facebookresearch/fairseq

key_padding_mask is not used in transformer decoder layer?

Open

#537 geöffnet am 27. Feb. 2019

Auf GitHub ansehen
 (1 Kommentar) (0 Reaktionen) (0 zugewiesene Personen)Python (6.224 Forks)batch import
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?

Contributor Guide