It seems the output photo a little bit brighter

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

It seems the output photo a little bit brighter #101

Open hiterjoshua opened 4 years ago

hiterjoshua commented 4 years ago

Good job! Nice code! Stilll, while I test the model whether on 577 or 736, the output photo looks a little bit bright, makes the image feel not so real, like the clothes or the grasslands. I think maybe the Adobe-Mit dataset should be responsible for this phenomenon, but still want some more suggestions and discussions! So how to make the output photos not so bright and be closer to the input photo? any advice is welcomed!

ozgurozkan123 commented 4 years ago

Hi can you please share the files you have for this project. The maintainer @nothinglo is not updating the links and all of them are broken. Thanks @hiterjoshua

Youlenda commented 3 years ago

Hi,

When I run the TF.py in the "[Online_Demo_Models]_Deep-Photo-Enhancer/LPGAN_exp_G3_736" file, I face this error:

Shapes (2, 1, 32, 32, 128) and () are incompatible

in line: netG_test_output1 = model(netG, test_df.input1, False, netG_act_o, is_first=True)

Would you mind helping me with it? Thank you in advance.