Model cloning is similar to calling a model on new inputs, except that it creates new layers (and thus new weights) instead of sharing the weights of the existing layers.
clone_model(model, input_tensors = NULL, clone_function = NULL)
Instance of Keras model (could be a functional model or a Sequential model).
Optional list of input tensors to build the model upon. If not provided, placeholders will be created.
Callable to be used to clone each layer in the target
By passing a custom callable, you can customize your copy of the model,
e.g. by wrapping certain layers of interest (you might want to replace all
LSTM instances with equivalent