-
Notifications
You must be signed in to change notification settings - Fork 20
[WIP] Adding SwinUNetR #12
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
Conversation
Codecov Report
@@ Coverage Diff @@
## main #12 +/- ##
==========================================
+ Coverage 37.34% 37.71% +0.37%
==========================================
Files 37 38 +1
Lines 3449 3500 +51
==========================================
+ Hits 1288 1320 +32
- Misses 2161 2180 +19
📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more |
|
Preview page for your plugin is ready here: |
|
@vidalmaxime can you fix merge conflicts? |
C-Achard
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Just a few comments on the PR @vidalmaxime :) Thanks for the work on the models
57d79ed to
b1be111
Compare
…xed padding only for sliding window inference
Removed draft of TRAILMAP port to Pytorch
- Fixed model instantiation - Fix window overlap argument type error - Updated reqs.txt to have einops (MONAI optional dep.)
- Added overlap parameter for window - Improved UI code slightly
|
Should be ready for review @vidalmaxime, if you could maybe test it quickly some time just to make sure everything is fine, that'd be great |
…xed padding only for sliding window inference
Removed draft of TRAILMAP port to Pytorch
- Fixed model instantiation - Fix window overlap argument type error - Updated reqs.txt to have einops (MONAI optional dep.)
- Added overlap parameter for window - Improved UI code slightly
da713e5 to
1030581
Compare
…ontrolLab/CellSeg3d into feature/swinunetr
Removed padding transform when using single layer inference and the sliding window inference option
Prepared for SWIN download
- Fixed error in training : get_net erroneous call
|
@vidalmaxime I think this is ready for merging into main - should we do a new rc on PyPi with the recently added features ? |
|
yes, let's make a new pypi, so new PR with the version bumped up! |
(WIP) This PR aims to
Add SwinUNetR to the modelzoo
Remove extra padding during inference which can worsen the predictions when using window inference
Removed old TRAILMAP copy