#Keras coders. Does model.getlayer('Dense_1').kernel_regularizer=l1(0.1)
actually change the value during runtime/training? I am looking to change hyper parameters to implement population based training from DeepMind @fchollet @maxpumperla
It does not. You should instantiate a new model with new regularizers, and then load the old weights into it.
-
-
Thanks!
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.