gUNet-main代码复现遇到的问题（请教各位大佬，感谢感谢）

E:\Anaconda\envs\pt1121\python.exe E:/gUNet-main/train.py
E:\Anaconda\envs\pt1121\lib\site-packages\torch\cuda\amp\grad_scaler.py:126: UserWarning: torch.cuda.amp.GradScaler is enabled, but CUDA is not available.  Disabling.
  warnings.warn(
==> Loaded existing trained model.
  0%|          | 0/190 [00:00<?, ?it/s]==> Start training, current model name: gunet_b
[ WARN:0@3.853] global D:\a\opencv-python\opencv-python\opencv\modules\imgcodecs\src\loadsave.cpp (239) cv::findDecoder imread_('E:\gUNet-main\data\ITS\GT'): can't open/read file: check file path/integrity
[ WARN:0@3.855] global D:\a\opencv-python\opencv-python\opencv\modules\imgcodecs\src\loadsave.cpp (239) cv::findDecoder imread_('E:\gUNet-main\data\ITS\GT'): can't open/read file: check file path/integrity
[ WARN:0@3.854] global D:\a\opencv-python\opencv-python\opencv\modules\imgcodecs\src\loadsave.cpp (239) cv::findDecoder imread_('E:\gUNet-main\data\ITS\IN'): can't open/read file: check file path/integrity
[ WARN:0@3.855] global D:\a\opencv-python\opencv-python\opencv\modules\imgcodecs\src\loadsave.cpp (239) cv::findDecoder imread_('E:\gUNet-main\data\ITS\GT'): can't open/read file: check file path/integrity
  0%|          | 0/190 [00:07<?, ?it/s][ WARN:0@3.856] global D:\a\opencv-python\opencv-python\opencv\modules\imgcodecs\src\loadsave.cpp (239) cv::findDecoder imread_('E:\gUNet-main\data\ITS\IN'): can't open/read file: check file path/integrity

Traceback (most recent call last):
  File "E:\gUNet-main\train.py", line 228, in <module>
    main()
  File "E:\gUNet-main\train.py", line 199, in main
    loss = train(train_loader, network, criterion, optimizer, scaler, frozen_bn)
  File "E:\gUNet-main\train.py", line 69, in train
    for batch in train_loader:
  File "E:\Anaconda\envs\pt1121\lib\site-packages\torch\utils\data\dataloader.py", line 631, in __next__
    data = self._next_data()
  File "E:\Anaconda\envs\pt1121\lib\site-packages\torch\utils\data\dataloader.py", line 1346, in _next_data
    return self._process_data(data)
  File "E:\Anaconda\envs\pt1121\lib\site-packages\torch\utils\data\dataloader.py", line 1372, in _process_data
    data.reraise()
  File "E:\Anaconda\envs\pt1121\lib\site-packages\torch\_utils.py", line 722, in reraise
    raise exception
TypeError: Caught TypeError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "E:\Anaconda\envs\pt1121\lib\site-packages\torch\utils\data\_utils\worker.py", line 308, in _worker_loop
    data = fetcher.fetch(index)
  File "E:\Anaconda\envs\pt1121\lib\site-packages\torch\utils\data\_utils\fetch.py", line 51, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "E:\Anaconda\envs\pt1121\lib\site-packages\torch\utils\data\_utils\fetch.py", line 51, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "E:\gUNet-main\datasets\loader.py", line 86, in __getitem__
    source_img = read_img(os.path.join(self.root_dir, img_name), to_float=False)
  File "E:\gUNet-main\utils\common.py", line 52, in read_img
    return img[:, :, ::-1] # 表示对图像的通道进行逆序操作，通常用于将图像从 BGR 格式转换为 RGB 格式
TypeError: 'NoneType' object is not subscriptable

进程已结束,退出代码1

提示是路径问题，可是已经按照说明文件分别新建文件夹，数据集也下载了，还是有问题

下面是代码中设置的