Enhance Clip_Score to calculate similarities between same modalities
#2875
+327
−69
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
rittik9
requested review from
SkafteNicki,
Borda,
justusschock and
stancld
as code owners
for more information, see https://pre-commit.ci
rittik9
changed the title
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## master #2875 +/- ##
========================================
- Coverage 69% 32% -37%
========================================
Files 346 332 -14
Lines 19142 18995 -147
========================================
- Hits 13230 6056 -7174
- Misses 5912 12939 +7027 |
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
Borda
approved these changes
Jan 7, 2025
for more information, see https://pre-commit.ci
|
@Borda I am planning to add some tests for new feature (calculate clip score in same modality). I am trying to understand how the reference metric should be. |
This reverts commit 81b4405.
rittik9
changed the title
Clip_Score to calculate similarities between same modalities [WIP]Clip_Score to calculate similarities between same modalities
rittik9
commented
Jan 10, 2025
|
|
||
| txt_features = model.get_text_features( | ||
| processed_input["input_ids"].to(device), processed_input["attention_mask"].to(device) | ||
| device = torch.device("cpu") |
There was a problem hiding this comment.
@Borda I changed this device assigning part a little bit. Can you please check it once..
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Outdated suggestions cannot be applied.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?
Fixes #2865
Before submitting
PR review
Anyone in the community is free to review the PR once the tests have passed.
If we didn't discuss your PR in Github issues there's a high chance it will not be merged.
Did you have fun?
Make sure you had fun coding 🙃
📚 Documentation preview 📚: https://torchmetrics--2875.org.readthedocs.build/en/2875/