Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

WIP - Instance Segmentation Experiments #187

Merged
merged 10 commits into from
Dec 20, 2023

Conversation

anwai98
Copy link
Contributor

@anwai98 anwai98 commented Dec 12, 2023

No description provided.

@anwai98 anwai98 marked this pull request as ready for review December 14, 2023 14:31
anwai98 and others added 6 commits December 14, 2023 15:46
Update UNETR model to optionally use skip connections or not
* Update distance transform (#11 - Getting instance segmentations from the distance transform)

* Making the encoder argument flexible (to either pytorch modules or model name as str)
@anwai98
Copy link
Contributor Author

anwai98 commented Dec 20, 2023

@constantinpape This PR makes the following updates and fixes:

  • Updates the postprocessing parameters (subjected to grid search) for distance-based experiments
  • Adds train_by_parts.py, to check for joint and disjoint training experiments
  • Adds a script to check UNETR initialization using different setups
  • Makes the encoder argument in UNETR modular - to accept pytorch modules or model type as str
  • Also makes the use of skip connections flexible.
  • Updates the distance transform, to return instances as well (when expected)

@constantinpape constantinpape merged commit 1409c56 into constantinpape:dev Dec 20, 2023
2 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants