Keras documentation only appears to support HDF5 for storing weights:
https://keras.io/getting-started/faq/#how-can-i-save-a-keras-model

However I see that QuantConnect implemented an ObjectStore feature here:
https://www.quantconnect.com/docs/algorithm-reference/machine-learning#Machine-Learning-Storing-Trained-Models

But when I look at the Keras example here, nothing is being stored or loaded:
https://github.com/QuantConnect/Lean/blob/master/Algorithm.Python/KerasNeuralNetworkAlgorithm.py

How can I store trained keras models with weights in QuantConnect?

Thank You!