Fix vqa loss #86
Open
Fix vqa loss #86
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
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Outdated suggestions cannot be applied.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.
VQA loss is not decreasing during training, we have tried several ways to reduce it, this is one of the tests.
So far we have been following GATO paper to place all text (including VQA question and answer) to the left of separator.
In this PR, we are doing a test to place the question to the left of the separator and place the answer to the right of the separator during training, and see whether that can reduce the VQA loss.
So far, the test has shown that it cannot reduce VQA loss.
This PR is created to track this issue and solicit code review and see whether we find a solution to reduce the VQA loss