Fix parsing of QConv2DBatchnorm weights

[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.