annotated_deep_learning_paper_implementations icon indicating copy to clipboard operation
annotated_deep_learning_paper_implementations copied to clipboard

want to use CelebA dataset,but there is an issue

Open Z0Victor opened this issue 2 years ago • 2 comments

PLZ

Z0Victor avatar Jun 07 '23 13:06 Z0Victor

File "F:\pycharmprojects\pythonProject\diffusion-git\ddpm\experiment.py", line 104, in init self.data_loader = torch.utils.data.DataLoader(self.dataset, self.batch_size, shuffle=True, pin_memory=True) File "D:\Annaconda\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 344, in init sampler = RandomSampler(dataset, generator=generator) # type: ignore[arg-type] File "D:\Annaconda\envs\pytorch\lib\site-packages\torch\utils\data\sampler.py", line 107, in init raise ValueError("num_samples should be a positive integer " ValueError: num_samples should be a positive integer value, but got num_samples=0

why data can't be loaded? how to fix it,I put the CelebA data in /ddpm/data/CelebA

Z0Victor avatar Jun 07 '23 13:06 Z0Victor

The data path is [project_folder]/data/celebA

vpj avatar Jun 30 '23 10:06 vpj