Hi everyone,
I’ve been trying to load a new dataset using DataLoader but I get the following error:
Traceback (most recent call last):
File "C:/Users/User/PycharmProjects/STN_LSTM/STN_LSTM.py", line 98, in <module>
main()
File "C:/Users/User/PycharmProjects/STN_LSTM/STN_LSTM.py", line 83, in main
for i_batch, sample_batched in enumerate(train_loader):
File "C:\Users\User\Anaconda3\envs\tensorflow\lib\site-packages\torch\utils\data\dataloader.py", line 451, in __iter__
return _DataLoaderIter(self)
File "C:\Users\User\Anaconda3\envs\tensorflow\lib\site-packages\torch\utils\data\dataloader.py", line 239, in __init__
w.start()
File "C:\Users\User\Anaconda3\envs\tensorflow\lib\multiprocessing\process.py", line 105, in start
self._popen = self._Popen(self)
File "C:\Users\User\Anaconda3\envs\tensorflow\lib\multiprocessing\context.py", line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "C:\Users\User\Anaconda3\envs\tensorflow\lib\multiprocessing\context.py", line 322, in _Popen
return Popen(process_obj)
File "C:\Users\User\Anaconda3\envs\tensorflow\lib\multiprocessing\popen_spawn_win32.py", line 65, in __init__
reduction.dump(process_obj, to_child)
File "C:\Users\User\Anaconda3\envs\tensorflow\lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
TypeError: cannot serialize '_io.BufferedReader' object
I’ve followed the data loading tutorial (https://pytorch.org/tutorials/beginner/data_loading_tutorial.html) and have successfully created a dataset class inheriting from Dataset that overrides len and getitem so that they return the size of the dataset and an indexed sample respectively. I can also iterate and print samples from this dataset.
However, once I run the code below that error pops up.
train_loader = DataLoader(mnist_clutterred, batch_size=64,
shuffle=True, num_workers=4)
print(len(train_loader))
for i_batch, sample_batched in enumerate(train_loader):
print(i_batch)
Any ideas on why I get that error?
Thanks in advance!