min/max value, and correct the weight.