DataLoader Error

[myagmur01]

Hi Irina,

Thanks for this great work. I am having an issue with DataLoader of Pytorch, it seems giving memory error or something. Can you help how to handle this? Actually it is MNIST, loading should not matter. I decreased the batch to 1 as well, but still having the same issue.

Traceback (most recent call last): File "./experiments/train.py", line 103, in train_loss_all.append(train(epoch, train_loader, model, optimizer, device)) File "./experiments/train.py", line 43, in train for batch_idx, (data, target) in tqdm(enumerate(train_loader), total=len(train_loader)): File "/home/yagmur/anaconda3/envs/ode/lib/python3.6/site-packages/tqdm/_tqdm.py", line 1005, in iter for obj in iterable: File "/home/yagmur/anaconda3/envs/ode/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 576, in next idx, batch = self._get_batch() File "/home/yagmur/anaconda3/envs/ode/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 553, in _get_batch success, data = self._try_get_batch() File "/home/yagmur/anaconda3/envs/ode/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 519, in _try_get_batch raise RuntimeError('DataLoader worker (pid(s) {}) exited unexpectedly'.format(pids_str)) RuntimeError: DataLoader worker (pid(s) 5169, 5170) exited unexpectedly

[saparina]

Hi! Sorry about the delay with the answer. Did you try to change num_workers parameter in all DataLoaders (like here)?