New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

关于注意力机制初始状态的问题 #130

Open

JingyeChen opened this issue Mar 26, 2020 · 1 comment

JingyeChen commented Mar 26, 2020

请问一下~在代码里面我看到您的注意力模型初始状态是全0

hidden = Variable(torch.zeros(nB,hidden_size).type_as(feats.data))
(asrn_res.py 106行)

注意力模型作为一个解码器，那么初始状态是不是应该设定为编码器的末状态呢
（不过我用全0初始状态跑代码，效果也挺棒的233）

Owner

Canjie-Luo commented Apr 16, 2020

理论上都是可以的，您可以试一试～

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment