[CLIP] fix logit_scale init #13436
Merged
[CLIP] fix logit_scale init #13436
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
patrickvonplaten
approved these changes
Sep 6, 2021
sgugger
approved these changes
Sep 6, 2021
patil-suraj
force-pushed
the
fix-logit-scale-init
branch
from
3eb4bc4
to
e496de0
Compare
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Outdated suggestions cannot be applied.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.
What does this PR do?
This PR fixes the initialization of
logit_scaleparameter as per the original CLIP implementation .Also, the initial value of
logit_scaleneeds to be carefully tuned for CLIP training, so this PR, adds alogit_scale_init_valueas aconfigparameter, so users could pass different init values as per their training.Fixes #13430