search

qinglew / PCN-PyTorch

Implementation of PCN(Point Completion Network) in PyTorch.
141 stars 33 forks source link

Caught ValueError in DataLoader worker process 0. #9

Closed Saji70 closed 2 years ago

Saji70 commented 2 years ago

Hello Qinglew

Would you please explain the reason of my training Error?

//##

Caught ValueError in DataLoader worker process 0. Original Traceback (most recent call last): File "/home/sj/.local/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 198, in _worker_loop data = fetcher.fetch(index) File "/home/sj/.local/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/sj/.local/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/sj/PCN-PyTorch-master/dataset/dataset.py", line 40, in getitem partial_input = resample_pcd(partial_input, self.num_input) File "/home/sj/PCN-PyTorch-master/utils.py", line 31, in resample_pcd idx = np.concatenate([idx, np.random.randint(pcd.shape[0], size=n-pcd.shape[0])]) File "mtrand.pyx", line 992, in mtrand.RandomState.randint ValueError: Range cannot be empty (low >= high) unless no samples are taken

//##

Regards