Client TensorFlow logic for Federated Averaging.

Inherits From: ClientDeltaFn

model A tff.learning.Model instance.
optimizer A optimizer_base.Optimizer instance, or a no-arg callable that returns a tf.keras.Optimizer instance..
client_weighting A value of tff.learning.ClientWeighting that specifies a built-in weighting method, or a callable that takes the model output and returns a tensor that provides the weight in the federated average of model deltas.
use_experimental_simulation_loop Controls the reduce loop function for input dataset. An experimental reduce loop is used for simulation.

variables Returns all the variables of this object.

Note this only includes variables that are part of the state of this object, and not the model variables themselves.



View source