def test_async_fit(sagemaker_session, mxnet_full_version):
endpoint_name = 'test-mxnet-attach-deploy-{}'.format(sagemaker_timestamp())
with timeout(minutes=5):
script_path = os.path.join(DATA_DIR, 'mxnet_mnist', 'mnist.py')
data_path = os.path.join(DATA_DIR, 'mxnet_mnist')
mx = MXNet(entry_point=script_path, role='SageMakerRole', py_version=PYTHON_VERSION,
train_instance_count=1, train_instance_type='ml.c4.xlarge',
sagemaker_session=sagemaker_session, framework_version=mxnet_full_version,
distributions={'parameter_server': {'enabled': True}})
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')
mx.fit({'train': train_input, 'test': test_input}, wait=False)
training_job_name = mx.latest_training_job.name
print("Waiting to re-attach to the training job: %s" % training_job_name)
time.sleep(20)
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
print("Re-attaching now to: %s" % training_job_name)
estimator = MXNet.attach(training_job_name=training_job_name, sagemaker_session=sagemaker_session)
predictor = estimator.deploy(1, 'ml.m4.xlarge', endpoint_name=endpoint_name)
data = numpy.zeros(shape=(1, 1, 28, 28))
predictor.predict(data)
def test_attach_deploy(
mxnet_training_job, sagemaker_session, cpu_instance_type, cpu_instance_family
):
endpoint_name = unique_name_from_base("test-neo-attach-deploy")
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
estimator = MXNet.attach(mxnet_training_job, sagemaker_session=sagemaker_session)
estimator.compile_model(
target_instance_family=cpu_instance_family,
input_shape={"data": [1, 1, 28, 28]},
output_path=estimator.output_path,
)
serializer = JSONSerializer(content_type="application/vnd+python.numpy+binary")
predictor = estimator.deploy(
1,
cpu_instance_type,
serializer=serializer,
use_compiled_model=True,
endpoint_name=endpoint_name,
)
data = numpy.zeros(shape=(1, 1, 28, 28))
predictor.predict(data)
def test_async_fit(sagemaker_session):
endpoint_name = 'test-mxnet-attach-deploy-{}'.format(sagemaker_timestamp())
with timeout(minutes=5):
script_path = os.path.join(DATA_DIR, 'mxnet_mnist', 'mnist.py')
data_path = os.path.join(DATA_DIR, 'mxnet_mnist')
mx = MXNet(entry_point=script_path, role='SageMakerRole',
train_instance_count=1, train_instance_type='ml.c4.xlarge',
sagemaker_session=sagemaker_session)
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')
mx.fit({'train': train_input, 'test': test_input}, wait=False)
training_job_name = mx.latest_training_job.name
print("Waiting to re-attach to the training job: %s" % training_job_name)
time.sleep(20)
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
print("Re-attaching now to: %s" % training_job_name)
estimator = MXNet.attach(training_job_name=training_job_name, sagemaker_session=sagemaker_session)
predictor = estimator.deploy(1, 'ml.m4.xlarge', endpoint_name=endpoint_name)
data = numpy.zeros(shape=(1, 1, 28, 28))
predictor.predict(data)
def test_attach_deploy(mxnet_training_job, sagemaker_session):
endpoint_name = 'test-mxnet-attach-deploy-{}'.format(sagemaker_timestamp())
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
estimator = MXNet.attach(mxnet_training_job, sagemaker_session=sagemaker_session)
predictor = estimator.deploy(1, 'ml.m4.xlarge', endpoint_name=endpoint_name)
data = numpy.zeros(shape=(1, 1, 28, 28))
predictor.predict(data)
def test_attach_deploy(mxnet_training_job, sagemaker_session):
endpoint_name = 'test-mxnet-attach-deploy-{}'.format(sagemaker_timestamp())
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
estimator = MXNet.attach(mxnet_training_job, sagemaker_session=sagemaker_session)
predictor = estimator.deploy(1, 'ml.m4.xlarge', endpoint_name=endpoint_name)
data = numpy.zeros(shape=(1, 1, 28, 28))
predictor.predict(data)
def test_attach_deploy(mxnet_training_job, sagemaker_session, cpu_instance_type):
endpoint_name = "test-mxnet-attach-deploy-{}".format(sagemaker_timestamp())
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
estimator = MXNet.attach(mxnet_training_job, sagemaker_session=sagemaker_session)
predictor = estimator.deploy(1, cpu_instance_type, endpoint_name=endpoint_name)
data = numpy.zeros(shape=(1, 1, 28, 28))
result = predictor.predict(data)
assert result is not None
def test_edge_packaging_job(mxnet_training_job, sagemaker_session):
estimator = MXNet.attach(mxnet_training_job, sagemaker_session=sagemaker_session)
model = estimator.compile_model(
target_instance_family="rasp3b",
input_shape={"data": [1, 1, 28, 28], "softmax_label": [1]},
output_path=estimator.output_path,
)
model.package_for_edge(
output_path=estimator.output_path,
role=estimator.role,
model_name="sdk-test-model",
model_version="1.0",
)
def test_attach_deploy(mxnet_training_job, sagemaker_session):
with timeout(minutes=15):
estimator = MXNet.attach(mxnet_training_job,
sagemaker_session=sagemaker_session)
predictor = estimator.deploy(
1,
'ml.m4.xlarge',
endpoint_name='test-mxnet-attach-deploy-{}'.format(int(
time.time())))
try:
data = numpy.zeros(shape=(1, 1, 28, 28))
predictor.predict(data)
finally:
sagemaker_session.delete_endpoint(predictor.endpoint)
def test_async_fit(
sagemaker_session,
mxnet_training_latest_version,
mxnet_inference_latest_py_version,
cpu_instance_type,
):
endpoint_name = "test-mxnet-attach-deploy-{}".format(sagemaker_timestamp())
with timeout(minutes=5):
script_path = os.path.join(DATA_DIR, "mxnet_mnist", "mnist.py")
data_path = os.path.join(DATA_DIR, "mxnet_mnist")
mx = MXNet(
entry_point=script_path,
role="SageMakerRole",
py_version=mxnet_inference_latest_py_version,
instance_count=1,
instance_type=cpu_instance_type,
sagemaker_session=sagemaker_session,
framework_version=mxnet_training_latest_version,
distribution={"parameter_server": {
"enabled": True
}},
)
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")
mx.fit({"train": train_input, "test": test_input}, wait=False)
training_job_name = mx.latest_training_job.name
print("Waiting to re-attach to the training job: %s" %
training_job_name)
time.sleep(20)
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
print("Re-attaching now to: %s" % training_job_name)
estimator = MXNet.attach(training_job_name=training_job_name,
sagemaker_session=sagemaker_session)
predictor = estimator.deploy(1,
cpu_instance_type,
endpoint_name=endpoint_name)
data = numpy.zeros(shape=(1, 1, 28, 28))
result = predictor.predict(data)
assert result is not None
def test_attach_deploy(mxnet_training_job, sagemaker_session):
endpoint_name = 'test-mxnet-attach-deploy-{}'.format(sagemaker_timestamp())
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
estimator = MXNet.attach(mxnet_training_job,
sagemaker_session=sagemaker_session)
estimator.compile_model(target_instance_family='ml_m4',
input_shape={'data': [1, 1, 28, 28]},
output_path=estimator.output_path)
predictor = estimator.deploy(1,
'ml.m4.xlarge',
use_compiled_model=True,
endpoint_name=endpoint_name)
predictor.content_type = "application/vnd+python.numpy+binary"
data = numpy.zeros(shape=(1, 1, 28, 28))
predictor.predict(data)
def test_deploy_estimator_with_different_instance_types(
mxnet_training_job,
sagemaker_session,
cpu_instance_type,
alternative_cpu_instance_type,
):
def _deploy_estimator_and_assert_instance_type(estimator, instance_type):
# don't use timeout_and_delete_endpoint_by_name because this tests if
# deploy() creates a new endpoint config/endpoint each time
with timeout(minutes=45):
try:
predictor = estimator.deploy(1, instance_type)
model_name = predictor._model_names[0]
config_name = sagemaker_session.sagemaker_client.describe_endpoint(
EndpointName=predictor.endpoint_name
)["EndpointConfigName"]
config = sagemaker_session.sagemaker_client.describe_endpoint_config(
EndpointConfigName=config_name
)
finally:
predictor.delete_model()
predictor.delete_endpoint()
assert config["ProductionVariants"][0]["InstanceType"] == instance_type
return (model_name, predictor.endpoint_name, config_name)
estimator = MXNet.attach(mxnet_training_job, sagemaker_session)
estimator.base_job_name = "test-mxnet-deploy-twice"
old_model_name, old_endpoint_name, old_config_name = _deploy_estimator_and_assert_instance_type(
estimator, cpu_instance_type
)
new_model_name, new_endpoint_name, new_config_name = _deploy_estimator_and_assert_instance_type(
estimator, alternative_cpu_instance_type
)
assert old_model_name != new_model_name
assert old_endpoint_name != new_endpoint_name
assert old_config_name != new_config_name
