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.

Sign up for GitHub

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

Jump to bottom

Further enhance DynUNet via removing unused parts #3293

Closed
yiheng-wang-nv opened this issue Nov 9, 2021 · 1 comment · Fixed by #3427
Closed

Further enhance DynUNet via removing unused parts #3293

yiheng-wang-nv opened this issue Nov 9, 2021 · 1 comment · Fixed by #3427
Assignees
@yiheng-wang-nv
Labels
Feature request

Comments

@yiheng-wang-nv
Copy link
Contributor

In current implementation, no matter deep_supervision is used, the corresponding heads will be used. In addition, extra heads may be maintained, when deep_supr_num is less than the number of up sample layer - 1. It may also be related with Project-MONAI/MONAILabel#492

I planned to change it within #3265 , but it brought breaking changes (574fe60) and may make users' old weights cannot be used.

Therefore, here I open another ticker, and I will do a further enhancement.
@yiheng-wang-nv
Copy link
Contributor Author

FYI @wyli @Nic-Ma @SachidanandAlle

@yiheng-wang-nv yiheng-wang-nv self-assigned this Nov 9, 2021
@yiheng-wang-nv yiheng-wang-nv mentioned this issue Dec 1, 2021
Merged
6 tasks
@wyli wyli closed this as completed in #3427 Dec 7, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@yiheng-wang-nv yiheng-wang-nv

Labels
Feature request
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

3293 Remove extra deep supervision modules of DynUNet yiheng-wang-nv/MONAI
1 participant
@yiheng-wang-nv