Skip to content
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.

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

老师您好,关于chapter5_RNN/time-series里面时间序列预测代码的问题 #40

Open
wmathor opened this issue Feb 29, 2020 · 1 comment

Comments

@wmathor
Copy link

wmathor commented Feb 29, 2020

第四个代码块"数据预处理"部分,最后一行,标准化不应该是(x-min_value)/(scalar)吗,为什么您的代码里没有减min_value

@ligeng0197
Copy link

确实, 老师这里没有减. 刚好我也看到这里了. 我觉得没有减的话放缩范围就变成了[min/scalar,1+min/scalar], 原LSTM输出隐藏状态h受tanh函数影响取值范围为[-1,1], 但是例子中最后有线性层将LSTM输出放大, 所以即使没有减也不太会影响性能.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants