search

Algolzw / image-restoration-sde

Image Restoration with Mean-Reverting Stochastic Differential Equations, ICML 2023. Winning solution of the NTIRE 2023 Image Shadow Removal Challenge.
https://algolzw.github.io/ir-sde/index.html
MIT License
520 stars 39 forks source link

AssertionError: datasets/rain/trainH/LQ is not a valid directory #9

Open FengEternity opened 1 year ago

FengEternity commented 1 year ago

I set up the dataset according to the operation you provided, but the following error still occurred at runtime, do you know why, thank you

Traceback (most recent call last): File "train.py", line 319, in main() File "train.py", line 156, in main train_set = create_dataset(dataset_opt) File "/LF/image-restoration-sde/codes/config/deraining/../../data/init.py", line 45, in create_dataset dataset = D(dataset_opt) File "/LF/image-restoration-sde/codes/config/deraining/../../data/LQGT_dataset.py", line 40, in init self.LR_paths = util.get_image_paths( File "/LF/image-restoration-sde/codes/config/deraining/../../data/util.py", line 48, in get_image_paths paths = sorted(_get_paths_from_images(dataroot)) File "/LF/image-restoration-sde/codes/config/deraining/../../data/util.py", line 19, in _get_paths_from_images assert os.path.isdir(path), '{:s} is not a valid directory'.format(path) AssertionError: datasets/rain/trainH/LQ is not a valid directory

Algolzw commented 1 year ago

It seems the system can't find the 'datasets/rain/trainH/LQ' directory. You can check whether the directory exists.