fix: make label smoothing delta configurable#12
Open
harens wants to merge 1 commit into
Open
Conversation
Thread the ContextBuilder delta parameter through training so LabelSmoothing no longer receives a hardcoded value. Pass the existing CLI --delta option into ContextBuilder.fit and expose delta on fit_predict and the DeepCASE wrapper methods. Document the delta parameter in the code usage example.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Thread the label smoothing
deltaparameter through DeepCASE training so it is configurable instead of hardcoded.Changes
--deltaintoContextBuilder.fitdeltatoContextBuilder.fit_predictdeltaon DeepCASE wrapper methodsdeltawhen constructingLabelSmoothingdeltain the usage exampleWhy
Previously,
LabelSmoothingalways received a hardcoded value of0.1, even though a CLI--deltaoption already existed. This change makes training behaviour consistent with the exposed interface and allows callers to tune label smoothing explicitly.Notes
deltastill defaults to0.1deltais provided