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

对HRNet剪枝,第一个bn的grad是None的问题 #92

Open
zhangdandan-git opened this issue Dec 21, 2023 · 0 comments
Open

对HRNet剪枝,第一个bn的grad是None的问题 #92

zhangdandan-git opened this issue Dec 21, 2023 · 0 comments

Comments

@zhangdandan-git
Copy link

HRNet有四个分支,每个分支都是由basicblock组成,我将basicblock中的结构调整为了bn1->relu->conv1->bn2->relu->conv2的顺序,在稀疏化训练时,会出现bn1的grad为None,请问这是什么原因?
HRNet网络;
e310240ece214000aec926c7f1b49b22

None
module.stage4.2.branches.0.1.bn1

tensorC[ 1.5367e-09-3.9298e-099.5592e-092.7138e-095.1612e-091.1661e-08,5.5898e-09-1.5646e-09-9.1451e-09-8.7433e-092.4812e-08-1.1339e-086.6680e-10-1.7799e-082.5298e-091.1260e-083.3191e-09-1.4545e-097.2233e-105.3598e-092.8224e-099.2047e-09,5.3420e-10-6.6877e-11-6.0079e-097.2883e-09-9.4481e-098.5220e-101.9245e-086.5513e-09-1.1795e-08,-1.4566e-09]device-'cuda:0
module.stage4.2.branches.0.1.bn2
微信图片_20231221162855

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

1 participant