Could you provide a link to your training/testing data or data sampling code?

[PatrickFeng]

When I executed this model in my environment(python 3.7 and pytorch 1.0.0) an error occurred. It said like below.

_Traceback (most recent call last):
File "train_classifier.py", line 166, in
main()
File "train_classifier.py", line 75, in main
for i, sample in enumerate(data_loader):
File "/home/usr_name/anaconda3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 637, in next
return self._process_next_batch(batch)
File "/home/usr_name/anaconda3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 658, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
RuntimeError: Traceback (most recent call last):
File "/home/usr_name/anaconda3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 138, in worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/usr_name/anaconda3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 232, in default_collate
return [default_collate(samples) for samples in transposed]
File "/home/usr_name/anaconda3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 232, in
return [default_collate(samples) for samples in transposed]
File "/home/usr_name/anaconda3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 209, in default_collate
return torch.stack(batch, 0, out=out)
RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 611 and 1420 in dimension 2 at /opt/conda/conda-bld/pytorch_1544202130060/work/aten/src/TH/generic/THTensorMoreMath.cpp:1333

I suppose this is because I run it with original ModelNet40 data and point size of single object varies from each other. It would be helpful if you could provide any download link of your dataset or give some guides on sampling data.