RuntimeError: An attempt has been made to start a new process before the current pr

报错：

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.

 原因是多进程需要在main函数中运行，

然后将其放入main函数中，问题解决

if __name__=='__main__':
    # get some random training images
    dataiter = iter(trainloader)
    images, lables = dataiter.next()
    # show images
    imshow(torchvision.utils.make_grid(images)) #make_grid的作用是将若干幅图像拼成一幅图像。其中padding的作用就是子图像与子图像之间的pad有多宽。
    # print labels
    print(' '.join('%5s' % classes[lables[j]] for j in range(4)))