search

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
793 stars 110 forks source link

About quick reproduce the results of unpaired learning parts #98

Open aimForProject opened 4 years ago

aimForProject commented 4 years ago

Hello @nothinglo , this work is awesome. I am an undergraduate and trying to reproduce your results and explore on this basis. I think I need to put the corresponding data set into folder_input, folder_label, and folder_label_HDR; Do I need to change any parameters in the code to reproduce the unpaired learning results of both MIT dataset and HDR dataset in the paper? Thanks a lot!

aimForProject commented 4 years ago

Has anyone successfully reproduced the results of unpaired learning or trying to reproduce? I really hope to communicate with you. I would appreciate it.

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.