So I'm creating a recommendation system using this Federated Reconstruction tutorial on Tensorflow Federated. I want to use and extract the model and the modelweights but I run into some problems. I get attribute errors whenever I try saving a model or modelweight saying 'ModelWeights doesn't have 'save' function' etc. Is there anyway I can save the model weights so I can build it onto a DNN or Sequential Model?
Source Code: https://www.tensorflow.org/federated/tutorials/federated_reconstruction_for_matrix_factorization
I tried model.save(), model_weights.save_weights(), model.save_weights()