def test_federated_cifar_structure(self):
crop_shape = (28, 28, 3)
cifar_train, cifar_test = cifar100_dataset.get_federated_datasets(
train_client_batch_size=3,
test_client_batch_size=5,
crop_shape=crop_shape)
sample_train_ds = cifar_train.create_tf_dataset_for_client(
cifar_train.client_ids[0])
train_batch = next(iter(sample_train_ds))
train_batch_shape = tuple(train_batch[0].shape)
self.assertEqual(train_batch_shape, (3, 28, 28, 3))
sample_test_ds = cifar_test.create_tf_dataset_for_client(
cifar_test.client_ids[0])
test_batch = next(iter(sample_test_ds))
test_batch_shape = tuple(test_batch[0].shape)
self.assertEqual(test_batch_shape, (5, 28, 28, 3))
def test_preprocess_applied(self, mock_load_data):
if tf.config.list_logical_devices('GPU'):
self.skipTest('skip GPU test')
# Mock out the actual data loading from disk. Assert that the preprocessing
# function is applied to the client data, and that only the ClientData
# objects we desired are used.
#
# The correctness of the preprocessing function is tested in other tests.
mock_train = mock.create_autospec(tff.simulation.ClientData)
mock_test = mock.create_autospec(tff.simulation.ClientData)
mock_load_data.return_value = (mock_train, mock_test)
_, _ = cifar100_dataset.get_federated_datasets()
mock_load_data.assert_called_once()
# Assert the training and testing data are preprocessed.
self.assertEqual(mock_train.mock_calls,
mock.call.preprocess(mock.ANY).call_list())
self.assertEqual(mock_test.mock_calls,
mock.call.preprocess(mock.ANY).call_list())
def test_raises_negative_epochs(self):
with self.assertRaisesRegex(
ValueError, 'client_epochs_per_round must be a positive integer.'):
cifar100_dataset.get_federated_datasets(train_client_epochs_per_round=-1)
def test_raises_length_2_crop(self):
with self.assertRaises(ValueError):
cifar100_dataset.get_federated_datasets(crop_shape=(32, 32))
with self.assertRaises(ValueError):
cifar100_dataset.get_centralized_datasets(crop_shape=(32, 32))
def run_federated(
iterative_process_builder: Callable[..., tff.templates.IterativeProcess],
client_epochs_per_round: int,
client_batch_size: int,
clients_per_round: int,
client_datasets_random_seed: Optional[int] = None,
crop_size: Optional[int] = 24,
total_rounds: Optional[int] = 1500,
experiment_name: Optional[str] = 'federated_cifar100',
root_output_dir: Optional[str] = '/tmp/fed_opt',
max_eval_batches: Optional[int] = None,
**kwargs):
"""Runs an iterative process on the CIFAR-100 classification task.
This method will load and pre-process dataset and construct a model used for
the task. It then uses `iterative_process_builder` to create an iterative
process that it applies to the task, using
`federated_research.utils.training_loop`.
We assume that the iterative process has the following functional type
signatures:
* `initialize`: `( -> S@SERVER)` where `S` represents the server state.
* `next`: `<S@SERVER, {B*}@CLIENTS> -> <S@SERVER, T@SERVER>` where `S`
represents the server state, `{B*}` represents the client datasets,
and `T` represents a python `Mapping` object.
The iterative process must also have a callable attribute `get_model_weights`
that takes as input the state of the iterative process, and returns a
`tff.learning.ModelWeights` object.
Args:
iterative_process_builder: A function that accepts a no-arg `model_fn`, and
returns a `tff.templates.IterativeProcess`. The `model_fn` must return a
`tff.learning.Model`.
client_epochs_per_round: An integer representing the number of epochs of
training performed per client in each training round.
client_batch_size: An integer representing the batch size used on clients.
clients_per_round: An integer representing the number of clients
participating in each round.
client_datasets_random_seed: An optional int used to seed which clients are
sampled at each round. If `None`, no seed is used.
crop_size: An optional integer representing the resulting size of input
images after preprocessing.
total_rounds: The number of federated training rounds.
experiment_name: The name of the experiment being run. This will be appended
to the `root_output_dir` for purposes of writing outputs.
root_output_dir: The name of the root output directory for writing
experiment outputs.
max_eval_batches: If set to a positive integer, evaluation datasets are
capped to at most that many batches. If set to None or a nonpositive
integer, the full evaluation datasets are used.
**kwargs: Additional arguments configuring the training loop. For details
on supported arguments, see
`federated_research/utils/training_utils.py`.
"""
crop_shape = (crop_size, crop_size, 3)
cifar_train, _ = cifar100_dataset.get_federated_datasets(
train_client_epochs_per_round=client_epochs_per_round,
train_client_batch_size=client_batch_size,
crop_shape=crop_shape)
_, cifar_test = cifar100_dataset.get_centralized_datasets(
train_batch_size=client_batch_size,
crop_shape=crop_shape)
if max_eval_batches and max_eval_batches >= 1:
cifar_test = cifar_test.take(max_eval_batches)
input_spec = cifar_train.create_tf_dataset_for_client(
cifar_train.client_ids[0]).element_spec
model_builder = functools.partial(
resnet_models.create_resnet18,
input_shape=crop_shape,
num_classes=NUM_CLASSES)
loss_builder = tf.keras.losses.SparseCategoricalCrossentropy
metrics_builder = lambda: [tf.keras.metrics.SparseCategoricalAccuracy()]
def tff_model_fn() -> tff.learning.Model:
return tff.learning.from_keras_model(
keras_model=model_builder(),
input_spec=input_spec,
loss=loss_builder(),
metrics=metrics_builder())
training_process = iterative_process_builder(tff_model_fn)
client_datasets_fn = training_utils.build_client_datasets_fn(
dataset=cifar_train,
clients_per_round=clients_per_round,
random_seed=client_datasets_random_seed)
evaluate_fn = training_utils.build_centralized_evaluate_fn(
eval_dataset=cifar_test,
model_builder=model_builder,
loss_builder=loss_builder,
metrics_builder=metrics_builder)
logging.info('Training model:')
logging.info(model_builder().summary())
training_loop.run(
iterative_process=training_process,
client_datasets_fn=client_datasets_fn,
validation_fn=evaluate_fn,
test_fn=evaluate_fn,
total_rounds=total_rounds,
experiment_name=experiment_name,
root_output_dir=root_output_dir,
**kwargs)