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

Add Monai's UNETR #155

Merged
merged 7 commits into from
Oct 18, 2023
Merged

Add Monai's UNETR #155

merged 7 commits into from
Oct 18, 2023

Conversation

anwai98
Copy link
Contributor

@anwai98 anwai98 commented Oct 16, 2023

  • Benchmarking from monai's unetr implementation
  • In experiments/vision-transformer/unetr/results, the row headers are the source models, and the column headers are for the cell-type-wise inference

PS: models from torch-em and monai (both training from scratch) have been tried for 10k iterations for two cell types

@anwai98
Copy link
Contributor Author

anwai98 commented Oct 18, 2023

@constantinpape We finally have the benchmarking results. The script now looks good to go (the negative values occured how, I am not sure - but they were with a pretty shallow training - for 1k iterations previously). The current results are with 100k iterations (more details of the training heuristic in the sheet linked above)

@anwai98 anwai98 marked this pull request as ready for review October 18, 2023 11:31
@@ -225,6 +236,7 @@ def main(args):
source_choice=args.source_choice
)

# FIXME this is wrong for the MONAI models
Copy link
Owner

Choose a reason for hiding this comment

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

@anwai98 This should have never worked for the monai unetrs.

@constantinpape constantinpape merged commit e3d9e2e into constantinpape:main Oct 18, 2023
0 of 2 checks passed
@anwai98 anwai98 deleted the rf-unetr branch November 7, 2023 23:59
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