def test_xy_train_volume_by_class_with_federated_dataset():
# Prepare
dataset_name = "fashion-mnist-100p-b1_045"
xy_partitions, _, _ = load_splits(dataset_name)
num_examples_expected = sum([x.shape[0] for x, _ in xy_partitions])
# We need to find out which classes are present in our dataset
# (actually we know it but making it a bit more adaptable in case we parameterize it)
all_classes = set()
for _, y_train in xy_partitions:
classes = np.unique(y_train)
for c in classes:
all_classes.add(c)
num_classes_total = len(all_classes)
results = []
# Execute
for xy_train in xy_partitions:
_, y_train = xy_train
r = xy_train_volume_by_class(num_classes=num_classes_total,
xy_train=xy_train)
results.append(r)
# Assert
num_examples_actual = 0
for r in results:
num_examples_actual += sum(r)
assert num_examples_expected == num_examples_actual
def main(_):
# Set exit callback
if FLAGS.push_results:
atexit.register(after_main,
group_name=FLAGS.group_name,
task_name=FLAGS.task_name)
# Load data
xy_train_partitions, xy_val, xy_test = load_splits(FLAGS.dataset)
# Execute training
start = time.time()
partition_id = FLAGS.partition_id
hist_metrics = None # For unitary training
if partition_id is not None: # Use only a single partition if required (unitary)
hist, loss, acc = run.unitary_training(
model_name=FLAGS.model,
xy_train=xy_train_partitions[partition_id],
xy_val=xy_val,
xy_test=xy_test,
E=FLAGS.E,
B=FLAGS.B,
)
else:
hist, _, hist_metrics, loss, acc = run.federated_training(
model_name=FLAGS.model,
xy_train_partitions=xy_train_partitions,
xy_val=xy_val,
xy_test=xy_test,
R=FLAGS.R,
E=FLAGS.E,
C=FLAGS.C,
B=FLAGS.B,
)
end = time.time()
# Write results
res = {
"group_name": FLAGS.group_name,
"task_name": FLAGS.task_name,
"task_label": FLAGS.task_label,
"dataset": FLAGS.dataset,
"model": FLAGS.model,
"R": FLAGS.R,
"E": FLAGS.E,
"C": FLAGS.C,
"B": FLAGS.B,
"partition_id": partition_id,
"start": start,
"end": end,
"duration": end - start,
"loss": float(loss),
"acc": float(acc),
"hist": hist,
"hist_metrics": hist_metrics,
}
storage.write_json(res, fname="results.json")
def benchmark_evolutionary_avg():
fn_name = benchmark_evolutionary_avg.__name__
logging.info("Starting {}".format(fn_name))
# Load dataset
xy_parts, xy_val, xy_test = load_splits("fashion-mnist-100p-noniid-03cpp")
# Run Federated Learning with evolutionary aggregation
evaluator = Evaluator(orig_cnn_compiled(), xy_val) # FIXME refactor
aggregator = EvoAgg(evaluator)
_, _, _, loss_a, acc_a = run.federated_training(
"blog_cnn",
xy_parts,
xy_val,
xy_test,
R=DEFAULT_R,
E=DEFAULT_E,
C=DEFAULT_C,
B=DEFAULT_B,
aggregator=aggregator,
)
# Run Federated Learning with weighted average aggregation
_, _, _, loss_b, acc_b = run.federated_training(
"blog_cnn",
xy_parts,
xy_val,
xy_test,
R=DEFAULT_R,
E=DEFAULT_E,
C=DEFAULT_C,
B=DEFAULT_B,
)
# Write results JSON
results = {}
results["loss_a"] = float(loss_a)
results["acc_a"] = float(acc_a)
results["loss_b"] = float(loss_b)
results["acc_b"] = float(acc_b)
# TODO add histories
storage.write_json(results, fname="EA-WA-results.json")
def unitary_versus_federated(
benchmark_name: str,
model_name: str,
dataset_name: str,
R: int = DEFAULT_R,
E: int = DEFAULT_E,
C: float = DEFAULT_C,
B: int = DEFAULT_B,
):
"""
:param C: Fraction of participants used in each round of training
"""
logging.info(f"Starting {benchmark_name}")
xy_train_partitions, xy_val, xy_test = load_splits(dataset_name)
start = time.time()
# Train CNN on a single partition ("unitary learning")
# TODO train n models on all partitions
partition_id = 0
xy_train = xy_train_partitions[partition_id]
logging.info(f"Run unitary training using partition {partition_id}")
ul_hist, ul_loss, ul_acc = unitary_training(model_name,
xy_train,
xy_val,
xy_test,
E=R * E,
B=B)
# Train CNN using federated learning on all partitions
logging.info("Run federated learning using all partitions")
fl_hist, _, _, fl_loss, fl_acc = federated_training(model_name,
xy_train_partitions,
xy_val,
xy_test,
R=R,
E=E,
C=C,
B=B)
end = time.time()
# Write results JSON
results = {
"name": benchmark_name,
"start": start,
"end": end,
"duration": end - start,
"R": R,
"E": E,
"C": C,
"B": B,
"unitary_learning": {
"loss": float(ul_loss),
"acc": float(ul_acc),
"hist": ul_hist,
},
"federated_learning": {
"loss": float(fl_loss),
"acc": float(fl_acc),
"hist": fl_hist,
},
}
storage.write_json(results, fname="results.json")
# Plot results
# TODO include aggregated participant histories in plot
plot_data: List[Tuple[str, List[float], Optional[List[int]]]] = [
(
"Unitary Learning",
ul_hist["val_acc"],
[i for i in range(1,
len(ul_hist["val_acc"]) + 1, 1)],
),
(
"Federated Learning",
fl_hist["val_acc"],
[i for i in range(E,
len(fl_hist["val_acc"]) * E + 1, E)],
),
]
# FIXME use different filenames for different datasets
task_accuracies.plot(plot_data, fname="plot.png")
