Load two model's weights into one on Keras

Question

What I'm trying to do is loading Keras layers' weights from model A and model B , both with same architecture, to model C . Let me explain:

I know that typical way of loading weights is:

modelC.load_weights('name.h5')

But by doing this you can only load from one model and, as I've said before, I do not want to load all of it. Is there any way you can partially load these weights? If not, how could I solve this?

What I really want would be something like this:

modelC_weights = 0.2 * modelA_weights + 0.8 * modelB_weights

Answer 1

Something ugly but that shoud work:

modelC.load_weights('name.h5')
weights1 = np.array(modelC.get_weights())

modelC.load_weights('name2.h5')
weights2 = np.array(modelC.get_weights())

modelC.set_weights(0.2 * weights1 + 0.8 * weights2)