Skip to content

Fix parsing of QConv2DBatchnorm weights

Javier Duarte requested to merge github/fork/vloncar/conv_bn_fix into main

Created by: vloncar

Description

With the recent reorganization of code in the Keras converter, we missed parsing the QConv2DBatchnorm's weights. The fix is a one liner.

Type of change

  • Bug fix (non-breaking change that fixes an issue)

Tests

There's a test added to test_qkeras.py

Checklist

  • I have read the guidelines for contributing.
  • I have commented my code, particularly in hard-to-understand areas.
  • I have made corresponding changes to the documentation.
  • My changes generate no new warnings.
  • I have installed and run pre-commit on the files I edited or added.
  • I have added tests that prove my fix is effective or that my feature works.

Merge request reports

Loading