def _dist_search_fn(temp_dir, study_id, tuner_id):
"""Multi-process safe tuner instantiation and tuner.search()."""
# Jitter instantiation so as to avoid contention on study
# creation and dataset download.
time.sleep(int(tuner_id[5:])) # tuner_id is formatted as 'tuner%d'
# Dataset must be loaded independently in sub-process.
(x, y), (val_x, val_y) = _load_data(temp_dir)
tuner = CloudTuner(
_build_model,
project_id=_PROJECT_ID,
region=_REGION,
objective="acc",
hyperparameters=_HPS,
max_trials=5,
study_id=study_id,
directory=os.path.join(temp_dir, study_id, tuner_id),
)
tuner.tuner_id = tuner_id
tuner.search(
x=x,
y=y,
epochs=2,
steps_per_epoch=20,
validation_steps=10,
validation_data=(val_x, val_y),
)
return tuner
def testCloudTunerHyperparameters(self):
"""Test case to configure Tuner with HyperParameters object."""
study_id = "{}_hyperparameters".format(_STUDY_ID_BASE)
self._study_id = study_id
tuner = CloudTuner(
_build_model,
project_id=_PROJECT_ID,
region=_REGION,
objective="acc",
hyperparameters=_HPS,
max_trials=5,
study_id=study_id,
directory=os.path.join(self.get_temp_dir(), study_id),
)
# "Search space summary" comes first, but the order of
# "learning_rate (Float)" and "num_layers (Int)" is not deterministic,
# hence they are wrapped as look-ahead assertions in the regex.
self._assert_output(
tuner.search_space_summary,
r".*Search space summary(?=.*learning_rate \(Float\))"
r"(?=.*num_layers \(Int\).*)",
)
tuner.search(
x=self._x,
y=self._y,
epochs=2,
steps_per_epoch=20,
validation_steps=10,
validation_data=(self._val_x, self._val_y),
)
self._assert_results_summary(tuner.results_summary)
def testCloudTunerStudyConfig(self):
"""Test case to configure Tuner with StudyConfig object."""
# Configure the search space. Specification:
# https://cloud.google.com/ai-platform/optimizer/docs/reference/rest/v1/projects.locations.studies#StudyConfig # pylint: disable=line-too-long
study_config = {
"metrics": [{"goal": "MAXIMIZE", "metric": "acc"}],
"parameters": [
{
"discrete_value_spec": {"values": [0.0001, 0.001, 0.01]},
"parameter": "learning_rate",
"type": "DISCRETE",
},
{
"integer_value_spec": {"max_value": 10, "min_value": 2},
"parameter": "num_layers",
"type": "INTEGER",
},
{
"discrete_value_spec": {"values": [32, 64, 96, 128]},
"parameter": "units",
"type": "DISCRETE",
},
],
"algorithm": "ALGORITHM_UNSPECIFIED",
"automatedStoppingConfig": {
"decayCurveStoppingConfig": {"useElapsedTime": True}
},
}
study_id = "{}_study_config".format(_STUDY_ID_BASE)
self._study_id = study_id
tuner = CloudTuner(
_build_model,
project_id=_PROJECT_ID,
region=_REGION,
study_config=study_config,
study_id=study_id,
max_trials=5,
directory=os.path.join(self.get_temp_dir(), study_id),
)
self._assert_output(
tuner.search_space_summary,
r".*Search space summary(?=.*learning_rate \(Choice\))"
r"(?=.*num_layers \(Int\))(?=.*units \(Int\))",
)
tuner.search(
x=self._x,
y=self._y,
epochs=2,
steps_per_epoch=20,
validation_steps=10,
validation_data=(self._val_x, self._val_y),
)
self._assert_results_summary(tuner.results_summary)
def testCloudTunerDatasets(self):
"""Test case to configure Tuner with tf.data.Dataset as input data."""
train_dataset = (
tf.data.Dataset.from_tensor_slices((self._x, self._y))
.batch(128)
.cache()
.prefetch(1000)
)
eval_dataset = (
tf.data.Dataset.from_tensor_slices((self._val_x, self._val_y))
.batch(128)
.cache()
.prefetch(1000)
)
study_id = "{}_dataset".format(_STUDY_ID_BASE)
self._study_id = study_id
tuner = CloudTuner(
_build_model,
project_id=_PROJECT_ID,
region=_REGION,
objective="acc",
hyperparameters=_HPS,
study_id=study_id,
max_trials=5,
directory=os.path.join(self.get_temp_dir(), study_id),
)
self._assert_output(
tuner.search_space_summary,
r".*Search space summary(?=.*learning_rate \(Float\))"
r"(?=.*num_layers \(Int\).*)",
)
tuner.search(
x=train_dataset,
epochs=2,
steps_per_epoch=20,
validation_steps=10,
validation_data=eval_dataset,
)
self._assert_results_summary(tuner.results_summary)
