PyTorch Getting Started example not working - pytorch

Question

I followed this tutorial in the Getting Started section on the PyTorch website: "Deep Learning with PyTorch: A 60 Minute Blitz" and I downloaded the code for "Training a Classifier" on the bottom of the page and I ran it, and it's not working for me. I'm using the CPU version of PyTorch if that makes a difference. I'm new to Python and basically learning it for Pytorch. Here's the error message, Control + K isn't working for me because I think the editing interface is different for the first few posts and Stack Overflow needs to fix it. Or it could just be my browser:
Traceback (most recent call last):
File "<string>", line 1, in <module>
File "C:\ProgramData\Anaconda3\lib\multiprocessing\spawn.py", line 105, in spawn_main
exitcode = _main(fd)
File "C:\ProgramData\Anaconda3\lib\multiprocessing\spawn.py", line 114, in _main
prepare(preparation_data)
File "C:\ProgramData\Anaconda3\lib\multiprocessing\spawn.py", line 225, in prepare
_fixup_main_from_path(data['init_main_from_path'])
File "C:\ProgramData\Anaconda3\lib\multiprocessing\spawn.py", line 277, in _fixup_main_from_path
run_name="__mp_main__")
File "C:\ProgramData\Anaconda3\lib\runpy.py", line 263, in run_path
pkg_name=pkg_name, script_name=fname)
File "C:\ProgramData\Anaconda3\lib\runpy.py", line 96, in _run_module_code
mod_name, mod_spec, pkg_name, script_name)
File "C:\ProgramData\Anaconda3\lib\runpy.py", line 85, in _run_code
exec(code, run_globals)
File "C:\Users\Anonymous\PycharmProjects\pytorchHelloWorld\train_network.py", line 100, in <module>
dataiter = iter(trainloader)
File "C:\ProgramData\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 819, in __iter__
return _DataLoaderIter(self)
File "C:\ProgramData\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 560, in __init__
w.start()
File "C:\ProgramData\Anaconda3\lib\multiprocessing\process.py", line 112, in start
self._popen = self._Popen(self)
File "C:\ProgramData\Anaconda3\lib\multiprocessing\context.py", line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "C:\ProgramData\Anaconda3\lib\multiprocessing\context.py", line 322, in _Popen
return Popen(process_obj)
File "C:\ProgramData\Anaconda3\lib\multiprocessing\popen_spawn_win32.py", line 33, in __init__
prep_data = spawn.get_preparation_data(process_obj._name)
File "C:\ProgramData\Anaconda3\lib\multiprocessing\spawn.py", line 143, in get_preparation_data
_check_not_importing_main()
File "C:\ProgramData\Anaconda3\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:/Users/Anonymous/PycharmProjects/pytorchHelloWorld/train_network.py", line 100, in <module>
dataiter = iter(trainloader)
File "C:\ProgramData\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 819, in __iter__
return _DataLoaderIter(self)
File "C:\ProgramData\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 560, in __init__
w.start()
File "C:\ProgramData\Anaconda3\lib\multiprocessing\process.py", line 112, in start
self._popen = self._Popen(self)
File "C:\ProgramData\Anaconda3\lib\multiprocessing\context.py", line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "C:\ProgramData\Anaconda3\lib\multiprocessing\context.py", line 322, in _Popen
return Popen(process_obj)
File "C:\ProgramData\Anaconda3\lib\multiprocessing\popen_spawn_win32.py", line 65, in __init__
reduction.dump(process_obj, to_child)
File "C:\ProgramData\Anaconda3\lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
BrokenPipeError: [Errno 32] Broken pipe

Answer 1

The error is likely due to multiprocessing in DataLoader and Windows since the tutorial is using num_workers=2. Python3 documentation shares some guidelines on this:
Make sure that the main module can be safely imported by a new Python interpreter without causing unintended side effects (such a starting a new process).
You can either set num_workers=0 or you need to wrap your code within if __name__ == '__main__'
# Safe DataLoader multiprocessing with Windows
if __name__ == '__main__':
# Code to load the data with num_workers > 1
Check this reply on PyTorch forum for more details and this issue on GitHub.