Refactor gaze prediction pipeline and add Euclidean accuracy metric#52
Merged
jvJUCA merged 2 commits intoruxailab:mainfrom Feb 11, 2026
Merged
Refactor gaze prediction pipeline and add Euclidean accuracy metric#52jvJUCA merged 2 commits intoruxailab:mainfrom
jvJUCA merged 2 commits intoruxailab:mainfrom
Conversation
…metrics calculations
…metrics calculations
jvJUCA
approved these changes
Feb 11, 2026
Member
jvJUCA
left a comment
jvJUCA
left a comment
There was a problem hiding this comment.
Thanks for the improvements, your changes will be merged!
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
This PR addresses the issues described in #51 by refactoring the gaze prediction pipeline and improving evaluation metrics.
What’s Changed
Refactored the ML training and prediction workflow to improve structure and correctness
Fixed scaling logic to prevent train/test data leakage
Centralized model training logic to remove duplication
Added a new Euclidean (pixel-based) accuracy metric via func_total_accuracy
Improved evaluation clarity by separating axis-based precision from spatial accuracy
Why This Matters
Prevents subtle evaluation bugs caused by data leakage
Makes model performance easier to interpret and compare
Provides a metric that reflects real gaze error in screen space
Improves code maintainability and extensibility
Related Issue
Fixes #51