MIRNet icon indicating copy to clipboard operation
MIRNet copied to clipboard

Published 20 hours ago • verified publisher icon swz30

training.yml for LOL enhancement

Open Seeyn opened this issue 2 years ago • 2 comments

Thanks for your excellent works! I'm trying to reproduce your enhancement result. Can you please share training.yml for training the enhancement model for the LOL dataset? Because I can only obtain PSNR 20.69 if I use the training setting of training.yml you share in this repository.

Seeyn avatar Aug 12 '21 07:08 Seeyn

Dear author, Thank you for your great work and the results look quite good. I also try to reproduce the results of the low-light enhancement experiments. I saw the MixUp_AUG is applied in the denoising training code. Does the enhancement also use this function for data augmentation?

xyIsHere avatar Aug 12 '21 15:08 xyIsHere

Hi @xyIsHere We do use MixUP_Aug for image enhancement as well.

Hi @Seeyn Please refer to #11

swz30 avatar Sep 19 '21 08:09 swz30