Fix batch-norm layers in PyTorchYolo._get_losses

[beat-buesser]

Signed-off-by: Beat Buesser [email protected]

Description

This pull request fixes batch-norm layers in PyTorchYolo._get_losses.

Fixes #1859

Type of change

Please check all relevant options.

• Improvement (non-breaking)
• Bug fix (non-breaking)
• New feature (non-breaking)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

[codecov-commenter]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 85.87%. Comparing base (89bf92f) to head (c6df4a1).

❌ Your project status has failed because the head coverage (85.87%) is below the target coverage (90.00%). You can increase the head coverage or adjust the target coverage.

Additional details and impacted files

@@             Coverage Diff             @@
##           dev_1.12.1    #1860   +/-   ##
===========================================
  Coverage       85.87%   85.87%           
===========================================
  Files             248      248           
  Lines           23310    23312    +2     
  Branches         4212     4212           
===========================================
+ Hits            20017    20019    +2     
+ Misses           2230     2229    -1     
- Partials         1063     1064    +1     

Files with missing lines	Coverage Δ
art/estimators/object_detection/pytorch_yolo.py	79.28% <100.00%> (+0.24%)	⬆️

... and 2 files with indirect coverage changes

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.