I've got the same psnr during training unpaired HDR model

nothinglo / Deep-Photo-Enhancer

TensorFlow implementation of the CVPR 2018 spotlight paper, Deep Photo Enhancer: Unpaired Learning for Image Enhancement from Photographs with GANs

MIT License

794 stars 110 forks source link

I've got the same psnr during training unpaired HDR model #71

Closed Soroorsh closed 5 years ago

Soroorsh commented 5 years ago

Hi, I've got the same problem as issue#54. I got almost the same PSNRs for test for different epochs, but I can't find any solution in issue#54! can anyone help me?

nothinglo commented 5 years ago

The reason is that there is no ground truth in the unpaired HDR experiment.

Soroorsh commented 5 years ago

I've used the ExpertC images for the PSNR, isn't it right?