Skip to content

Conversation

@C-Achard
Copy link
Collaborator

@C-Achard C-Achard commented Mar 24, 2023

PR adding WNet self-supervised model, and overhauled code for models usage

Note : merge to main after #34 has been merged (branch dependency)

  • Run new pre-commit hooks from this branch on main before merging to avoid conflicts
  • Update docs for custom model template
  • Document WNet usage
  • Add notebook for training
    -> WILL BE DONE IN OTHER PR : Improve ONNX support/UI/docs and add pre-trained ONNX model to HF

@C-Achard C-Achard added enhancement New feature or request ML Related to machine learning : MONAI, Torch... labels Mar 24, 2023
@C-Achard C-Achard self-assigned this Mar 24, 2023
@C-Achard C-Achard changed the title WNet + models code refactor [WIP] WNet + models code refactor Mar 24, 2023
@C-Achard C-Achard marked this pull request as draft March 24, 2023 16:44
@codecov-commenter
Copy link

codecov-commenter commented Apr 23, 2023

Codecov Report

Merging #36 (3083705) into main (e00806c) will increase coverage by 8.45%.
The diff coverage is 55.11%.

@@            Coverage Diff             @@
##             main      #36      +/-   ##
==========================================
+ Coverage   59.73%   68.19%   +8.45%     
==========================================
  Files          48       51       +3     
  Lines        4555     5524     +969     
==========================================
+ Hits         2721     3767    +1046     
+ Misses       1834     1757      -77     
Impacted Files Coverage Δ
...ari_cellseg3d/code_models/models/TEMPLATE_model.py 0.00% <0.00%> (ø)
...ari_cellseg3d/code_models/models/model_TRAILMAP.py 0.00% <0.00%> (ø)
...ellseg3d/code_models/models/unet/buildingblocks.py 65.18% <0.00%> (+42.40%) ⬆️
...ri_cellseg3d/code_models/models/wnet/train_wnet.py 0.00% <0.00%> (ø)
napari_cellseg3d/code_plugins/plugin_review.py 77.14% <0.00%> (-0.26%) ⬇️
napari_cellseg3d/dev_scripts/evaluate_labels.py 63.15% <0.00%> (ø)
napari_cellseg3d/code_models/model_framework.py 55.45% <18.75%> (+4.52%) ⬆️
napari_cellseg3d/code_models/workers.py 62.69% <48.96%> (ø)
napari_cellseg3d/_tests/fixtures.py 72.72% <50.00%> (-5.06%) ⬇️
napari_cellseg3d/code_plugins/plugin_crop.py 62.24% <51.85%> (-1.83%) ⬇️
... and 35 more

... and 3 files with indirect coverage changes

📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more

Copy link

@nastya236 nastya236 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

In my opinion, the code is well written. + documentation to all classes!!
Well done! I commented the places in the code which could be (from my personal perspective) done a little bit more flexible.

@C-Achard C-Achard marked this pull request as ready for review June 10, 2023 10:13
@C-Achard C-Achard requested review from MMathisLab and jeylau June 10, 2023 10:26
@C-Achard C-Achard changed the title [WIP] WNet + models code refactor WNet + models code refactor Jun 10, 2023
@MMathisLab MMathisLab requested review from CYHSM and removed request for jeylau June 11, 2023 10:05
@C-Achard C-Achard changed the base branch from cy/voronoi-otsu to main June 11, 2023 10:48
@C-Achard
Copy link
Collaborator Author

@MMathisLab Working on rebase now ! Thanks for the review. And yes, docs will be added, just thought I'd open the code for review

Copy link
Contributor

@CYHSM CYHSM left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code looks good and very clean to me, just added some comments (can also discuss later)

@C-Achard C-Achard merged commit 634f5a4 into main Jul 12, 2023
@C-Achard C-Achard deleted the cy/wnet branch December 5, 2023 14:10
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

enhancement New feature or request ML Related to machine learning : MONAI, Torch...

Projects

None yet

Development

Successfully merging this pull request may close these issues.

6 participants