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

Disable cudnn for batch norm是基于什么考虑 #11

Closed
janicevidal opened this issue Nov 16, 2018 · 3 comments
Closed

Disable cudnn for batch norm是基于什么考虑 #11

janicevidal opened this issue Nov 16, 2018 · 3 comments

Comments

@janicevidal
Copy link

Disable cudnn for batch norm的操作,和默认的torch batchNorm、扩展的Synchronized batchNorm区别在哪?

@LiMeng95
Copy link
Owner

这个操作是在bn方法中禁用了cudnn。借鉴了和这个项目相同的操作。

我们在训练keypoint subnet的时候对bn层采用了train()模式(trainer.py#L173, trainer.py#L318),不禁用cudnn的话训练和测试过程会出现不收敛的情况。不过如果把L173和L318删掉,即在所有训练过程中bn层均为eval()模式,不禁用cudnn也可以,但精度可能稍低。

更多信息可以参照这两个issue: issue1, issue2

@lianuo
Copy link

lianuo commented Dec 18, 2018

他们说pytorch1.0已经解决了这个bughttps://github.com/Microsoft/human-pose-estimation.pytorch/issues/67

@LiMeng95
Copy link
Owner

@lianuo
多谢!

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

3 participants