def main() -> None:
"""Load data, create and start client."""
args = parse_args()
client_setting = get_client_setting(args.setting, args.cid)
# Configure logger
configure(identifier=f"client:{client_setting.cid}", host=args.log_host)
# Load model
model = keyword_cnn(input_shape=(80, 40, 1), seed=SEED)
# Load local data partition
(
(xy_train_partitions, xy_test_partitions),
_,
) = tf_hotkey_partitioned.load_data(
iid_fraction=client_setting.iid_fraction,
num_partitions=client_setting.num_clients,
)
(x_train, y_train) = xy_train_partitions[client_setting.partition]
(x_test, y_test) = xy_test_partitions[client_setting.partition]
if client_setting.dry_run:
x_train = x_train[0:100]
y_train = y_train[0:100]
x_test = x_test[0:50]
y_test = y_test[0:50]
# Start client
client = VisionClassificationClient(
client_setting.cid,
model,
(x_train, y_train),
(x_test, y_test),
client_setting.delay_factor,
10,
normalization_factor=100.0,
)
fl.client.start_client(args.server_address, client)
def main() -> None:
"""Start server and train a number of rounds."""
args = parse_args()
# Configure logger
configure(identifier="server", host=args.log_host)
server_setting = get_setting(args.setting).server
log(INFO, "server_setting: %s", server_setting)
# Load evaluation data
(_, _), (x_test,
y_test) = tf_hotkey_partitioned.load_data(iid_fraction=0.0,
num_partitions=1)
if server_setting.dry_run:
x_test = x_test[0:50]
y_test = y_test[0:50]
# Load model (for centralized evaluation)
model = keyword_cnn(input_shape=(80, 40, 1), seed=SEED)
# Strategy
eval_fn = get_eval_fn(model=model,
num_classes=10,
xy_test=(x_test, y_test))
on_fit_config_fn = get_on_fit_config_fn(
lr_initial=server_setting.lr_initial,
timeout=server_setting.training_round_timeout,
partial_updates=server_setting.partial_updates,
)
if server_setting.strategy == "fedavg":
strategy = fl.server.strategy.FedAvg(
fraction_fit=server_setting.sample_fraction,
min_fit_clients=server_setting.min_sample_size,
min_available_clients=server_setting.min_num_clients,
eval_fn=eval_fn,
on_fit_config_fn=on_fit_config_fn,
)
if server_setting.strategy == "fast-and-slow":
if server_setting.training_round_timeout is None:
raise ValueError(
"No `training_round_timeout` set for `fast-and-slow` strategy")
strategy = fl.server.strategy.FastAndSlow(
fraction_fit=server_setting.sample_fraction,
min_fit_clients=server_setting.min_sample_size,
min_available_clients=server_setting.min_num_clients,
eval_fn=eval_fn,
on_fit_config_fn=on_fit_config_fn,
importance_sampling=server_setting.importance_sampling,
dynamic_timeout=server_setting.dynamic_timeout,
dynamic_timeout_percentile=0.9,
alternating_timeout=server_setting.alternating_timeout,
r_fast=1,
r_slow=1,
t_fast=math.ceil(0.5 * server_setting.training_round_timeout),
t_slow=server_setting.training_round_timeout,
)
if server_setting.strategy == "fedfs-v0":
if server_setting.training_round_timeout is None:
raise ValueError(
"No `training_round_timeout` set for `fedfs-v0` strategy")
t_fast = (math.ceil(0.5 * server_setting.training_round_timeout)
if server_setting.training_round_timeout_short is None else
server_setting.training_round_timeout_short)
strategy = fl.server.strategy.FedFSv0(
fraction_fit=server_setting.sample_fraction,
min_fit_clients=server_setting.min_sample_size,
min_available_clients=server_setting.min_num_clients,
eval_fn=eval_fn,
on_fit_config_fn=on_fit_config_fn,
r_fast=1,
r_slow=1,
t_fast=t_fast,
t_slow=server_setting.training_round_timeout,
)
if server_setting.strategy == "qffedavg":
strategy = fl.server.strategy.QFedAvg(
q_param=0.2,
qffl_learning_rate=0.1,
fraction_fit=server_setting.sample_fraction,
min_fit_clients=server_setting.min_sample_size,
min_available_clients=server_setting.min_num_clients,
eval_fn=eval_fn,
on_fit_config_fn=on_fit_config_fn,
)
# Run server
fl.server.start_server(
DEFAULT_SERVER_ADDRESS,
config={"num_rounds": server_setting.rounds},
strategy=strategy,
)