[neural search] fix the bug of reading files when calculating the recall scores #7836
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
|
Thanks for your contribution! |
|
|
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## develop #7836 +/- ##
===========================================
- Coverage 56.95% 56.95% -0.01%
===========================================
Files 587 587
Lines 88628 88628
===========================================
- Hits 50482 50480 -2
- Misses 38146 38148 +2 ☔ View full report in Codecov by Sentry. |
w5688414
changed the title
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Outdated suggestions cannot be applied.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.
PR types
[ Bug fixes ]
PR changes
[ Scripts ]
Description
For this file 'applications/neural_search/recall/in_batch_negative/evaluate.py'.
If (the number of rows in 'similar_text_pair') mod ('recall_num') doesn't equal 0, the current code will still store the remaining rows in the 'rs' list, resulting in inconsistent list dimensions stored in the 'rs' list. Although it won't raise errors, logically there are some problems.
In this file 'applications/neural_search/recall/simcse/evaluate.py'.
The current loop will not save the last 'relevance_labels' list into the 'rs' list.
Therefore, the corrected code can be applied to the above two files. Besides, I think the issue should be similar for the following files:
examples/semantic_indexing/evaluate.py
applications/question_answering/supervised_qa/faq_system/evaluate.py
applications/question_answering/supervised_qa/faq_finance/evaluate.py
applications/text_classification/multi_class/retrieval_based/evaluate.py
applications/text_classification/hierarchical/retrieval_based/evaluate.py
I hadn't modified these files because I didn't check the usage in their modules. Please check those files. Thanks.