Error Training: RecursionError

[Zhaohy21]

Hello everyone I have some problems in training:

    2023-06-27 09:53:33,078 VGG16:to: 0 
    2023-06-27 09:53:34,880 Found 10 samples. 
    2023-06-27 09:53:34,901 Found 30 samples. 
    2023-06-27 09:53:35,105 Found 0 images. 
    2023-06-27 09:53:35,105 Dataset is empty!

And the Error is:

    File "/usr/lib/python3.10/pathlib.py", line 960, in __new__
      self = cls._from_parts(args)
    File "/usr/lib/python3.10/pathlib.py", line 594, in _from_parts
      drv, root, parts = self._parse_args(args)
    File "/usr/lib/python3.10/pathlib.py", line 587, in _parse_args
      return cls._flavour.parse_parts(parts)
    File "/usr/lib/python3.10/pathlib.py", line 67, in parse_parts
      drv, root, rel = self.splitroot(part)
    File "/usr/lib/python3.10/pathlib.py", line 240, in splitroot
      if part and part[0] == sep:
  RecursionError: maximum recursion depth exceeded in comparison

Is it because my dataset is not set up correctly?

These are the steps I took to prepare the dataset:

• Pfd
  gbuffers --> by generate_fake_gbuffers.py --> .npz
  robust labels --> by Mseg --> .png (gray images
  gt labels --> download from webseit --> .png

Their order in the filetext also follows the guide: paths to image, gbuffers, robust labels, and gt labels

And also i changed the (height, width) for the compute_weights.py script, since the image from Pfd is 1054x1914

Is there anything I've missed or gotten wrong?