def test_tf_vpc_multi(sagemaker_session, tf_full_version):
"""Test Tensorflow multi-instance using the same VpcConfig for training and inference"""
instance_type = 'ml.c4.xlarge'
instance_count = 2
train_input = sagemaker_session.upload_data(
path=os.path.join(DATA_DIR, 'iris', 'data'),
key_prefix='integ-test-data/tf_iris')
script_path = os.path.join(DATA_DIR, 'iris', 'iris-dnn-classifier.py')
ec2_client = sagemaker_session.boto_session.client('ec2')
subnet_ids, security_group_id = get_or_create_vpc_resources(
ec2_client, sagemaker_session.boto_session.region_name)
setup_security_group_for_encryption(ec2_client, security_group_id)
estimator = TensorFlow(entry_point=script_path,
role='SageMakerRole',
framework_version=tf_full_version,
training_steps=1,
evaluation_steps=1,
hyperparameters={'input_tensor_name': 'inputs'},
train_instance_count=instance_count,
train_instance_type=instance_type,
sagemaker_session=sagemaker_session,
base_job_name='test-vpc-tf',
subnets=subnet_ids,
security_group_ids=[security_group_id],
encrypt_inter_container_traffic=True)
with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
estimator.fit(train_input)
print('training job succeeded: {}'.format(
estimator.latest_training_job.name))
job_desc = sagemaker_session.sagemaker_client.describe_training_job(
TrainingJobName=estimator.latest_training_job.name)
assert set(subnet_ids) == set(job_desc['VpcConfig']['Subnets'])
assert [security_group_id] == job_desc['VpcConfig']['SecurityGroupIds']
assert job_desc['EnableInterContainerTrafficEncryption'] is True
endpoint_name = estimator.latest_training_job.name
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
model = estimator.create_model()
json_predictor = model.deploy(initial_instance_count=instance_count,
instance_type='ml.c4.xlarge',
endpoint_name=endpoint_name)
features = [6.4, 3.2, 4.5, 1.5]
dict_result = json_predictor.predict({'inputs': features})
print('predict result: {}'.format(dict_result))
list_result = json_predictor.predict(features)
print('predict result: {}'.format(list_result))
assert dict_result == list_result
model_desc = sagemaker_session.sagemaker_client.describe_model(
ModelName=model.name)
assert set(subnet_ids) == set(model_desc['VpcConfig']['Subnets'])
assert [security_group_id] == model_desc['VpcConfig']['SecurityGroupIds']
def test_tuning_tf_vpc_multi(
sagemaker_session,
cpu_instance_type,
tensorflow_training_latest_version,
tensorflow_training_latest_py_version,
):
"""Test Tensorflow multi-instance using the same VpcConfig for training and inference"""
instance_type = cpu_instance_type
instance_count = 2
resource_path = os.path.join(DATA_DIR, "tensorflow_mnist")
script_path = "mnist.py"
ec2_client = sagemaker_session.boto_session.client("ec2")
subnet_ids, security_group_id = vpc_test_utils.get_or_create_vpc_resources(
ec2_client)
vpc_test_utils.setup_security_group_for_encryption(ec2_client,
security_group_id)
estimator = TensorFlow(
entry_point=script_path,
source_dir=resource_path,
role="SageMakerRole",
framework_version=tensorflow_training_latest_version,
py_version=tensorflow_training_latest_py_version,
instance_count=instance_count,
instance_type=instance_type,
sagemaker_session=sagemaker_session,
base_job_name="test-vpc-tf",
subnets=subnet_ids,
security_group_ids=[security_group_id],
encrypt_inter_container_traffic=True,
)
hyperparameter_ranges = {"epochs": IntegerParameter(1, 2)}
objective_metric_name = "accuracy"
metric_definitions = [{
"Name": objective_metric_name,
"Regex": "accuracy = ([0-9\\.]+)"
}]
tuner = HyperparameterTuner(
estimator,
objective_metric_name,
hyperparameter_ranges,
metric_definitions,
max_jobs=2,
max_parallel_jobs=2,
)
with timeout(minutes=TUNING_DEFAULT_TIMEOUT_MINUTES):
inputs = estimator.sagemaker_session.upload_data(
path=os.path.join(resource_path, "data"),
key_prefix="scriptmode/mnist")
tuning_job_name = unique_name_from_base("tune-tf", max_length=32)
print(
f"Started hyperparameter tuning job with name: {tuning_job_name}")
tuner.fit(inputs, job_name=tuning_job_name)
def test_transform_pytorch_vpc_custom_model_bucket(
sagemaker_session,
pytorch_inference_latest_version,
pytorch_inference_latest_py_version,
cpu_instance_type,
custom_bucket_name,
):
data_dir = os.path.join(DATA_DIR, "pytorch_mnist")
ec2_client = sagemaker_session.boto_session.client("ec2")
subnet_ids, security_group_id = get_or_create_vpc_resources(ec2_client)
model_data = sagemaker_session.upload_data(
path=os.path.join(data_dir, "model.tar.gz"),
bucket=custom_bucket_name,
key_prefix="integ-test-data/pytorch_mnist/model",
)
model = PyTorchModel(
model_data=model_data,
entry_point=os.path.join(data_dir, "mnist.py"),
role="SageMakerRole",
framework_version=pytorch_inference_latest_version,
py_version=pytorch_inference_latest_py_version,
sagemaker_session=sagemaker_session,
vpc_config={
"Subnets": subnet_ids,
"SecurityGroupIds": [security_group_id]
},
code_location="s3://{}".format(custom_bucket_name),
)
transform_input = sagemaker_session.upload_data(
path=os.path.join(data_dir, "transform", "data.npy"),
key_prefix="integ-test-data/pytorch_mnist/transform",
)
transformer = model.transformer(1, cpu_instance_type)
transformer.transform(
transform_input,
content_type="application/x-npy",
job_name=unique_name_from_base("test-transform-vpc"),
)
with timeout_and_delete_model_with_transformer(
transformer,
sagemaker_session,
minutes=TRANSFORM_DEFAULT_TIMEOUT_MINUTES):
transformer.wait()
model_desc = sagemaker_session.sagemaker_client.describe_model(
ModelName=transformer.model_name)
assert set(subnet_ids) == set(model_desc["VpcConfig"]["Subnets"])
assert [security_group_id
] == model_desc["VpcConfig"]["SecurityGroupIds"]
model_bucket, _ = s3.parse_s3_url(
model_desc["PrimaryContainer"]["ModelDataUrl"])
assert custom_bucket_name == model_bucket
def test_tuning_tf_vpc_multi(sagemaker_session):
"""Test Tensorflow multi-instance using the same VpcConfig for training and inference"""
instance_type = "ml.c4.xlarge"
instance_count = 2
script_path = os.path.join(DATA_DIR, "iris", "iris-dnn-classifier.py")
ec2_client = sagemaker_session.boto_session.client("ec2")
subnet_ids, security_group_id = vpc_test_utils.get_or_create_vpc_resources(
ec2_client, sagemaker_session.boto_region_name)
vpc_test_utils.setup_security_group_for_encryption(ec2_client,
security_group_id)
estimator = TensorFlow(
entry_point=script_path,
role="SageMakerRole",
training_steps=1,
evaluation_steps=1,
hyperparameters={"input_tensor_name": "inputs"},
train_instance_count=instance_count,
train_instance_type=instance_type,
sagemaker_session=sagemaker_session,
base_job_name="test-vpc-tf",
subnets=subnet_ids,
security_group_ids=[security_group_id],
encrypt_inter_container_traffic=True,
)
inputs = sagemaker_session.upload_data(
path=DATA_PATH, key_prefix="integ-test-data/tf_iris")
hyperparameter_ranges = {"learning_rate": ContinuousParameter(0.05, 0.2)}
objective_metric_name = "loss"
metric_definitions = [{"Name": "loss", "Regex": "loss = ([0-9\\.]+)"}]
tuner = HyperparameterTuner(
estimator,
objective_metric_name,
hyperparameter_ranges,
metric_definitions,
objective_type="Minimize",
max_jobs=2,
max_parallel_jobs=2,
)
tuning_job_name = unique_name_from_base("tune-tf", max_length=32)
with timeout(minutes=TUNING_DEFAULT_TIMEOUT_MINUTES):
tuner.fit(inputs, job_name=tuning_job_name)
print("Started hyperparameter tuning job with name:" + tuning_job_name)
time.sleep(15)
tuner.wait()
def test_transform_mxnet_vpc(sagemaker_session, mxnet_full_version):
data_path = os.path.join(DATA_DIR, "mxnet_mnist")
script_path = os.path.join(data_path, "mnist.py")
ec2_client = sagemaker_session.boto_session.client("ec2")
subnet_ids, security_group_id = get_or_create_vpc_resources(
ec2_client, sagemaker_session.boto_session.region_name
)
mx = MXNet(
entry_point=script_path,
role="SageMakerRole",
train_instance_count=1,
train_instance_type="ml.c4.xlarge",
sagemaker_session=sagemaker_session,
framework_version=mxnet_full_version,
subnets=subnet_ids,
security_group_ids=[security_group_id],
)
train_input = mx.sagemaker_session.upload_data(
path=os.path.join(data_path, "train"), key_prefix="integ-test-data/mxnet_mnist/train"
)
test_input = mx.sagemaker_session.upload_data(
path=os.path.join(data_path, "test"), key_prefix="integ-test-data/mxnet_mnist/test"
)
job_name = unique_name_from_base("test-mxnet-vpc")
with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
mx.fit({"train": train_input, "test": test_input}, job_name=job_name)
job_desc = sagemaker_session.sagemaker_client.describe_training_job(
TrainingJobName=mx.latest_training_job.name
)
assert set(subnet_ids) == set(job_desc["VpcConfig"]["Subnets"])
assert [security_group_id] == job_desc["VpcConfig"]["SecurityGroupIds"]
transform_input_path = os.path.join(data_path, "transform", "data.csv")
transform_input_key_prefix = "integ-test-data/mxnet_mnist/transform"
transform_input = mx.sagemaker_session.upload_data(
path=transform_input_path, key_prefix=transform_input_key_prefix
)
transformer = _create_transformer_and_transform_job(mx, transform_input)
with timeout_and_delete_model_with_transformer(
transformer, sagemaker_session, minutes=TRANSFORM_DEFAULT_TIMEOUT_MINUTES
):
transformer.wait()
model_desc = sagemaker_session.sagemaker_client.describe_model(
ModelName=transformer.model_name
)
assert set(subnet_ids) == set(model_desc["VpcConfig"]["Subnets"])
assert [security_group_id] == model_desc["VpcConfig"]["SecurityGroupIds"]
def test_transform_mxnet_vpc(sagemaker_session, mxnet_full_version):
data_path = os.path.join(DATA_DIR, 'mxnet_mnist')
script_path = os.path.join(data_path, 'mnist.py')
ec2_client = sagemaker_session.boto_session.client('ec2')
subnet_ids, security_group_id = get_or_create_vpc_resources(
ec2_client, sagemaker_session.boto_session.region_name)
mx = MXNet(entry_point=script_path,
role='SageMakerRole',
train_instance_count=1,
train_instance_type='ml.c4.xlarge',
sagemaker_session=sagemaker_session,
framework_version=mxnet_full_version,
subnets=subnet_ids,
security_group_ids=[security_group_id])
train_input = mx.sagemaker_session.upload_data(
path=os.path.join(data_path, 'train'),
key_prefix='integ-test-data/mxnet_mnist/train')
test_input = mx.sagemaker_session.upload_data(
path=os.path.join(data_path, 'test'),
key_prefix='integ-test-data/mxnet_mnist/test')
with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
mx.fit({'train': train_input, 'test': test_input})
job_desc = sagemaker_session.sagemaker_client.describe_training_job(
TrainingJobName=mx.latest_training_job.name)
assert set(subnet_ids) == set(job_desc['VpcConfig']['Subnets'])
assert [security_group_id] == job_desc['VpcConfig']['SecurityGroupIds']
transform_input_path = os.path.join(data_path, 'transform', 'data.csv')
transform_input_key_prefix = 'integ-test-data/mxnet_mnist/transform'
transform_input = mx.sagemaker_session.upload_data(
path=transform_input_path, key_prefix=transform_input_key_prefix)
transformer = _create_transformer_and_transform_job(mx, transform_input)
with timeout_and_delete_model_with_transformer(
transformer,
sagemaker_session,
minutes=TRANSFORM_DEFAULT_TIMEOUT_MINUTES):
transformer.wait()
model_desc = sagemaker_session.sagemaker_client.describe_model(
ModelName=transformer.model_name)
assert set(subnet_ids) == set(model_desc['VpcConfig']['Subnets'])
assert [security_group_id
] == model_desc['VpcConfig']['SecurityGroupIds']
