yunjey / show-attend-and-tell

TensorFlow Implementation of "Show, Attend and Tell"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Does the computational graph implementation contains hard attention?

Sanqiang opened this issue · comments

Regarding original paper, does the computational graph implementation contains hard attention (includes reinforcement learning)?

@Sanqiang No, it only contains a soft version of the attention.