On Fri, 9 Mar 2018 11:38:55, Robert Kern wrote:

> > Sorry for being a bit inaccurate.
> > My Scala code actually mirrors the NumPy based random initialization, so
> > I sample with Gaussian of mean = 0 and std dev = 1, then multiply with
> Have you verified this? I.e. save out the Scala-initialized network and
> load it up with numpy to check the mean and std dev? How about if you run
> the numpy NN training with the Scala-initialized network? Does that also
> diverge?

I did what you suggested and it turned out my NumPy NN code
was behaving exactly as the Scala code when using Scala-initialized network.
After digging deeper into this I managed to find and fix a bug in how I was
the random initilization and it's working correctly now.

Thanks a lot for your help!

NumPy-Discussion mailing list

Reply via email to