Notice me of the runtimeError about "freeze_support()

First of all,I am a freshman in machine learning and pytorch.I downloaded an example of MNIST test from github.But it arose the same RuntimeError after I tried some different MNST test code.The RuntimeError is An attempt has been made to start a new process before the current process has finished its bootstrapping phase.
…The "freeze_support()"line can be omiitted if the program is not going to be frozen to produce an executable.But I didn’t imoport the mutipleprocessing module.So I am confused of it and want to know how to solve the problem.
The website above is where I copy the test code.And I run the pytorch in Anaconda in win10 only using my CPU. I haven’t intalled the cuda