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

请问为什么加了DCN的resnet和不加DCN的resnet要用两种不同的预训练模型呢 #30

Open
ocrhei opened this issue Feb 2, 2024 · 3 comments

Comments

@ocrhei
Copy link

ocrhei commented Feb 2, 2024

小白,不太懂

@junjiehe96
Copy link
Owner

因为加了DCN的resnet-d与不加DCN的resnet结构上有一些区别,resnet-d是resnet的一个变种,详见line207

@ocrhei
Copy link
Author

ocrhei commented Feb 3, 2024

因为加了DCN的resnet-d与不加DCN的resnet结构上有一些区别,resnet-d是resnet的一个变种,详见line207

明白了,感谢指点,还有个小问题,就是为什么ResNet不用syncbn呢,原理上好像多卡用syncbn效果更好吧,不明白。

@junjiehe96
Copy link
Owner

因为加了DCN的resnet-d与不加DCN的resnet结构上有一些区别,resnet-d是resnet的一个变种,详见line207

明白了,感谢指点,还有个小问题,就是为什么ResNet不用syncbn呢,原理上好像多卡用syncbn效果更好吧,不明白。

是的,我们并没有使用syncbn,这是为了和别的方法公平比较,使用相同的实验设置。

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