问题
如果你用windows玩cifar10_tutorial.py,一定碰到过这个问题：
BrokenPipeError: [Errno 32] Broken pipe When i :"run cifar10_tutorial.py
先给解决方案，参考：https://github.com/pytorch/examples/issues/201
分析
用IPython运行，事个运行过程直到报错，列出来的详细情况如下，
(pytorch) E:\APytorchDev\TutorialCode>IPython cifar10_tutorial.py
Files already downloaded and verified
Files already downloaded and verified
Files already downloaded and verified
Files already downloaded and verified
Traceback (most recent call last):
File "<string>", line 1, in <module>
File "C:\ProgramData\Anaconda3\envs\pytorch\lib\multiprocessing\spawn.py", line 105, in spawn_main
exitcode = _main(fd)
File "C:\ProgramData\Anaconda3\envs\pytorch\lib\multiprocessing\spawn.py", line 114, in _main
prepare(preparation_data)
File "C:\ProgramData\Anaconda3\envs\pytorch\lib\multiprocessing\spawn.py", line 225, in prepare
_fixup_main_from_path(data['init_main_from_path'])
File "C:\ProgramData\Anaconda3\envs\pytorch\lib\multiprocessing\spawn.py", line 277, in _fixup_main_from_path
run_name="__mp_main__")
File "C:\ProgramData\Anaconda3\envs\pytorch\lib\runpy.py", line 263, in run_path
pkg_name=pkg_name, script_name=fname)
File "C:\ProgramData\Anaconda3\envs\pytorch\lib\runpy.py", line 96, in _run_module_code
mod_name, mod_spec, pkg_name, script_name)
File "C:\ProgramData\Anaconda3\envs\pytorch\lib\runpy.py", line 85, in _run_code
exec(code, run_globals)
File "E:\APytorchDev\TutorialCode\cifar10_tutorial.py", line 162, in <module>
for i, data in enumerate(trainloader, 0):
File "C:\ProgramData\Anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 819, in __iter__
return _DataLoaderIter(self)
File "C:\ProgramData\Anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 560, in __init__
w.start()
File "C:\ProgramData\Anaconda3\envs\pytorch\lib\multiprocessing\process.py", line 112, in start
self._popen = self._Popen(self)
File "C:\ProgramData\Anaconda3\envs\pytorch\lib\multiprocessing\context.py", line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "C:\ProgramData\Anaconda3\envs\pytorch\lib\multiprocessing\context.py", line 322, in _Popen
return Popen(process_obj)
File "C:\ProgramData\Anaconda3\envs\pytorch\lib\multiprocessing\popen_spawn_win32.py", line 33, in __init__
prep_data = spawn.get_preparation_data(process_obj._name)
File "C:\ProgramData\Anaconda3\envs\pytorch\lib\multiprocessing\spawn.py", line 143, in get_preparation_data
_check_not_importing_main()
File "C:\ProgramData\Anaconda3\envs\pytorch\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.
---------------------------------------------------------------------------
BrokenPipeError Traceback (most recent call last)
E:\APytorchDev\TutorialCode\cifar10_tutorial.py in <module>
160
161 running_loss = 0.0
--> 162 for i, data in enumerate(trainloader, 0):
163 # get the inputs
164 inputs, labels = data
C:\ProgramData\Anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py in __iter__(self)
817
818 def __iter__(self):
--> 819 return _DataLoaderIter(self)
820
821 def __len__(self):
C:\ProgramData\Anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py in __init__(self, loader)
558 # before it starts, and __del__ tries to join but will get:
559 # AssertionError: can only join a started process.
--> 560 w.start()
561 self.index_queues.append(index_queue)
562 self.workers.append(w)
C:\ProgramData\Anaconda3\envs\pytorch\lib\multiprocessing\process.py in start(self)
110 'daemonic processes are not allowed to have children'
111 _cleanup()
--> 112 self._popen = self._Popen(self)
113 self._sentinel = self._popen.sentinel
114 # Avoid a refcycle if the target function holds an indirect
C:\ProgramData\Anaconda3\envs\pytorch\lib\multiprocessing\context.py in _Popen(process_obj)
221 @staticmethod
222 def _Popen(process_obj):
--> 223 return _default_context.get_context().Process._Popen(process_obj)
224
225 class DefaultContext(BaseContext):
C:\ProgramData\Anaconda3\envs\pytorch\lib\multiprocessing\context.py in _Popen(process_obj)
320 def _Popen(process_obj):
321 from .popen_spawn_win32 import Popen
--> 322 return Popen(process_obj)
323
324 class SpawnContext(BaseContext):
C:\ProgramData\Anaconda3\envs\pytorch\lib\multiprocessing\popen_spawn_win32.py in __init__(self, process_obj)
63 try:
64 reduction.dump(prep_data, to_child)
---> 65 reduction.dump(process_obj, to_child)
66 finally:
67 set_spawning_popen(None)
C:\ProgramData\Anaconda3\envs\pytorch\lib\multiprocessing\reduction.py in dump(obj, file, protocol)
58 def dump(obj, file, protocol=None):
59 '''Replacement for pickle.dump() using ForkingPickler.'''
---> 60 ForkingPickler(file, protocol).dump(obj)
61
62 #
BrokenPipeError: [Errno 32] Broken pipe
(pytorch) E:\APytorchDev\TutorialCode>其实呢，报错的信息里已经提示了解决方案：
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.究其原因，大致是因为windows的multiprocessing library会不停地产生子进程（child process），如果用main保护起来，子进程在运行时因为会导入这个main，（只有一个main进程），所以避免了循环生成子进程。
On Windows the subprocesses will import (i.e. execute) the main module at start. You need to insert an if __name__ == '__main__': guard in the main module to avoid creating subprocesses recursively.