I've recently been testing around tensorflow and keras and I've been doing a project to classify images. So far it's been working but now I want to use real data mixed with the image in order to solve a different problem.

Imagine that I have a camera that takes pictures of a living room and then, combined with the input from sensors I want it to do a different classification. Basically a CNN mixed with a regular ANN.


1 Answer 1


You need to define sub-modules of the network and then somehow merge them and do further processing on the whole data. This is usually done by creating smaller neural networks within the bigger one. For example, you have one sub-network that processes images (say convolutional network) and another one that processes tabular data (say, dense network), then you combine the outputs of both networks and put some layers on top (dense layers are the simplest case). By merging I mean in here operations like concatenation of the outputs, but other operations are possible as well, for example if all the dimensions match you can simply add them.

Recent example of such network was described on the Google Cloud blog (diagram below), where they used three sources of data: raw videos, tabular data on the movies, and tabular data on viewers of the movies, to forecast the movie audience.

enter image description here

  • $\begingroup$ thank you so much. That's kiiindaaa what I was thinking of doing, but with my limited experience. Things can get pretty interesting and complicated once you go deep. Again .. thank you very much $\endgroup$
    – morcillo
    Nov 23, 2018 at 14:41
  • 1
    $\begingroup$ @morcillo Here you can find Keras documentation keras.io/getting-started/functional-api-guide/… that you can find helpful $\endgroup$
    – Tim
    Nov 23, 2018 at 14:45
  • $\begingroup$ oops sorry ... forgot about marking as accepted ... accepted now $\endgroup$
    – morcillo
    Nov 23, 2018 at 14:53

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.