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

关于生成的noise的一点疑问 #15

Open
Fangzhenxuan opened this issue Mar 26, 2022 · 4 comments
Open

关于生成的noise的一点疑问 #15

Fangzhenxuan opened this issue Mar 26, 2022 · 4 comments

Comments

@Fangzhenxuan
Copy link

其中 noise 的shape为[B, 1, 1, 1],而 x 的shape为[B, 3, 32, 32]
请问一下作者生成的noise对LR图像的每一个通道和每一个pixel都是相同的吗?

@greatlog
Copy link
Owner

noise生成时有一些参数需要自己指定,比如指定spatial = False时,一般需要指定 mix=True,这样生成的noise还是 [B, 3, 32,32],或者直接指定spatial=True(详细过程参考deg_arch.py)。提供的yml默认设置可能有些问题,感谢提醒,我回头修改一下。

@Fangzhenxuan
Copy link
Author

谢谢,请问作者还有哪些地方需要修改的呢,我现在用提供的代码还train不到论文中的结果。

@Feynman1999
Copy link

谢谢,请问作者还有哪些地方需要修改的呢,我现在用提供的代码还train不到论文中的结果。

+1 , 希望作者可以放出能train出文中结果的配置文件,感谢!

@hot-dog
Copy link

hot-dog commented Oct 11, 2022

请问你们自己训练的时候,训练代码是不是有些地方需要改一下,配置文件有些配置项是缺失的,代码有些地方也是错误的。 @Feynman1999 @Fangzhenxuan

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

4 participants