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

关于DCN版本和施加的层的疑问 #20

Open
lywhapp opened this issue May 18, 2021 · 0 comments
Open

关于DCN版本和施加的层的疑问 #20

lywhapp opened this issue May 18, 2021 · 0 comments

Comments

@lywhapp
Copy link

lywhapp commented May 18, 2021

你好,感谢开源这么有意义的工作,我这边有点关于DCN的具体配置的疑问,如网页上所述:
[3] dcnv2 denotes deformable convolutional networks v2. Note that for ResNe(X)t based models, we apply deformable convolutions from stage c3 to c5 in backbones.
训练时使用的都是DCNv2,并在c3-c5都替换为DCNv2。但我看config/gfocal/目录下的脚本都是如下设置:
  dcn=dict(type='DCN', deform_groups=1, fallback_on_stride=False),
stage_with_dcn=(False, False, True, True),

我的理解这样配置实际是应用的DCNv1到c4-c5层,不知是否是我理解有误?望解答,谢谢~
而使用DCNv2到c3-c5是否应这样配置:
dcn=dict(type='DCNv2', deform_groups=1, fallback_on_stride=False),
stage_with_dcn=(False, True, True, True)

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