search

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

droupout rate in paper is 0.1, but there is 0.3 #113

Open xiongma opened 5 years ago

xiongma commented 5 years ago

@Kyubyong droupout rate in paper is 0.1, but there is 0.3, is any different between you and paper?

paper: image