Google I/O is a wrap! Catch up on TensorFlow sessions View sessions

tff.learning.state_with_new_model_weights

Returns a ServerState with updated model weights.

Used in the notebooks

Used in the tutorials

server_state A server state object returned by an iterative training process like tff.learning.build_federated_averaging_process.
trainable_weights A list of numpy values in the order of the original model's trainable_variables.
non_trainable_weights A list of numpy values in the order of the original model's non_trainable_variables.

A new server ServerState object which can be passed to the next method of the iterative process.