mask missing in ScaledDotProductAttention call#8
Open
thierryherrmann wants to merge 1 commit intokeitakurita:masterfrom
Open
mask missing in ScaledDotProductAttention call#8thierryherrmann wants to merge 1 commit intokeitakurita:masterfrom
thierryherrmann wants to merge 1 commit intokeitakurita:masterfrom
Conversation
This file contains hidden or 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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
I'm a newbie in attention mechanisms but I think the
maskarg is missing when calling the ScaledDotProductAttention block.Also I noticed in github the right args are passed in the
DecoderBlockwhen calling the 2ndMultiHeadAttention:att = self.attn_head(queries=x, keys=enc_out, values=enc_out, mask=tgt_mask)but in the blog, it's still:
att = self.attn_head(queries=att, keys=x, values=x, mask=tgt_mask)It would be nice to fix it too there.
Kudos for your fanstastic blog! Enlightening!