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.

[zzczzc-0118]

我也遇到过这个问题，现在已经解决了。我刚刚开始使用我以前的数据集 - pointr 数据集。但是，测试数据集路径与本论文所需的路径不同。 Hi, have you tested it yet? I would like to ask what is the path to the test dataset?