tff.learning.build_federated_evaluation

Builds the TFF computation for federated evaluation of the given model.

tff.learning.build_federated_evaluation(
    model_fn,
    use_experimental_simulation_loop: bool = False
)

Used in the tutorials
Federated Learning for Image Classification

Args
`model_fn`	A no-arg function that returns a `tff.learning.Model`. This method must not capture TensorFlow tensors or variables and use them. The model must be constructed entirely from scratch on each invocation, returning the same pre-constructed model each call will result in an error.
`use_experimental_simulation_loop`	Controls the reduce loop function for input dataset. An experimental reduce loop is used for simulation.

Returns
A federated computation (an instance of `tff.Computation`) that accepts model parameters and federated data, and returns the evaluation metrics as aggregated by `tff.learning.Model.federated_output_computation`.

Args