def _test_mnist_deploy(sagemaker_session, instance_type):
model_path = 'test/resources/mnist/model.tar.gz'
script_path = 'test/resources/mnist/mnist.py'
endpoint_name = sagemaker.utils.unique_name_from_base(
'sagemaker-chainer-test')
model_data = sagemaker_session.upload_data(
path=model_path,
key_prefix='sagemaker-chainer/models',
)
with timeout_and_delete_endpoint_by_name(endpoint_name,
sagemaker_session,
minutes=30):
chainer = ChainerModel(
model_data=model_data,
role='SageMakerRole',
entry_point=script_path,
sagemaker_session=sagemaker_session,
)
predictor = chainer.deploy(initial_instance_count=1,
instance_type=instance_type)
batch_size = 100
data = np.zeros(shape=(batch_size, 1, 28, 28), dtype='float32')
output = predictor.predict(data)
assert len(output) == batch_size
def test_deploy_model(chainer_training_job, sagemaker_session):
endpoint_name = 'test-chainer-deploy-model-{}'.format(sagemaker_timestamp())
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
desc = sagemaker_session.sagemaker_client.describe_training_job(TrainingJobName=chainer_training_job)
model_data = desc['ModelArtifacts']['S3ModelArtifacts']
script_path = os.path.join(DATA_DIR, 'chainer_mnist', 'mnist.py')
model = ChainerModel(model_data, 'SageMakerRole', entry_point=script_path, sagemaker_session=sagemaker_session)
predictor = model.deploy(1, "ml.m4.xlarge", endpoint_name=endpoint_name)
_predict_and_assert(predictor)
def test_deploy_model(chainer_training_job, sagemaker_session):
endpoint_name = 'test-chainer-deploy-model-{}'.format(sagemaker_timestamp())
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
desc = sagemaker_session.sagemaker_client.describe_training_job(TrainingJobName=chainer_training_job)
model_data = desc['ModelArtifacts']['S3ModelArtifacts']
script_path = os.path.join(DATA_DIR, 'chainer_mnist', 'mnist.py')
model = ChainerModel(model_data, 'SageMakerRole', entry_point=script_path, sagemaker_session=sagemaker_session)
predictor = model.deploy(1, "ml.m4.xlarge", endpoint_name=endpoint_name)
_predict_and_assert(predictor)
def test_deploy_model(chainer_local_training_job, sagemaker_local_session):
script_path = os.path.join(DATA_DIR, "chainer_mnist", "mnist.py")
model = ChainerModel(
chainer_local_training_job.model_data,
"SageMakerRole",
entry_point=script_path,
sagemaker_session=sagemaker_local_session,
)
predictor = model.deploy(1, "local")
try:
_predict_and_assert(predictor)
finally:
predictor.delete_endpoint()
def test_deploy_model(chainer_training_job, sagemaker_session):
endpoint_name = unique_name_from_base("test-chainer-deploy-model")
with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
desc = sagemaker_session.sagemaker_client.describe_training_job(
TrainingJobName=chainer_training_job)
model_data = desc["ModelArtifacts"]["S3ModelArtifacts"]
script_path = os.path.join(DATA_DIR, "chainer_mnist", "mnist.py")
model = ChainerModel(
model_data,
"SageMakerRole",
entry_point=script_path,
sagemaker_session=sagemaker_session,
)
predictor = model.deploy(1,
"ml.m4.xlarge",
endpoint_name=endpoint_name)
_predict_and_assert(predictor)