I’m currently working on two models that train on separate (but related) types of data. I’d like to make a combined model that than take in an instance of each of the types of data, runs them through each of the models that was pre-trained individually, and then has a few feed-forward layers at the top that process the combined result of the two individual models.
So far, I know that I can modify forward to take in both inputs, so I just have copied the architectures of my individual models into the combined one, process them both separately by running them through the correct layers in forward(), and then combining the results as I described. What I can’t figure out how to do is used the pre trained models, rather than having to use the same architecture from scratch, in the combined model.
I’d really appreciate any input! Thanks!