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()
serializer.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_inferentia_deploy_model(
mxnet_training_job,
sagemaker_session,
inf_instance_type,
inf_instance_family,
inferentia_mxnet_latest_version,
inferentia_mxnet_latest_py_version,
):
endpoint_name = unique_name_from_base("test-neo-deploy-model")
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
desc = sagemaker_session.sagemaker_client.describe_training_job(
TrainingJobName=mxnet_training_job)
model_data = desc["ModelArtifacts"]["S3ModelArtifacts"]
script_path = os.path.join(DATA_DIR, "mxnet_mnist", "mnist_neo.py")
role = "SageMakerRole"
model = MXNetModel(
model_data,
role,
entry_point=script_path,
framework_version=inferentia_mxnet_latest_version,
py_version=inferentia_mxnet_latest_py_version,
sagemaker_session=sagemaker_session,
)
model.compile(
target_instance_family=inf_instance_family,
input_shape={
"data": [1, 1, 28, 28],
"softmax_label": [1]
},
role=role,
job_name=unique_name_from_base(
"test-deploy-model-compilation-job"),
output_path="/".join(model_data.split("/")[:-1]),
)
serializer = JSONSerializer()
serializer.CONTENT_TYPE = "application/vnd+python.numpy+binary"
predictor = model.deploy(1,
inf_instance_type,
serializer=serializer,
endpoint_name=endpoint_name)
data = numpy.zeros(shape=(1, 1, 28, 28))
predictor.predict(data)