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.

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

关于代码中的bn实现部分的疑问 #83

Open
ghost opened this issue Nov 11, 2020 · 2 comments
Open

关于代码中的bn实现部分的疑问 #83

ghost opened this issue Nov 11, 2020 · 2 comments

Comments

@ghost
Copy link

ghost commented Nov 11, 2020

hist_i = tf.layers.batch_normalization(inputs = hist_i)
如上代码，请问下为什么bn没有设置training参数呢？
@zhougr1993
@GuoshenLi
Copy link

我也觉得肯定有问题的 要有training参数 并且要 updat_ops操作 可能在新版dien有解决吧

@Waydrow
Copy link

Waydrow commented Mar 2, 2021

我也觉得肯定有问题的 要有training参数 并且要 updat_ops操作 可能在新版dien有解决吧

DIEN源码也是这么写的，没有加training参数。不过我测试了一下，发现加上training参数效果反而变差了，有点迷惑...

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@Waydrow @GuoshenLi