I have been try to download Celeba dataset with torchvision as follows
import torchvision image_path = './'celeba_train_dataset = torchvision.datasets.CelebA(image_path, split='train', target_type='attr', download=False)celeba_valid_dataset = torchvision.datasets.CelebA(image_path, split='valid', target_type='attr', download=False)celeba_test_dataset = torchvision.datasets.CelebA(image_path, split='test', target_type='attr', download=False)
When i set download = True i get a MD5 checksum error and when i set it false and downloaded it manually it says it cant find it or it is corrupted.
I have downloaded the images and appropriate txt files from Kaggle and Gdrive and put it in the 'celeba' folder as follows