Use NNlib's within_gradient
#2152
Merged
Conversation
This file contains 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
Codecov ReportBase: 86.79% // Head: 83.50% // Decreases project coverage by
Additional details and impacted files@@ Coverage Diff @@
## master #2152 +/- ##
==========================================
- Coverage 86.79% 83.50% -3.30%
==========================================
Files 19 19
Lines 1477 1479 +2
==========================================
- Hits 1282 1235 -47
- Misses 195 244 +49
Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here. ☔ View full report at Codecov. |
CarloLucibello
approved these changes
Jan 6, 2023
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Outdated suggestions cannot be applied.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.
Uses FluxML/NNlib.jl#434
Planned to fix issue #2122, but doesn't! This is because ForwardDiff's chunk mode runs the model several times, and each of them updates the history within BatchNorm. Sounds pretty tricky to solve.
But with FluxML/Tracker.jl#136, BatchNorm should work with Tracker. Ideally we'd have multi-AD tests... not here though.