@fchollet any recommendations for implementing truncated BPTT with Keras currently, besides using train_on_batch and stateful LSTMs?
@seaandsailor that is definitely what I would use. You could also roll out a Theano-based RNN layer and configure scan
-
-
@fchollet Thanks! I think I'll go with fit_on_batch as it is portable.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.