We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
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
在RNN+ATTENTION的model中为什么直接用targets来作为Decoder的Input来训练啊?用每一个时间步(程序中的di)的hidden来作为下一步的input吗?
The text was updated successfully, but these errors were encountered:
decoder的每一步的input用的是上一步预测位置的真实标签(target),
Sorry, something went wrong.
训练的时候这样可以理解,但是为什么evaluate的时候第一步也要输入真实标签呢,测试的时候不是没有真实标签的吗?
evaluate的时候第一个输入taget[:,0]是一个表示开始的标志位呀,不是真实标签。就是说在数据预处理的时候已经在所有样本的第一位添加了一个特殊标识符,所以测试也是没问题的
No branches or pull requests
在RNN+ATTENTION的model中为什么直接用targets来作为Decoder的Input来训练啊?用每一个时间步(程序中的di)的hidden来作为下一步的input吗?
The text was updated successfully, but these errors were encountered: