Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Questions about the model #2

Open
lx233 opened this issue Nov 25, 2020 · 1 comment
Open

Questions about the model #2

lx233 opened this issue Nov 25, 2020 · 1 comment

Comments

@lx233
Copy link

lx233 commented Nov 25, 2020

Hello! Some questions ocurrs when I'm trying to run the code :

  1. 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 !
@xypan1232
Copy link
Owner

First, please install the software dependecy as the readme.
model.add(Dense(2, input_shape=(total_hid,))) is the fully connected layer to the output layer. ideep was developed in 2016, i have no idea the Merge function in Keras 2.0. but it is better to install the required keras version as mentioned in readme file.
2. Yes, some fucntions were not used, i did not clean the code.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants