Question：multihead_attention()’s output and ff()‘s output need dropout？ - Githubissues

Kyubyong / transformer

A TensorFlow Implementation of the Transformer: Attention Is All You Need

Apache License 2.0

4.28k stars 1.3k forks source link

Question：multihead_attention()’s output and ff()‘s output need dropout？ #169

Open codefish1990 opened 3 years ago

codefish1990 commented 3 years ago

Question：multihead_attention()’s output and ff()‘s output need dropout？