fix: if layers == 0, layers were not initialized#306
Open
stephantul wants to merge 4 commits intoMinishLab:mainfrom
Open
fix: if layers == 0, layers were not initialized#306stephantul wants to merge 4 commits intoMinishLab:mainfrom
stephantul wants to merge 4 commits intoMinishLab:mainfrom
Conversation
Codecov Report✅ All modified and coverable lines are covered by tests.
🚀 New features to boost your workflow:
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
While working on a classifier with no hidden layers, I saw that linear layers were not initialized properly if n_layers == 0. The short circuiting was returning a linear with default initialization, which happens to be kaiming anyway.
Not a big deal, but just for consistency. I also initialized to xavier_uniform for the final layer, because this could help (that is, kaiming init is often used for relu, xavier for linear or tanh), although I didn't see any difference on 20 newsgroups.