Added Support for Returning Attention Scores in TransformerEncoder call #1879
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Outdated suggestions cannot be applied.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: This pull request introduces a new feature that adds support for optionally returning attention scores in the
TransformerEncoder
class. This is controlled by thereturn_attention_scores
flag, which when set toTrue
, returns both the output and the attention scores from the attention mechanism.Changes Introduced:
TransformerEncoder
to handle thereturn_attention_scores
flag.call
method to reflect the changes.Testing:
Ran the unit tests to verify that the
return_attention_scores
flag works as expected.return_attention_scores=True
(verifies that attention scores are returned and the shapes are correct).Related Issue: #1644