问题 My goal is to load a base model from a .hdf5 file (it's a Keras model), and continue to train it with federated learning. Here is how I initialize the base model for FL: def model_fn(): model = tf.keras.load_model(path/to/model.hdf5) return tff.learning.from_keras_model(model=model, dummy_batch=db, loss=loss, metrics=metrics) trainer = tff.learning.build_federated_averaging_process(model_fn) state = trainer.initialize() However, it seems like the resulting state.model weights are randomly