SamLynnEvans/Transformer

ys = trg[:, 1:].contiguous().view(-1)，why do we have to discard the first seq?

Darleen71 opened this issue · 0 comments

Darleen71 commented

Hello~ may I ask a question？ In this line of code -- ys = trg[:, 1:].contiguous().view(-1)，why do we have to discard the first seq?