bug：ValueError: num_samples should be a positive integer value, but got num_samples=0

#未读取到样本

完整报错
Traceback (most recent call last):
File “D:/LanduseDataset/pytorch_segmentation/segmentation_models/train_upernet.py”, line 292, in
main()
File “D:/LanduseDataset/pytorch_segmentation/segmentation_models/train_upernet.py”, line 73, in main
train_loader = DataLoader(train_dataset, batch_size=8, shuffle=True, num_workers=8,pin_memory=True)
File “C:\Users\laoji.conda\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py”, line 277, in init
sampler = RandomSampler(dataset, generator=generator) # type: ignore[arg-type]
File “C:\Users\laoji.conda\envs\pytorch\lib\site-packages\torch\utils\data\sampler.py”, line 97, 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
Process finished with exit code 1

解决方案

检查数据集路径