search

soapisnotfat / super-resolution

collection of super-resolution models & algorithms
Apache License 2.0
744 stars 188 forks source link

some improvements and questions about psnr #30

Open lunasdejavu opened 4 years ago

lunasdejavu commented 4 years ago

I think the resize input_transform should be bicubic since the default value is bilinear, and centercrop should be changed to RandomCrop() and some of the calculation of the PSNR in test should be normalize first and use MSELoss() not L1Loss() directly. and there still might be some problems that I can't achieve PSNR >30 by this project