在windows上运行pytorch时，稍不注意就会遇到freeze_support()的错误。解决这种错误只要把代码放到if name == “main”: 中运行就可以了。就忍不住来深究下这个问题。

这是一个关于windows上多进程实现的恩特。在windows上，子进程会自动import启动它的这个文件，而在import的时候是会自动执行这些语句的。如果不加__main__限制的化，就会无限递归创建子进程，进而报错。于是import的时候使用 name == “main” 保护起来就可以了。

出现错误：

Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "D:\opt\anaconda3\lib\multiprocessing\spawn.py", line 105, in spawn_main
    exitcode = _main(fd)
  File "D:\opt\anaconda3\lib\multiprocessing\spawn.py", line 114, in _main
    prepare(preparation_data)
  File "D:\opt\anaconda3\lib\multiprocessing\spawn.py", line 225, in prepare
    _fixup_main_from_path(data['init_main_from_path'])
  File "D:\opt\anaconda3\lib\multiprocessing\spawn.py", line 277, in _fixup_main_from_path
    run_name="__mp_main__")
  File "D:\opt\anaconda3\lib\runpy.py", line 263, in run_path
    pkg_name=pkg_name, script_name=fname)
  File "D:\opt\anaconda3\lib\runpy.py", line 96, in _run_module_code
    mod_name, mod_spec, pkg_name, script_name)
  File "D:\opt\anaconda3\lib\runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "D:\ML_Study\PyTorch-garbage-classify\garbage-classification-using-pytorch.py", line 59, in <module>
    image,label = next(iter(train_loader))
  File "D:\opt\anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 819, in __iter__
    return _DataLoaderIter(self)
  File "D:\opt\anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 560, in __init__
    w.start()
  File "D:\opt\anaconda3\lib\multiprocessing\process.py", line 105, in start
    self._popen = self._Popen(self)
  File "D:\opt\anaconda3\lib\multiprocessing\context.py", line 223, in _Popen
    return _default_context.get_context().Process._Popen(process_obj)
  File "D:\opt\anaconda3\lib\multiprocessing\context.py", line 322, in _Popen
    return Popen(process_obj)
  File "D:\opt\anaconda3\lib\multiprocessing\popen_spawn_win32.py", line 33, in __init__
    prep_data = spawn.get_preparation_data(process_obj._name)
  File "D:\opt\anaconda3\lib\multiprocessing\spawn.py", line 143, in get_preparation_data
    _check_not_importing_main()
  File "D:\opt\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.

解决方案：

if __name__ == '__main__':
    # 代码

通过上述方式实验完美解决，这里说下我的实验版本

In [1]: import torch

In [2]: import torchvision

In [3]: torch.version
Out[3]: ‘1.0.1’

In [4]: torchvision.version
Out[4]: ‘0.2.2’