NLRN_v0

NLRN_v0 copied to clipboard

Question about repo NLRN

2

I just follow default setting to retrain the model and then test it, but the output image seems like bellow. Test the image with the pretrained model given in [https://drive.google.com/open?id=1l_G9wniOKSM4dS8NqGP-SptPVT5PFo6l](sigma25)...

yangxh11

When training, it only do evalute and give PSNR when save chackpoints. change here is useless: parser.add_argument( '--eval-steps', help='Number of steps to run evaluation for at each checkpoint', default=100, type=int)...

LvZhenFeng

What's the defference between new version and the older version?

4

Hi, What's the defference between new version and the older version?

scut-salmon

Hi i run your command provided in readme of new version for 500k step but the psnr reached only to 28 ,far away from your metrics (30.8) in your paper...

adamas-v

Sorry to bother, the link of pretrained model has been disabled could you provide a new link? Thanks a lot.

MC-E

https://github.com/Ding-Liu/NLRN/blob/ca5c0a54329c157b31f2daf708e20f677546b208/models/nlrn.py#L218 Why not use the "else" branch to train the model without crop patches?

manmanCover

about implement of non-local module

5

I find that the output of this non-local module on each location only depends on its q × q neighborhood, as descripted in your paper, but I can not find...

qibao77