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

Train with cycle_gan model #63

Closed GuoLanqing closed 3 years ago

GuoLanqing commented 3 years ago

When I change the training model to --model cycle_gan, this error will occur.

Traceback (most recent call last):
  File "train.py", line 19, in <module>
    model = create_model(opt)
  File "/home/xxx/projects/EnlightenGAN/models/models.py", line 36, in create_model
    model.initialize(opt)
  File "/home/xxx/projects/EnlightenGAN/models/cycle_gan_model.py", line 31, in initialize
    self.vgg_loss = networks.PerceptualLoss()
TypeError: __init__() missing 1 required positional argument: 'opt'

Have you encountered this problem? Is there any solution? Many thanks.

yifanjiang19 commented 3 years ago

I suggest you directly use the original cyclegan repo.