facebookresearch/fairseq
Auf GitHub ansehenkey_padding_mask is not used in transformer decoder layer?
Open
#537 geöffnet am 27. Feb. 2019
bughelp wanted
Repository-Metriken
- Stars
- (29.107 Stars)
- PR-Merge-Metriken
- (Keine gemergten PRs in 30 T)
Beschreibung
when reading the source code i found that key_padding_mask is not used when calculating self attention. There is no problem when the target is padded right by default because attn_mask could do the same thing. But how about left padding on the target?