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

测试时达不到论文中的指标 #29

Open
TTZ56952 opened this issue Aug 10, 2022 · 2 comments
Open

测试时达不到论文中的指标 #29

TTZ56952 opened this issue Aug 10, 2022 · 2 comments

Comments

@TTZ56952
Copy link

作者您好!使用您在checkpoint里的2020Track1-PSNR.pt权重,测试2020Track1——Valid,测试时输入整张图片,得到的PSNR是26.2,达不到您论文中写的26.80的效果。并且我尝试重新训练,复现代码,按照您论文里的detail修改配置文件,最终复现效果PSNR只有24.30。请问用您的权重测试时,哪里出现了问题?

@1170300511
Copy link

请问您训练的模型noise估计的表现符合预期吗?我这边噪声完全学不到信息,按照给的配置文件做的

@hot-dog
Copy link

hot-dog commented Oct 11, 2022

您好,请问如果要用自己的数据训练的话,代码是不是有很多地方需要改动呀,我目前做的改动有配置文件做了相应修改,添加相应的配置项,patchgandiscriminator的输出通道改成了1,还有一些其他的修改没有记录下来。但是目前训练的效果不是太好,请问您当时训练的时候有得到好的结果吗? @1170300511

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