pytorch運行報錯：BrokenPipeError: [Errno 32] Broken pipe

錯誤如下：

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.
    ForkingPickler(file, protocol).dump(obj)
BrokenPipeError: [Errno 32] Broken pipe

錯誤原因：該問題的產生是由於windows下多線程的問題，和DataLoader類有關。將num_workers的數量修改爲0即可。這是windows下的一個bug，現在（2020/6/22）仍未解決。