-
Notifications
You must be signed in to change notification settings - Fork 18
Open
Description
Hello! Some questions ocurrs when I'm trying to run the code :
- the models trained from multiple sources are merged by the code:
model.add(Merge(training_net, mode='concat')) (in line 950)
then what's the reason for the new input block in the code below
model.add(Dense(2, input_shape=(total_hid,))) (line 958)
what's more, Merge are discarded in keras 2.0 , new method is recommend like:
model = Model(inputs=[input,input2],outputs=[output,output2])
so should i try to merge the net as well as the input in line 958?
2.i wonder if something goes wrong with the code since some function ocurrs only once,such as they are defined but not used, besides it seems the rnn network is not complete , as far as the documents are concerned , there're only 2 Dense in function: get_rnn_fea()
Thanks a lot !
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
No labels