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

blur kernels in Tab.3 #25

Closed
sujyQ opened this issue Jul 29, 2021 · 4 comments
Closed

blur kernels in Tab.3 #25

sujyQ opened this issue Jul 29, 2021 · 4 comments

Comments

@sujyQ
Copy link

sujyQ commented Jul 29, 2021

Hi. I'm sorry to bothering you.
Does this paper contain information about eigen values and rotate angles of the blur kernels in Tab.3 ?
I can see just shapes.

@LongguangWang
Copy link
Member

Hi @sujyQ, thanks for your interest in our work.
The detailed settings of the blur kernels in Tab. 3 are shown below.
image
While re-producing the results in Tab. 3, we find a bug and fix it. We also notice that a wrong pre-trained model for anisotropic kernels is released by mistake and we have uploaded the correct one.

This was referenced Jul 30, 2021
@sujyQ
Copy link
Author

sujyQ commented Jul 30, 2021

Thanks :)

@sujyQ sujyQ closed this as completed Jul 30, 2021
@Lewis0427
Copy link

util代码中random_anisotropic_gaussian_kernel里面您的更改是否有错误:theta = torch.rand(batch).cuda() / 180 * math.pi
是否应是theta = torch.rand(batch).cuda() * math.pi,180无需再加了

@LongguangWang
Copy link
Member

@Lewis0427,感谢指出这一bug,我们已经对其进行了修复。

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