But more importantly, you can do stark raving mad stuff like this. This API is totally out of controlpic.twitter.com/vimau9dEeh
-
@fchollet The model([e, f]) syntax is exactly what I was missing in keras! Been using Lasagne's get_output/PrettyTensor's templates instead.
@poolio btw can Lasagne handle shared layers easily (e.g. the first dense layer in the example above)? Just curious...
-
-
@fchollet yep, you can just do c = get_output(output_layer, inputs=a); d = get_output(output_layer, inputs=b) -
@fchollet would be awesome to go beyond that and allow arbitrary node substitution. Something like a symbolic version of feed_dict - Show replies
New conversation -
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.