Hello, my program gets stuck at random iteration when it tries to load the datasets with the following code.
import os
from ogb.nodeproppred import Evaluator, PygNodePropPredDataset
from tqdm import tqdm
from torch_geometric.loader import NeighborLoader, NeighborSampler
#dataset_name = 'ogbn-products'
dataset_name = 'ogbn-arxiv'
print("Loading dataset...")
root = os.path.join('data', dataset_name)
dataset = PygNodePropPredDataset(dataset_name, root)
split_idx = dataset.get_idx_split()
evaluator = Evaluator(name=dataset_name)
data = dataset[0]
train_idx = split_idx['train']
train_loader = NeighborLoader(data, input_nodes=train_idx, num_neighbors=[15, 10, 5],
batch_size=1024, shuffle=True, num_workers=12)
subgraph_loader = NeighborLoader(data, input_nodes=None, num_neighbors=[-1],
batch_size=4096, shuffle=False, num_workers=12)
for epoch in range(1, 21):
for batch in tqdm(train_loader, desc="Testing"):
pass
After I have interrupted it, it shows
Loading dataset...
Loading: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 89/89 [00:03<00:00, 27.66it/s]
Loading: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 89/89 [00:02<00:00, 35.51it/s]
Loading: 1%|█▊ | 1/89 [00:00<00:41, 2.11it/s]Loading: 3%|█████▎ | 3/89 [00:16<07:54, 5.51s/it]
Traceback (most recent call last):
File "test3.py", line 24, in <module>
for batch in tqdm(train_loader, desc="Loading"):
File "/home/mankit/anaconda3/envs/gnn/lib/python3.8/site-packages/tqdm/std.py", line 1195, in __iter__
for obj in iterable:
File "/home/mankit/anaconda3/envs/gnn/lib/python3.8/site-packages/torch_geometric/loader/base.py", line 36, in __next__
return self.transform_fn(next(self.iterator))
File "/home/mankit/anaconda3/envs/gnn/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 652, in __next__
data = self._next_data()
File "/home/mankit/anaconda3/envs/gnn/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1330, in _next_data
idx, data = self._get_data()
File "/home/mankit/anaconda3/envs/gnn/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1296, in _get_data
success, data = self._try_get_data()
File "/home/mankit/anaconda3/envs/gnn/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1134, in _try_get_data
data = self._data_queue.get(timeout=timeout)
File "/home/mankit/anaconda3/envs/gnn/lib/python3.8/multiprocessing/queues.py", line 107, in get
if not self._poll(timeout):
File "/home/mankit/anaconda3/envs/gnn/lib/python3.8/multiprocessing/connection.py", line 257, in poll
return self._poll(timeout)
File "/home/mankit/anaconda3/envs/gnn/lib/python3.8/multiprocessing/connection.py", line 424, in _poll
r = wait([self], timeout)
File "/home/mankit/anaconda3/envs/gnn/lib/python3.8/multiprocessing/connection.py", line 931, in wait
ready = selector.select(timeout)
File "/home/mankit/anaconda3/envs/gnn/lib/python3.8/selectors.py", line 415, in select
fd_event_list = self._selector.poll(timeout)
KeyboardInterrupt
Hello, my program gets stuck at random iteration when it tries to load the datasets with the following code.
After I have interrupted it, it shows
It happens with: pytorch: 1.12.0 py3.8_cuda11.3_cudnn8.3.2_0 torch-geometric: 2.0.5 torch-scatter: 2.0.9 torch-sparse: 0.6.14 ogb: 1.3.3