IBP Loss Weighting

[GiulioZizzo]

Description

We fix an issue where the default value for a loss weighting parameter was being used rather than user supplied inputs in certain situations. Further, we add additional input checking to the ibp trainer.

Fixes #2102

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

Testing

Existing tests pass

Test Configuration:

• OS: Mac OS
• Python version: 3.8
• ART version or commit number: 1.14
• Pytorch 1.13.1

Checklist

• My code follows the style guidelines of this project
• I have performed a self-review of my own code
• I have commented my code
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes

[codecov-commenter]

Codecov Report

Merging #2112 (bbeae7d) into dev_1.14.1 (6a8d734) will decrease coverage by 8.33%.
The diff coverage is 0.00%.

📣 This organization is not using Codecov’s GitHub App Integration. We recommend you install it so Codecov can continue to function properly for your repositories. Learn more

@@              Coverage Diff               @@
##           dev_1.14.1    #2112      +/-   ##
==============================================
- Coverage       85.64%   77.32%   -8.33%     
==============================================
  Files             297      297              
  Lines           26506    26512       +6     
  Branches         4861     4864       +3     
==============================================
- Hits            22701    20500    -2201     
- Misses           2568     4908    +2340     
+ Partials         1237     1104     -133     

Impacted Files	Coverage Δ
.../defences/trainer/ibp_certified_trainer_pytorch.py	75.00% <0.00%> (-3.17%)	⬇️

... and 28 files with indirect coverage changes

[beat-buesser]

Hi @GiulioZizzo Thank you very much, looks good to me.