Gb/pad bug

[grantbuster]

No description provided.

[bnb32]

Are you using np.pad in your current runs? How much slower is it for training?

[grantbuster]

Are you using np.pad in your current runs? How much slower is it for training?

No i didnt end up using np.pad anywhere because with how many padding ops we have it's just too slow. Still a good option if the model had fewer padding ops or if you wanted to do a single large fwp for any reason.

[codecov-commenter]

Codecov Report

Attention: Patch coverage is 66.66667% with 5 lines in your changes missing coverage. Please review.

Project coverage is 88.52%. Comparing base (c5b0cdb) to head (ff29b5f).

Files with missing lines	Patch %	Lines
phygnn/layers/custom_layers.py	54.54%	5 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main      #54      +/-   ##
==========================================
- Coverage   88.64%   88.52%   -0.13%     
==========================================
  Files          27       27              
  Lines        3329     3337       +8     
==========================================
+ Hits         2951     2954       +3     
- Misses        378      383       +5     

Flag	Coverage Δ
unittests	88.52% <66.66%> (-0.13%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.