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

n_feats and block_feats for x4 #8

Closed
bensuucar opened this issue Oct 9, 2018 · 2 comments
Closed

n_feats and block_feats for x4 #8

bensuucar opened this issue Oct 9, 2018 · 2 comments

Comments

@bensuucar
Copy link

Hi, Jiahui,

I am trying to implement wdsr_a with the scale 4. I would like to compare its performance with EDSR( # of residual blocks = 32, n_feats = 256). In this case, what would be your recommendation to set n_feats and block_feats?
Currently I am using wdsr_a with n_feats 128 and block_feats 512. However I am not sure if it is the intended approach while constructing the network.

@JiahuiYu
Copy link
Owner

JiahuiYu commented Oct 9, 2018

Hi, @bensuucar, you are correct - n_feats 128 and block_feats 512 is a good choice, compared with EDSR of channel number 256.

@JiahuiYu JiahuiYu closed this as completed Oct 9, 2018
@qingchuanhuajuan
Copy link

Hi @bensuucar ,I want to know what the PSNR value of the x4 model you are running on the standard dataset (eg.Set5, Set14, B100...)? How long have you been training? Thank you!

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