I tried implementing a custom dataset, which works fine, but as soon as I specify to use multiple workers for accelerating the loading, I get a huge chained error message. The example here doesn’t make any practical sense, it is just the minimal example to reproduce the error. Curiously, the error happens on windows, but not when running it on ubuntu. (both pytorch 1.6, and I tested both python 3.7 and 3.8 on both systems)
Can anyone give me a hint what is going wrong and possibly how to fix it?
import torch
class MyDataset(torch.utils.data.Dataset):
def __init__(self):
super().__init__()
def __len__(self):
return 10
def __getitem__(self, idx):
return torch.ones((1,))
dataset1 = MyDataset()
loader = torch.utils.data.DataLoader(
dataset1, batch_size=2, num_workers=0)
x = next(iter(loader)) # works fine
dataset2 = MyDataset()
loader_parallel = torch.utils.data.DataLoader(
dataset2, batch_size=2, num_workers=1)
y = next(iter(loader_parallel)) # explodes
The error message is
Traceback (most recent call last):
File "<string>", line 1, in <module>
File "C:\ProgramData\Anaconda3\envs\smp2\lib\multiprocessing\spawn.py", line 105, in spawn_main
exitcode = _main(fd)
File "C:\ProgramData\Anaconda3\envs\smp2\lib\multiprocessing\spawn.py", line 114, in _main
prepare(preparation_data)
File "C:\ProgramData\Anaconda3\envs\smp2\lib\multiprocessing\spawn.py", line 225, in prepare
_fixup_main_from_path(data['init_main_from_path'])
File "C:\ProgramData\Anaconda3\envs\smp2\lib\multiprocessing\spawn.py", line 277, in _fixup_main_from_path
run_name="__mp_main__")
File "C:\ProgramData\Anaconda3\envs\smp2\lib\runpy.py", line 263, in run_path
pkg_name=pkg_name, script_name=fname)
File "C:\ProgramData\Anaconda3\envs\smp2\lib\runpy.py", line 96, in _run_module_code
mod_name, mod_spec, pkg_name, script_name)
File "C:\ProgramData\Anaconda3\envs\smp2\lib\runpy.py", line 85, in _run_code
exec(code, run_globals)
File "path\to\my\file.py", line 27, in <module>
y = next(iter(loader_parallel)) # explodes
File "C:\ProgramData\Anaconda3\envs\smp2\lib\site-packages\torch\utils\data\dataloader.py", line 279, in __iter__
return _MultiProcessingDataLoaderIter(self)
File "C:\ProgramData\Anaconda3\envs\smp2\lib\site-packages\torch\utils\data\dataloader.py", line 719, in __init__
w.start()
File "C:\ProgramData\Anaconda3\envs\smp2\lib\multiprocessing\process.py", line 112, in start
self._popen = self._Popen(self)
File "C:\ProgramData\Anaconda3\envs\smp2\lib\multiprocessing\context.py", line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "C:\ProgramData\Anaconda3\envs\smp2\lib\multiprocessing\context.py", line 322, in _Popen
return Popen(process_obj)
File "C:\ProgramData\Anaconda3\envs\smp2\lib\multiprocessing\popen_spawn_win32.py", line 46, in __init__
prep_data = spawn.get_preparation_data(process_obj._name)
File "C:\ProgramData\Anaconda3\envs\smp2\lib\multiprocessing\spawn.py", line 143, in get_preparation_data
_check_not_importing_main()
File "C:\ProgramData\Anaconda3\envs\smp2\lib\multiprocessing\spawn.py", line 136, in _check_not_importing_main
is not going to be frozen to produce an executable.'')
RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.
This probably means that you are not using fork to start your
child processes and you have forgotten to use the proper idiom
in the main module:
if __name__ == '__main__':
freeze_support()
...
The "freeze_support()" line can be omitted if the program
is not going to be frozen to produce an executable.
Traceback (most recent call last):
File "C:\ProgramData\Anaconda3\envs\smp2\lib\site-packages\torch\utils\data\dataloader.py", line 761, in _try_get_data
data = self._data_queue.get(timeout=timeout)
File "C:\ProgramData\Anaconda3\envs\smp2\lib\multiprocessing\queues.py", line 105, in get
raise Empty
_queue.Empty
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "path\to\my\file.py", line 27, in <module>
y = next(iter(loader_parallel)) # explodes
File "C:\ProgramData\Anaconda3\envs\smp2\lib\site-packages\torch\utils\data\dataloader.py", line 345, in __next__
data = self._next_data()
File "C:\ProgramData\Anaconda3\envs\smp2\lib\site-packages\torch\utils\data\dataloader.py", line 841, in _next_data
idx, data = self._get_data()
File "C:\ProgramData\Anaconda3\envs\smp2\lib\site-packages\torch\utils\data\dataloader.py", line 808, in _get_data
success, data = self._try_get_data()
File "C:\ProgramData\Anaconda3\envs\smp2\lib\site-packages\torch\utils\data\dataloader.py", line 774, in _try_get_data
raise RuntimeError('DataLoader worker (pid(s) {}) exited unexpectedly'.format(pids_str))
RuntimeError: DataLoader worker (pid(s) 5144) exited unexpectedly