ValueError: Input must be 1- or 2-d.

[hahahaff]

When training, the following error occurred.
I did not know how to solve it. Could anyone provide some ideas to solve？Thanks a lot!

  File "/home/auto/anaconda3/envs/2Dpass/lib/python3.8/site-packages/pytorch_lightning/loops/loop.py", line 206, in run
    output = self.on_run_end()
  File "/home/auto/anaconda3/envs/2Dpass/lib/python3.8/site-packages/pytorch_lightning/loops/dataloader/evaluation_loop.py", line 180, in on_run_end
    self._evaluation_epoch_end(self._outputs)
  File "/home/auto/anaconda3/envs/2Dpass/lib/python3.8/site-packages/pytorch_lightning/loops/dataloader/evaluation_loop.py", line 288, in _evaluation_epoch_end
    self.trainer._call_lightning_module_hook(hook_name, output_or_outputs)
  File "/home/auto/anaconda3/envs/2Dpass/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 1347, in _call_lightning_module_hook
    output = fn(*args, **kwargs)
  File "/media/auto/data/lff_projection/2DPASS-main/network/base_model.py", line 226, in validation_epoch_end
    iou, best_miou = self.val_iou.compute()
  File "/home/auto/anaconda3/envs/2Dpass/lib/python3.8/site-packages/torchmetrics/metric.py", line 440, in wrapped_func
    value = compute(*args, **kwargs)
  File "/media/auto/data/lff_projection/2DPASS-main/utils/metric_util.py", line 38, in compute
    iou = per_class_iu(sum(self.hist_list))
  File "/media/auto/data/lff_projection/2DPASS-main/utils/metric_util.py", line 15, in per_class_iu
    return np.diag(hist) / (hist.sum(1) + hist.sum(0) - np.diag(hist))
  File "<__array_function__ internals>", line 5, in diag
  File "/home/auto/anaconda3/envs/2Dpass/lib/python3.8/site-packages/numpy/lib/twodim_base.py", line 303, in diag
    raise ValueError("Input must be 1- or 2-d.")
ValueError: Input must be 1- or 2-d.

[issouker97]

Hey, would you please tell me how could you finally achieve to train your 2DPASS and what is the dataset that you use for it !
can you tell also if you know how to train 2DPASS with another dataset ( in my case, i wanna train it on mine dataset)