def test_conditional_pytorch_training_model_registration(
sagemaker_session,
role,
cpu_instance_type,
pipeline_name,
region_name,
):
base_dir = os.path.join(DATA_DIR, "pytorch_mnist")
entry_point = os.path.join(base_dir, "mnist.py")
input_path = sagemaker_session.upload_data(
path=os.path.join(base_dir, "training"),
key_prefix="integ-test-data/pytorch_mnist/training",
)
inputs = TrainingInput(s3_data=input_path)
instance_count = ParameterInteger(name="InstanceCount", default_value=1)
instance_type = ParameterString(name="InstanceType",
default_value="ml.m5.xlarge")
good_enough_input = ParameterInteger(name="GoodEnoughInput",
default_value=1)
in_condition_input = ParameterString(name="Foo", default_value="Foo")
pytorch_estimator = PyTorch(
entry_point=entry_point,
role=role,
framework_version="1.5.0",
py_version="py3",
instance_count=instance_count,
instance_type=instance_type,
sagemaker_session=sagemaker_session,
)
step_train = TrainingStep(
name="pytorch-train",
estimator=pytorch_estimator,
inputs=inputs,
)
step_register = RegisterModel(
name="pytorch-register-model",
estimator=pytorch_estimator,
model_data=step_train.properties.ModelArtifacts.S3ModelArtifacts,
content_types=["*"],
response_types=["*"],
inference_instances=["*"],
transform_instances=["*"],
description="test-description",
)
model = Model(
image_uri=pytorch_estimator.training_image_uri(),
model_data=step_train.properties.ModelArtifacts.S3ModelArtifacts,
sagemaker_session=sagemaker_session,
role=role,
)
model_inputs = CreateModelInput(
instance_type="ml.m5.large",
accelerator_type="ml.eia1.medium",
)
step_model = CreateModelStep(
name="pytorch-model",
model=model,
inputs=model_inputs,
)
step_cond = ConditionStep(
name="cond-good-enough",
conditions=[
ConditionGreaterThanOrEqualTo(left=good_enough_input, right=1),
ConditionIn(value=in_condition_input, in_values=["foo", "bar"]),
],
if_steps=[step_train, step_register],
else_steps=[step_model],
)
pipeline = Pipeline(
name=pipeline_name,
parameters=[
in_condition_input,
good_enough_input,
instance_count,
instance_type,
],
steps=[step_cond],
sagemaker_session=sagemaker_session,
)
try:
response = pipeline.create(role)
create_arn = response["PipelineArn"]
assert re.match(
rf"arn:aws:sagemaker:{region_name}:\d{{12}}:pipeline/{pipeline_name}",
create_arn,
)
execution = pipeline.start(parameters={})
assert re.match(
rf"arn:aws:sagemaker:{region_name}:\d{{12}}:pipeline/{pipeline_name}/execution/",
execution.arn,
)
execution = pipeline.start(parameters={"GoodEnoughInput": 0})
assert re.match(
rf"arn:aws:sagemaker:{region_name}:\d{{12}}:pipeline/{pipeline_name}/execution/",
execution.arn,
)
finally:
try:
pipeline.delete()
except Exception:
pass
def test_tuning_single_algo(
sagemaker_session,
role,
cpu_instance_type,
pipeline_name,
region_name,
):
base_dir = os.path.join(DATA_DIR, "pytorch_mnist")
entry_point = os.path.join(base_dir, "mnist.py")
input_path = sagemaker_session.upload_data(
path=os.path.join(base_dir, "training"),
key_prefix="integ-test-data/pytorch_mnist/training",
)
inputs = TrainingInput(s3_data=input_path)
instance_count = ParameterInteger(name="InstanceCount", default_value=1)
instance_type = ParameterString(name="InstanceType",
default_value="ml.m5.xlarge")
pytorch_estimator = PyTorch(
entry_point=entry_point,
role=role,
framework_version="1.5.0",
py_version="py3",
instance_count=instance_count,
instance_type=instance_type,
sagemaker_session=sagemaker_session,
enable_sagemaker_metrics=True,
max_retry_attempts=3,
)
min_batch_size = ParameterInteger(name="MinBatchSize", default_value=64)
max_batch_size = ParameterInteger(name="MaxBatchSize", default_value=128)
hyperparameter_ranges = {
"batch-size": IntegerParameter(min_batch_size, max_batch_size),
}
tuner = HyperparameterTuner(
estimator=pytorch_estimator,
objective_metric_name="test:acc",
objective_type="Maximize",
hyperparameter_ranges=hyperparameter_ranges,
metric_definitions=[{
"Name": "test:acc",
"Regex": "Overall test accuracy: (.*?);"
}],
max_jobs=2,
max_parallel_jobs=2,
)
step_tune = TuningStep(
name="my-tuning-step",
tuner=tuner,
inputs=inputs,
)
best_model = Model(
image_uri=pytorch_estimator.training_image_uri(),
model_data=step_tune.get_top_model_s3_uri(
top_k=0,
s3_bucket=sagemaker_session.default_bucket(),
),
sagemaker_session=sagemaker_session,
role=role,
)
model_inputs = CreateModelInput(
instance_type="ml.m5.large",
accelerator_type="ml.eia1.medium",
)
step_best_model = CreateModelStep(
name="1st-model",
model=best_model,
inputs=model_inputs,
)
second_best_model = Model(
image_uri=pytorch_estimator.training_image_uri(),
model_data=step_tune.get_top_model_s3_uri(
top_k=1,
s3_bucket=sagemaker_session.default_bucket(),
),
sagemaker_session=sagemaker_session,
role=role,
entry_point=entry_point,
source_dir=base_dir,
)
step_second_best_model = CreateModelStep(
name="2nd-best-model",
model=second_best_model,
inputs=model_inputs,
)
pipeline = Pipeline(
name=pipeline_name,
parameters=[
instance_count, instance_type, min_batch_size, max_batch_size
],
steps=[step_tune, step_best_model, step_second_best_model],
sagemaker_session=sagemaker_session,
)
try:
response = pipeline.create(role)
create_arn = response["PipelineArn"]
assert re.match(
rf"arn:aws:sagemaker:{region_name}:\d{{12}}:pipeline/{pipeline_name}",
create_arn,
)
for _ in retries(
max_retry_count=5,
exception_message_prefix=
"Waiting for a successful execution of pipeline",
seconds_to_sleep=10,
):
execution = pipeline.start(parameters={})
assert re.match(
rf"arn:aws:sagemaker:{region_name}:\d{{12}}:pipeline/{pipeline_name}/execution/",
execution.arn,
)
try:
execution.wait(delay=30, max_attempts=60)
except WaiterError:
pass
execution_steps = execution.list_steps()
assert len(execution_steps) == 3
for step in execution_steps:
assert step["StepStatus"] == "Succeeded"
break
finally:
try:
pipeline.delete()
except Exception:
pass
