Errors when training the completion models :1、raise self.exc_type(msg) ValueError: Caught ValueError in DataLoader worker process 0. 2、ValueError: high <= 0

[by0619]

Dear sir, I am a beginner tring to repeat your fantastic work. I made sure that the environment and PyTorch extensions are installed according to the instructions , then I also modified the dataset path in the [configuration files].But when training, I encountered these two problems.1、raise self.exc_type(msg) ValueError: Caught ValueError in DataLoader worker process 0.
2、ValueError: high <= 0
How can I solve theses problems?Thanks and sincere regards!

(spd) ➜ [/home/carl/SnowflakeNet/completion] python train.py --config ./configs/pcn_cd1.yaml
Loaded compiled 3D CUDA chamfer distance
0%| | 0/906 [00:00<?, ?it/s][Open3D WARNING] Read PCD failed: unable to open file: /home/carl/SnowflakeNet/completion/train/partial/04530566/6c1458eec06ad0c147a67ad1fb1cf329/02.pcd
[Open3D WARNING] Read PCD failed: unable to open file: /home/carl/SnowflakeNet/completion/train/partial/04530566/df307c1941ca4bbd8f6810e1a2b6aa04/05.pcd
0%| | 0/906 [00:00<?, ?it/s]
Traceback (most recent call last):
File "train.py", line 166, in
train(config)
File "train.py", line 91, in train
for batch_idx, (taxonomy_ids, model_ids, data) in enumerate(t):
File "/home/carl/anaconda3/envs/spd/lib/python3.7/site-packages/tqdm/std.py", line 1182, in iter
for obj in iterable:
File "/home/carl/anaconda3/envs/spd/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 435, in next
data = self._next_data()
File "/home/carl/anaconda3/envs/spd/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1085, in _next_data
return self._process_data(data)
File "/home/carl/anaconda3/envs/spd/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1111, in _process_data
data.reraise()
File "/home/carl/anaconda3/envs/spd/lib/python3.7/site-packages/torch/_utils.py", line 428, in reraise
raise self.exc_type(msg)
ValueError: Caught ValueError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/carl/anaconda3/envs/spd/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 198, in _worker_loop
data = fetcher.fetch(index)
File "/home/carl/anaconda3/envs/spd/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/carl/anaconda3/envs/spd/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/carl/SnowflakeNet/completion/core/datasets/dataset.py", line 34, in getitem
data = self.transforms(data)
File "/home/carl/SnowflakeNet/completion/core/datasets/utils.py", line 71, in call
data[k] = transform(v)
File "/home/carl/SnowflakeNet/completion/core/datasets/utils.py", line 190, in call
ptcloud = farthest_point_sample(ptcloud, n_valid)
File "/home/carl/SnowflakeNet/completion/core/datasets/utils.py", line 33, in farthest_point_sample
farthest = np.random.randint(0, N)
File "mtrand.pyx", line 748, in numpy.random.mtrand.RandomState.randint
File "_bounded_integers.pyx", line 1247, in numpy.random._bounded_integers._rand_int64
ValueError: high <= 0

[w1hao]

I had this problem as well and it has been resolved.
I just started using my previous dataset directly - the pointr dataset. However the test dataset path is not the same as required for this thesis.