search

VITA-Group / EnlightenGAN

[IEEE TIP] "EnlightenGAN: Deep Light Enhancement without Paired Supervision" by Yifan Jiang, Xinyu Gong, Ding Liu, Yu Cheng, Chen Fang, Xiaohui Shen, Jianchao Yang, Pan Zhou, Zhangyang Wang
Other
890 stars 198 forks source link

Settings for Training #53

Closed jeighfrost closed 3 years ago

jeighfrost commented 4 years ago

Hi! Thank you for sharing the EnlightenGAN. I just want to ask some questions cause I'm kinda new to this. How am I able to find the best setting for training? I used the same training dataset that you provided and used the same settings for training (100 epoch with learning rate of 0.0001 followed by another 100 epochs with learning rate linearly decayed to zero) but the trained model seemed to differ a lot from the pretrained model. What factors should I consider about this? Which of which parameters should I will change to get a close or a better result with the pretrained model?

yifanjiang19 commented 4 years ago

Did you use the exactly same setting as I provided in the script?

jeighfrost commented 4 years ago

Yes, i didn't change anything on the script and I used the same set of training images in the link that was provided

yifanjiang19 commented 4 years ago

Did you use pytorch 0.3.1 and batchsize 32? Could you provide some results?

yifanjiang19 commented 3 years ago

If no reply I will close this issue, feel free to contact me if you meet new problems.