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

how to get the results? #7

Open
stormcoral opened this issue Jan 11, 2018 · 5 comments
Open

how to get the results? #7

stormcoral opened this issue Jan 11, 2018 · 5 comments

Comments

@stormcoral
Copy link

Thanks for your code. I want to know how to get the Set5 (x4) result reported. What's your training datasets in the generate_train_lap_pry file? I can't reproduce it. Thanks!

@twtygqyy
Copy link
Owner

@stormcoral
Copy link
Author

@twtygqyy I can't reproduce the result with my own model when training the 291 images. Can you provide some details? What's your training datasets in the generate_train_lap_pry file? Thank you!

@twtygqyy
Copy link
Owner

Hi @stormcoral, what kind of performance did you achieve? I trained with 291 images and used exactly all the settings I pushed.

@stormcoral
Copy link
Author

@twtygqyy
('Scale=', 4)
('Dataset=', 'Set5')
('PSNR_predicted=', 30.25896192566164)
('PSNR_bicubic=', 28.432432425785287)
It takes average 0.0904507637024s for processing
It confused me.

@twtygqyy
Copy link
Owner

@stormcoral How about the performance of model I pushed?
I think it must be the reason of training set, please check and train again, especially for the format.

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