yolov8分类时候出现类别数量与文件夹数量不符的问题

在autodl云服务上训练yolov8分类模型的时候出现了报错，以及文件夹数量和跑模型的时候类别对应不上的问题。比如：我的train文件夹下只有cat,dog。但是代码出现了 ERROR ❌️ requires 2 classes, not 4 这种问题。去github看了下issue才知道的，特做笔记

train: New cache created: /root/datasets/Smile_classify_part/train.cache
Traceback (most recent call last):
  File "model_train.py", line 6, in <module>
    model.train(
  File "/root/miniconda3/lib/python3.8/site-packages/ultralytics/engine/model.py", line 810, in train
    self.trainer.train()
  File "/root/miniconda3/lib/python3.8/site-packages/ultralytics/engine/trainer.py", line 208, in train
    self._do_train(world_size)
  File "/root/miniconda3/lib/python3.8/site-packages/ultralytics/engine/trainer.py", line 323, in _do_train
    self._setup_train(world_size)
  File "/root/miniconda3/lib/python3.8/site-packages/ultralytics/engine/trainer.py", line 290, in _setup_train
    self.test_loader = self.get_dataloader(
  File "/root/miniconda3/lib/python3.8/site-packages/ultralytics/models/yolo/classify/train.py", line 82, in get_dataloader
    dataset = self.build_dataset(dataset_path, mode)
  File "/root/miniconda3/lib/python3.8/site-packages/ultralytics/models/yolo/classify/train.py", line 77, in build_dataset
    return ClassificationDataset(root=img_path, args=self.args, augment=mode == "train", prefix=mode)
  File "/root/miniconda3/lib/python3.8/site-packages/ultralytics/data/dataset.py", line 427, in __init__
    self.base = torchvision.datasets.ImageFolder(root=root)
  File "/root/miniconda3/lib/python3.8/site-packages/torchvision/datasets/folder.py", line 309, in __init__
    super().__init__(
  File "/root/miniconda3/lib/python3.8/site-packages/torchvision/datasets/folder.py", line 145, in __init__
    samples = self.make_dataset(self.root, class_to_idx, extensions, is_valid_file)
  File "/root/miniconda3/lib/python3.8/site-packages/torchvision/datasets/folder.py", line 189, in make_dataset
    return make_dataset(directory, class_to_idx, extensions=extensions, is_valid_file=is_valid_file)
  File "/root/miniconda3/lib/python3.8/site-packages/torchvision/datasets/folder.py", line 102, in make_dataset
    raise FileNotFoundError(msg)
FileNotFoundError: Found no valid file for the classes .ipynb_checkpoints. Supported extensions are: .jpg, .jpeg, .png, .ppm, .bmp, .pgm, .tif, .tiff, .webp

和

train: /root/datasets/Smile_classify_part/train... found 44155 images in 2 classes ✅ 
val: /root/datasets/Smile_classify_part/val... found 1007 images in 4 classes: ERROR ❌️ requires 2 classes, not 4

        
        

原因：因为我在jupyter上运行的，数据集是上传到autodl上的，租用别人的云显卡的。并且我上传数据的时候对数据集进行了操作，比如移动删除之类的。所以有可能会导致出现了隐藏的文件

解决方式：每次操作完数据集，请重新启动jupyter，然后使用下面的命令检测是否有隐藏的文件，有时候使用这个命令后，在终端还是显示不出来的。建议直接执行删除隐藏文件的命令

查看的命令

find . -type f -name ".*"
这里.表示当前目录，-type f表示只查找文件（不包括目录），“-name ".*"”表示匹配以.开头的文件名。不过这个命令会查找所有子目录中的隐藏文件

在当前路径下删除所有隐藏文件 和 .ipynb_checkpoints 文件夹

find . \( -name ".*" -o -name ".ipynb_checkpoints" \) -delete