Support for lecun normal weight initialization #2311
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 ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## master #2311 +/- ##
==========================================
- Coverage 79.47% 77.42% -2.05%
==========================================
Files 31 31
Lines 1749 1750 +1
==========================================
- Hits 1390 1355 -35
- Misses 359 395 +36 ☔ View full report in Codecov by Sentry. |
mcabbott
reviewed
Oct 26, 2024
CarloLucibello
approved these changes
Oct 26, 2024
mcabbott
added a commit
that referenced
this pull request
Nov 1, 2024
* Support for lecun normal weight initialization * add test * add to docs * Update utils.jl * fixup * fix rtol * doctests --------- Co-authored-by: Michael Abbott <32575566+mcabbott@users.noreply.github.com>
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Outdated suggestions cannot be applied.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.
feat: Add LeCun normal weight initialization
lecun_normalfunction for weight initialization based on fan-in.lecun_normalas non-differentiable using ChainRulesCore.It resolves issue #2290
[Edit: closes #2290, closes #2491, closes #2299]
PR Checklist