@karpathy @fchollet @sedielem @_mayfa @j26774 comparing char-rnn models, very different results for keras & lasagne!pic.twitter.com/dkynepPH9e
-
Any progress or insights on this?
it really looks like an initialization or learning rate issue. Please look into it.
-
-
the initialization and learning rate are the same. i suspect their is an internal implementation diff somewhere.
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.