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

Log file #4

Open
hokiyoshi opened this issue Oct 16, 2024 · 3 comments
Open

Log file #4

hokiyoshi opened this issue Oct 16, 2024 · 3 comments

Comments

@hokiyoshi
Copy link

Hi, I am curious about log file. May you publish it?

@XiangZ-0
Copy link
Owner

Hi, due to some server issues, it might take some time to find the log files, but you should be able to reproduce the logs and results with the training configs. Did you encounter any problems during training?

@hokiyoshi
Copy link
Author

Actually, It took me more than 1 week to train from starch, so if you have log file, It will be very help full for me to stop early if I have sth wrong. Thank you very much

@XiangZ-0
Copy link
Owner

Hi, unfortunately, I did not find the original log files due to the server problem... Sorry about that. But I found some of my own logs when developing HiT-SRF-2x (only the first 200K training iterations though). The validation results on Set 5 should be around:

  • 50K iteration: PSNR=38.11, SSIM=0.9608
  • 100K iteration: PSNR=38.14, SSIM=0.9610
  • 200K iteration: PSNR=38.23, SSIM=0.9613

Hope this helps!

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