News for hackers. Stuff that matters.
Re:AI generation of fake celeb images by johnwatson11218 on Sunday April 22, 2018 @05:29PM (#16898703)
I did the Udacity nanodegree last year and the only part I never understood was the call to the "de-convolution" operator in tensorflow. It seems that every description keeps painting the same picture of how the two networks are in competition to reach "nash equilibrium". I think they really skimp over what a "de-convolution" actually is.
Re:AI generation of fake celeb images by libdjml on Sunday April 22, 2018 @05:44PM (#16898772)
Did you do the DLND? If so, they may have updated the videos, as the current explanation of conv2d_transpose seemed fairly clear to me. Or maybe it was some of the extra materials they provided that helped. I think I found a good video on YT also.
Re:AI generation of fake celeb images by johnwatson11218 on Sunday April 22, 2018 @10:08PM (#16900010)
yea I did that program. I'll check it out again at some point and see if they added more description on that part of it.