Conversation
There was a problem hiding this comment.
Pull request overview
Fixes a bug where AI-predicted pixels were being incorrectly marked as user-drawn pixels during legacyPredictMask(), causing the user mask view to be overwritten by predictions after training.
Changes:
- Stops writing AI prediction pixels into the user mask data during prediction application.
- Removes the unnecessary
newUserMaskDatacopy and related post-update verification/logging.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
|
Codecov Report✅ All modified and coverable lines are covered by tests. 🚀 New features to boost your workflow:
|
rfievet
approved these changes
Apr 7, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Hotfix for issue I noticed during some testing. After annotating pixels, then training, the AI predictions would be incorrectly included in the user mask, and not only the final mask.
This PR fixes the problem by stopping the writing of those pixels to the newUserMaskData. In fact, newUserMaskData is not necessary at all in the legacyPredictMask() function, as predictions will never influence the user mask.
To reproduce error in code prior to hotfix:
(i) reset mask (remove all user and ai pixels)
(ii) draw pixels of 2 classes (observe the user mask correctly visualises the brushstrokes)
(iii)train AI model
(iv) observe user mask again, which will now be filled with all the AI's predictions, filling in the whole image around the user's annotations