Chenzhaowei13 / Light-Condition-Style-Transfer

Lane Detection in Low-light Conditions Using an Efficient Data Enhancement : Light Conditions Style Transfer (IV 2020)
MIT License
136 stars 30 forks source link

ModuleNotFoundError: No module named 'models.cycle_gan_model' #17

Closed xyloww closed 3 years ago

xyloww commented 3 years ago

请问以下error如何修改?感谢! cd /content/Light-Condition-Style-Transfer/SIM-CycleGAN/ python train.py --dataroot ./datasets/maps --/content/Light-Condition-Style-Transfer/Culane/driver_37_30frame --name maps_cyclegan --model cycle_gan

请问有哪些 models. 有lowlight的作用?

File "train.py", line 28, in opt = TrainOptions().parse() # get training options File "/content/Light-Condition-Style-Transfer/SIM-CycleGAN/options/base_options.py", line 118, in parse opt = self.gather_options() File "/content/Light-Condition-Style-Transfer/SIM-CycleGAN/options/base_options.py", line 78, in gather_options model_option_setter = models.get_option_setter(model_name) File "/content/Light-Condition-Style-Transfer/SIM-CycleGAN/models/init.py", line 50, in get_option_setter model_class = find_model_using_name(model_name) File "/content/Light-Condition-Style-Transfer/SIM-CycleGAN/models/init.py", line 33, in find_model_using_name modellib = importlib.import_module(model_filename) File "/usr/lib/python3.7/importlib/init.py", line 127, in import_module return _bootstrap._gcd_import(name[level:], package, level) File "", line 1006, in _gcd_import File "", line 983, in _find_and_load File "", line 965, in _find_and_load_unlocked ModuleNotFoundError: No module named 'models.cycle_gan_model'

Chenzhaowei13 commented 3 years ago

你好,这个repo没有包含cyclegan,请尝试使用默认的SIM-CycleGAN

xyloww commented 3 years ago

谢谢您的回复.

I am suppose to create a dataset folder under /dataset for 'dataset'. Create subfolders testA, testB, trainA, and trainB under your dataset's folder. How did you categorize CULANE datasets into testA, trainA, test B, train B?

Also, where can one download the official pretrained models for light condition-style-transfer?

Chenzhaowei13 commented 3 years ago

For CULane,we use dataset_loadmode=1(load txt) as default, which is different from cyclegan repo. In paper, we mentioned that the daytime is regarded as domain A, and night is regarded as domain B. Due to time constraints, the pre-trained model is stored on the school's server, but I have already graduated, so I’m sorry to be unable to provide it at the moment.

xyloww commented 3 years ago

Thank you for your response!