last_update

[JairMathAI]

I have made some minor fixes to enable correct training with both 2D and 3D images for the Probabilistic U-Net architecture. I also included a more robust implementation of the model to be used with regularizers. I am keeping the previous version for now to maintain compatibility with the SV project so Phillip can still run predictions; however, once the latest models are finalized, this older implementation will be removed.

[codecov-commenter]

Codecov Report

❌ Patch coverage is 10.97852% with 373 lines in your changes missing coverage. Please review.
✅ Project coverage is 16.55%. Comparing base (ba85ae2) to head (6448028).
⚠️ Report is 31 commits behind head on main.

Files with missing lines	Patch %	Lines
mmv_im2im/models/pl_ProbUnet_old.py	0.00%	81 Missing ⚠️
mmv_im2im/models/pl_nnUnet.py	0.00%	77 Missing ⚠️
mmv_im2im/utils/misc.py	2.59%	75 Missing ⚠️
mmv_im2im/utils/nnHeuristic.py	6.97%	40 Missing ⚠️
mmv_im2im/utils/elbo_loss.py	50.00%	25 Missing and 12 partials ⚠️
mmv_im2im/models/nets/ProbUnet.py	0.00%	16 Missing ⚠️
mmv_im2im/models/pl_ProbUnet.py	0.00%	15 Missing ⚠️
mmv_im2im/proj_trainer.py	7.69%	12 Missing ⚠️
mmv_im2im/models/pl_FCN.py	0.00%	9 Missing ⚠️
mmv_im2im/proj_tester.py	16.66%	5 Missing ⚠️
... and 2 more

Additional details and impacted files

@@            Coverage Diff             @@
##            main     #120       +/-   ##
==========================================
+ Coverage   4.40%   16.55%   +12.15%     
==========================================
  Files         36       53       +17     
  Lines       2815     5465     +2650     
  Branches       0      901      +901     
==========================================
+ Hits         124      905      +781     
- Misses      2691     4416     +1725     
- Partials       0      144      +144     

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

🚀 New features to boost your workflow:

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