facebookresearch/fairseq
Ver no GitHubkey_padding_mask is not used in transformer decoder layer?
Open
#537 aberto em 27 de fev. de 2019
bughelp wanted
Métricas do repositório
- Stars
- (29.107 stars)
- Métricas de merge de PR
- (Nenhuma PRs mesclada em 30d)
Description
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?