语义分割程序调试：TypeError: expected str, bytes or os.PathLike object, not NoneType

项目地址：
https://github.com/meetshah1995/pytorch-semseg

遇到的问题：

Traceback (most recent call last):
  File "H:/pycharm_pro/semantic_segmentation/train.py", line 236, in <module>
    train(cfg, writer, logger)  #配置文件，可视化，日志文件
  File "H:/pycharm_pro/semantic_segmentation/train.py", line 53, in train
    augmentations=data_aug,
  File "H:\pycharm_pro\semantic_segmentation\ptsemseg\loader\pascal_voc_loader.py", line 73, in __init__
    self.setup_annotations()
  File "H:\pycharm_pro\semantic_segmentation\ptsemseg\loader\pascal_voc_loader.py", line 199, in setup_annotations
    path = pjoin(sbd_path, "dataset/train.txt")
  File "C:\Users\Zichao Zhang\Anaconda3\lib\ntpath.py", line 76, in join
    path = os.fspath(path)
TypeError: expected str, bytes or os.PathLike object, not NoneType

一直指向的是sbd_path不能为空，我一开始认为自己的路径设置的有问题，一直在修改路径，但是显然并不是这个问题，弄了半天之后，非常受挫，于是就很不开心，决定去吃晚饭，并和女朋友打招呼，因为她要下班啦！回来之后，突然发现，在

t_loader = data_loader(
    data_path,
    # sbd_path,
    is_transform=True,
    split=cfg["data"]["train_split"],
    img_size=(cfg["data"]["img_rows"], cfg["d