yolov5 训练模型报错

Question

train: WARNING: No labels found in tmp\train.cache. See https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data
train: WARNING: Cache directory tmp is not writeable: [WinError 183] 当文件已存在时，无法创建该文件。: 'tmp\\train.cache.npy' -> 'tmp\\train.cache'
Traceback (most recent call last):
  File "train.py", line 614, in <module>
    main(opt)
  File "train.py", line 511, in main
    train(opt.hyp, opt, device, callbacks)
  File "train.py", line 212, in train
    prefix=colorstr('train: '))
  File "D:\PycharmProject\CSU_XYB\utils\datasets.py", line 108, in create_dataloader
    prefix=prefix)
  File "D:\PycharmProject\CSU_XYB\utils\datasets.py", line 422, in __init__
    assert nf > 0 or not augment, f'{prefix}No labels in {cache_path}. Can not train without labels. See {HELP_URL}'
AssertionError: train: No labels in tmp\train.cache. Can not train without labels. See https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data

不懂为什么会显示没有标注.

Answer 1

Train Custom Data · ultralytics/yolov5 Wiki · GitHub YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite. Contribute to ultralytics/yolov5 development by creating an account on GitHub. https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data

你要么自己改下dataload，变成直接读取你目前的数据格式，要么按照教程中的格式，将你目前的标注转成他需要的格式