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
Disable cudnn for batch norm的操作,和默认的torch batchNorm、扩展的Synchronized batchNorm区别在哪?
The text was updated successfully, but these errors were encountered:
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
Sorry, something went wrong.
他们说pytorch1.0已经解决了这个bughttps://github.com/Microsoft/human-pose-estimation.pytorch/issues/67
@lianuo 多谢!
No branches or pull requests
Disable cudnn for batch norm的操作,和默认的torch batchNorm、扩展的Synchronized batchNorm区别在哪?
The text was updated successfully, but these errors were encountered: