chuangchuangtan / NPR-DeepfakeDetection

140 stars 11 forks source link

AssertionError: datasets should not be an empty iterable #20

Open tongleyan opened 1 month ago

tongleyan commented 1 month ago

2024_09_17_08_5135 (0 AttGAN ) acc: 64.8; ap: 73.0 (1 InfoMaxGAN ) acc: 53.1; ap: 61.2 (2 MMDGAN ) acc: 53.1; ap: 62.6 (3 RelGAN ) acc: 98.6; ap: 100.0 Traceback (most recent call last): File "/root/share/NPR-DeepfakeDetection-main/test.py", line 69, in acc, ap, , , , _ = validate(model, opt) File "/root/share/NPR-DeepfakeDetection-main/validate.py", line 10, in validate data_loader = create_dataloader(opt) File "/root/share/NPR-DeepfakeDetection-main/data/init.py", line 44, in create_dataloader dataset = get_dataset(opt) File "/root/share/NPR-DeepfakeDetection-main/data/init.py", line 26, in get_dataset return torch.utils.data.ConcatDataset(dset_lst) File "/opt/conda/lib/python3.10/site-packages/torch/utils/data/dataset.py", line 317, in init assert len(self.datasets) > 0, 'datasets should not be an empty iterable' # type: ignore[arg-type] AssertionError: datasets should not be an empty iterable

tongleyan commented 1 month ago

Hello author, how can this issue be resolved? @chuangchuangtan