def test_autoensemble_end_to_end(self):
train_dataset, test_dataset = testing_utils.get_holdout_data(
train_samples=128,
test_samples=64,
input_shape=(10, ),
num_classes=10,
random_seed=42)
# TODO: Consider performing `tf.data.Dataset` transformations
# within get_holdout_data function.
train_dataset = train_dataset.batch(32)
test_dataset = test_dataset.batch(32)
def build_model(hp):
model = tf.keras.Sequential()
model.add(
tf.keras.layers.Dense(units=hp.Int('units',
min_value=32,
max_value=512,
step=32),
activation='relu'))
model.add(tf.keras.layers.Dense(10, activation='softmax'))
model.compile(optimizer=tf.keras.optimizers.Adam(
hp.Choice('learning_rate', values=[1e-2, 1e-3, 1e-4])),
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
return model
# This allows us to have a shared storage for all the autoensemble phases
# that occur in the repeat phase.
autoensemble_storage = InMemoryStorage()
input_phase = InputPhase(train_dataset, test_dataset)
# pylint: disable=g-long-lambda
repeat_phase = RepeatPhase([
lambda: KerasTunerPhase(
tuners.RandomSearch(build_model,
objective='val_accuracy',
max_trials=3,
executions_per_trial=1,
directory=self.test_subdirectory,
project_name='helloworld_' + str(
int(time.time())),
overwrite=True)),
lambda: AutoEnsemblePhase(ensemblers=[
MeanEnsembler('sparse_categorical_crossentropy', 'adam',
['accuracy'])
],
ensemble_strategies=[GrowStrategy()],
storage=autoensemble_storage)
],
repetitions=3)
# pylint: enable=g-long-lambda
controller = SequentialController(phases=[input_phase, repeat_phase])
model_search = ModelSearch(controller)
model_search.run()
self.assertIsInstance(
model_search.get_best_models(num_models=1)[0], MeanEnsemble)
def test_tuner_end_to_end(self):
train_dataset, test_dataset = testing_utils.get_test_data(
train_samples=128,
test_samples=64,
input_shape=(10, ),
num_classes=10,
random_seed=42)
# TODO: Consider performing `tf.data.Dataset` transformations
# within get_test_data function.
train_dataset = train_dataset.batch(32)
test_dataset = test_dataset.batch(32)
def build_model(hp):
model = tf.keras.Sequential()
model.add(
tf.keras.layers.Dense(units=hp.Int('units',
min_value=32,
max_value=512,
step=32),
activation='relu'))
model.add(tf.keras.layers.Dense(10, activation='softmax'))
model.compile(optimizer=tf.keras.optimizers.Adam(
hp.Choice('learning_rate', values=[1e-2, 1e-3, 1e-4])),
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
return model
# Define phases.
tuner = tuners.RandomSearch(build_model,
objective='val_accuracy',
max_trials=3,
executions_per_trial=1,
directory=self.test_subdirectory,
project_name='helloworld')
tuner_phase = KerasTunerPhase(tuner,
train_dataset,
validation_data=test_dataset)
def build_ensemble():
ensemble = MeanEnsemble(submodels=tuner_phase.get_best_models(
num_models=2))
ensemble.compile(optimizer=tf.keras.optimizers.Adam(0.01),
loss='mse',
metrics=['mae'])
return [ensemble]
ensemble_phase = TrainKerasModelsPhase(build_ensemble,
dataset=train_dataset)
controller = SequentialController(phases=[tuner_phase, ensemble_phase])
# Execute phases.
model_search = ModelSearch(controller)
model_search.run()
self.assertIsInstance(
model_search.get_best_models(num_models=1)[0], MeanEnsemble)
decay_rate=hp.Choice("decay_rate", [0.5, 0.75, 0.95]),
staircase=True,
)
model.compile(
loss="sparse_categorical_crossentropy",
optimizer=tf.keras.optimizers.RMSprop(learning_rate=lr_schedule),
metrics=["sparse_categorical_accuracy"],
)
return model
tuner = tuners.RandomSearch(
build_model,
objective="val_sparse_categorical_accuracy",
max_trials=5,
executions_per_trial=3,
directory="test_dir",
)
tuner.search_space_summary()
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.cifar10.load_data()
train_dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train))
test_dataset = tf.data.Dataset.from_tensor_slices((x_test, y_test))
BUFFER_SIZE = 10000
BATCH_SIZE = 64
def scale(image, label):
image = tf.cast(image, tf.float32)