Fix RMS spot size calculation order#105
Merged
singer-yang merged 1 commit intovccimaging:devfrom Feb 6, 2026
Merged
Conversation
RMS = sqrt(mean(x^2)), but the code was computing mean(sqrt(x^2)). Apply sqrt after averaging across rays, not before. Also add EPSILON inside sqrt in training loss paths to prevent NaN gradients from sqrt(0) when field points have zero valid rays. Fixes vccimaging#102 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
sqrt(mean(x^2))instead ofmean(sqrt(x^2))ingeolens.py,optim.py, and2_autolens_rms.pyEPSILONinsidesqrtin training loss paths to prevent NaN gradients fromsqrt(0)when field points have zero valid raysFixes #102
🤖 Generated with Claude Code