what the difference between att_mask and key_padding_mask in MultiHeadAttnetion

This video explains
what the difference between att_mask and key_padding_mask in MultiHeadAttnetion

--

Become part of the top 3% of the developers by applying to Toptal
https://topt.al/25cXVn

--

Music by Eric Matyas
https://www.soundimage.org
Track title: Isolated

--

Chapters
00:00 Question
01:06 Accepted answer (Score 17)
02:17 Answer 2 (Score 1)
03:34 Thank you

--

Full question
https://stackoverflow.com/questions/6262...

Answer 1 links:
[pytorch/functional.py]: https://github.com/pytorch/pytorch/blob/...

--

Content licensed under CC BY-SA
https://meta.stackexchange.com/help/lice...

--

Tags
#python #deeplearning #pytorch #transformermodel #attentionmodel

#avk47