YOLOv5模型训练报错，如何解决？

Question

YOLOv5模型训练报错

classify\train: model=yolov5s-cls.pt, data=imagenette160, epochs=10, batch_size=64, imgsz=224, nosave=False, cache=None, device=, workers=8, project=..\runs\train-cls, name=exp, exist_ok=False, pretrained=True, optimizer=Adam, lr0=0.001, decay=5e-05, label_smoothing=0.1, cutoff=None, dropout=None, verbose=False, seed=0, local_rank=-1
github: skipping check (not a git repository), for updates see https://github.com/ultralytics/yolov5
YOLOv5  2022-11-22 Python-3.11.5 torch-2.0.1+cpu CPU
TensorBoard: Start with 'tensorboard --logdir ..\runs\train-cls', view at http://localhost:6006/
Traceback (most recent call last):
  File "D:\venv\Lib\site-packages\IPython\core\interactiveshell.py", line 3526, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-2-3bd7b49a8733>", line 1, in <module>
    runfile('D:\\YOLOv5\\classify\\train.py', wdir='D:\\YOLOv5\\classify')
  File "D:\pyCharm\PyCharm Community Edition 2023.2.1\plugins\python-ce\helpers\pydev\_pydev_bundle\pydev_umd.py", line 197, in runfile
    pydev_imports.execfile(filename, global_vars, local_vars)  # execute the script
    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\pyCharm\PyCharm Community Edition 2023.2.1\plugins\python-ce\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile
    exec(compile(contents+"\n", file, 'exec'), glob, loc)
  File "D:\YOLOv5\classify\train.py", line 333, in <module>
    main(opt)
  File "D:\YOLOv5\classify\train.py", line 319, in main
    train(opt, device)
  File "D:\YOLOv5\classify\train.py", line 90, in train
    trainloader = create_classification_dataloader(path=data_dir / 'train',
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\YOLOv5\utils\dataloaders.py", line 1206, in create_classification_dataloader
    dataset = ClassificationDataset(root=path, imgsz=imgsz, augment=augment, cache=cache)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\YOLOv5\utils\dataloaders.py", line 1172, in __init__
    super().__init__(root=root)
  File "D:\venv\Lib\site-packages\torchvision\datasets\folder.py", line 309, in __init__
    super().__init__(
  File "D:\venv\Lib\site-packages\torchvision\datasets\folder.py", line 144, in __init__
    classes, class_to_idx = self.find_classes(self.root)
                            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\venv\Lib\site-packages\torchvision\datasets\folder.py", line 218, in find_classes
    return find_classes(directory)
           ^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\venv\Lib\site-packages\torchvision\datasets\folder.py", line 40, in find_classes
    classes = sorted(entry.name for entry in os.scandir(directory) if entry.is_dir())
                                             ^^^^^^^^^^^^^^^^^^^^^
FileNotFoundError: [WinError 3] 系统找不到指定的路径。: 'imagenette160\\train'

不知道这个到底是什么问题，而且为什么会找不到路径？

Answer 1

不要用相对路径，修改为绝对路径