has anybody else tried to visualize weights of variational autoencoders? why no Gabors?pic.twitter.com/tFL02tBCaR
@edersantana Maybe it's your dataset? Did you try on MNIST?
-
-
@fchollet this is CIFAR10 with conv weights. MNIST is kinda Gabor if I add l2 regularization. Were yours Gabor?Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.