Repository navigation
Support Conv1d and Conv3d weights in Adahessian trace - #547
Open
shaneraphel wants to merge 1 commit into
Open
shaneraphel wants to merge 1 commit into
shaneraphel wants to merge 1 commit into
Conversation
get_trace averaged the Hessian diagonal over the spatial dims only for 4D kernels. Conv1d (3D) and Conv3d (5D) weights left tmp_output unbound. Average over dims 2..ndim-1 instead; 4D is unchanged.
This branch has not been deployed
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Adahessian.get_traceaveraged the Hessian diagonal over the spatial dims only when the weight was 4D. AConv1d(3D) orConv3d(5D) weight lefttmp_outputunbound andstep()raisedUnboundLocalError.The trace now averages
hv.abs()over dims2..ndim-1withkeepdim=True. For 4D that is exactly dims[2, 3], soConv2dis unchanged.Fixes #500.
Test plan
pytest tests/test_adahessian_conv.py: Conv1d, Conv2d, and Conv3d each take a step; the 4D generic mean equals the old explicit dimspytest tests/test_basic.py -k Adahessian: 3 passed