pytorch-cifar复现问题

[FYM1209]

我直接把作者的文件都下来，在pycharm打开运行main.py，为什么出这些错
prep_data = spawn.get_preparation_data(process_obj._name)
File "F:\Download\envs\pytorch\lib\multiprocessing\spawn.py", line 154, in get_preparation_data
_check_not_importing_main()
File "F:\Download\envs\pytorch\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main
raise RuntimeError('''
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.

[Dabu9]

相同情况，还没找到解决办法

[fzjcdt]

num_workers=0

[henryzhuhr]

要把代码放在if name == 'main':里面才不会报错

[samrere]

我问过一样的问题：
https://discuss.pytorch.org/t/dataloader-worker-failed/140518
Windows系统都这样。要么让num_worker = 0； 要么把代码放在 if name == 'main': 里