Result is too big
ChriswooTalent opened this issue · 2 comments
Hi:
Thanks for your sharing, I get the images and weights, set scale 2, use model weights/RBPN_2x.pth, but got a very big result, psnr is nan, how can I fix this bug
The reason why psnr is nan is that the shape of target and predition are 3x576x720, the height and width should be the last two but the method in this project takes the 3 channels as height，so that the tensor shape is wrong.
I also tried to run the test code on the vid4 dataset, but the psnr calculated according to the method in the project is inconsistent with the paper. Have you seen this happen?
The reason why psnr is nan is that the shape of target and predition are 3x576x720, the height and width should be the last two but the method in this project takes the 3 channels as height，so that the tensor shape is wrong.
I also tried to run the test code on the vid4 dataset, but the psnr calculated according to the method in the project is inconsistent with the paper. Have you seen this happen?
me
The reason why psnr is nan is that the shape of target and predition are 3x576x720, the height and width should be the last two but the method in this project takes the 3 channels as height，so that the tensor shape is wrong.
I also tried to run the test code on the vid4 dataset, but the psnr calculated according to the method in the project is inconsistent with the paper. Have you seen this happen?
ME TOO,have you solved the problem?