https://zhuanlan.zhihu.com/p/39034683
http://nlp.seas.harvard.edu/2018/04/03/attention.html#batches-and-masking
https://jalammar.github.io/illustrated-transformer/
https://www.jiqizhixin.com/articles/2018-06-11-17
https://blog.csdn.net/lipengcn/article/details/85313971
网友评论