def create_model(self,
role=None,
predictor_cls=None,
serializer=IdentitySerializer(),
deserializer=BytesDeserializer(),
vpc_config_override=vpc_utils.VPC_CONFIG_DEFAULT,
**kwargs):
"""Create a model to deploy.
The serializer and deserializer are only used to define a default
Predictor. They are ignored if an explicit predictor class is passed in.
Other arguments are passed through to the Model class.
Args:
role (str): The ``ExecutionRoleArn`` IAM Role ARN for the ``Model``,
which is also used during transform jobs. If not specified, the
role from the Estimator will be used.
predictor_cls (Predictor): The predictor class to use when
deploying the model.
serializer (:class:`~sagemaker.serializers.BaseSerializer`): A
serializer object, used to encode data for an inference endpoint
(default: :class:`~sagemaker.serializers.IdentitySerializer`).
deserializer (:class:`~sagemaker.deserializers.BaseDeserializer`): A
deserializer object, used to decode data from an inference
endpoint (default: :class:`~sagemaker.deserializers.BytesDeserializer`).
vpc_config_override (dict[str, list[str]]): Optional override for VpcConfig set on
the model. Default: use subnets and security groups from this Estimator.
* 'Subnets' (list[str]): List of subnet ids.
* 'SecurityGroupIds' (list[str]): List of security group ids.
**kwargs: Additional arguments for creating a :class:`~sagemaker.model.ModelPackage`.
.. tip::
You can find additional parameters for using this method at
:class:`~sagemaker.model.ModelPackage` and
:class:`~sagemaker.model.Model`.
Returns:
a Model ready for deployment.
"""
removed_kwargs("content_type", kwargs)
removed_kwargs("accept", kwargs)
if predictor_cls is None:
def predict_wrapper(endpoint, session):
return Predictor(endpoint, session, serializer, deserializer)
predictor_cls = predict_wrapper
role = role or self.role
return sagemaker.ModelPackage(
role,
algorithm_arn=self.algorithm_arn,
model_data=self.model_data,
vpc_config=self.get_vpc_config(vpc_config_override),
sagemaker_session=self.sagemaker_session,
predictor_cls=predictor_cls,
**kwargs)
def test_removed_kwargs():
kwarg = {"a": 1}
removed_kwargs("b", kwarg)
with pytest.warns(DeprecationWarning):
kwarg = {"a": 1, "b": 3}
removed_kwargs("b", kwarg)
def __init__(
self,
endpoint_name,
sagemaker_session=None,
serializer=JSONSerializer(),
deserializer=JSONDeserializer(),
model_name=None,
model_version=None,
**kwargs,
):
"""Initialize a ``TensorFlowPredictor``.
See :class:`~sagemaker.predictor.Predictor` for more info about parameters.
Args:
endpoint_name (str): The name of the endpoint to perform inference
on.
sagemaker_session (sagemaker.session.Session): Session object which
manages interactions with Amazon SageMaker APIs and any other
AWS services needed. If not specified, the estimator creates one
using the default AWS configuration chain.
serializer (callable): Optional. Default serializes input data to
json. Handles dicts, lists, and numpy arrays.
deserializer (callable): Optional. Default parses the response using
``json.load(...)``.
model_name (str): Optional. The name of the SavedModel model that
should handle the request. If not specified, the endpoint's
default model will handle the request.
model_version (str): Optional. The version of the SavedModel model
that should handle the request. If not specified, the latest
version of the model will be used.
"""
removed_kwargs("content_type", kwargs)
removed_kwargs("accept", kwargs)
super(TensorFlowPredictor, self).__init__(
endpoint_name,
sagemaker_session,
serializer,
deserializer,
)
attributes = []
if model_name:
attributes.append("tfs-model-name={}".format(model_name))
if model_version:
attributes.append("tfs-model-version={}".format(model_version))
self._model_attributes = ",".join(attributes) if attributes else None
def __init__(
self,
endpoint_name,
sagemaker_session=None,
serializer=IdentitySerializer(),
deserializer=BytesDeserializer(),
**kwargs,
):
"""Initialize a ``Predictor``.
Behavior for serialization of input data and deserialization of
result data can be configured through initializer arguments. If not
specified, a sequence of bytes is expected and the API sends it in the
request body without modifications. In response, the API returns the
sequence of bytes from the prediction result without any modifications.
Args:
endpoint_name (str): Name of the Amazon SageMaker endpoint to which
requests are sent.
sagemaker_session (sagemaker.session.Session): A SageMaker Session
object, used for SageMaker interactions (default: None). If not
specified, one is created using the default AWS configuration
chain.
serializer (:class:`~sagemaker.serializers.BaseSerializer`): A
serializer object, used to encode data for an inference endpoint
(default: :class:`~sagemaker.serializers.IdentitySerializer`).
deserializer (:class:`~sagemaker.deserializers.BaseDeserializer`): A
deserializer object, used to decode data from an inference
endpoint (default: :class:`~sagemaker.deserializers.BytesDeserializer`).
"""
removed_kwargs("content_type", kwargs)
removed_kwargs("accept", kwargs)
endpoint_name = renamed_kwargs("endpoint", "endpoint_name",
endpoint_name, kwargs)
self.endpoint_name = endpoint_name
self.sagemaker_session = sagemaker_session or Session()
self.serializer = serializer
self.deserializer = deserializer
self._endpoint_config_name = self._get_endpoint_config_name()
self._model_names = self._get_model_names()
self._context = None
def deploy(
self,
initial_instance_count,
instance_type,
serializer=None,
deserializer=None,
accelerator_type=None,
endpoint_name=None,
tags=None,
kms_key=None,
wait=True,
data_capture_config=None,
**kwargs,
):
"""Deploy this ``Model`` to an ``Endpoint`` and optionally return a ``Predictor``.
Create a SageMaker ``Model`` and ``EndpointConfig``, and deploy an
``Endpoint`` from this ``Model``. If self.model is not None, then the ``Endpoint``
will be deployed with parameters in self.model (like vpc_config,
enable_network_isolation, etc). If self.model is None, then use the parameters
in ``MultiDataModel`` constructor will be used. If ``self.predictor_cls`` is not
None, this method returns a the result of invoking ``self.predictor_cls`` on
the created endpoint name.
The name of the created model is accessible in the ``name`` field of
this ``Model`` after deploy returns
The name of the created endpoint is accessible in the
``endpoint_name`` field of this ``Model`` after deploy returns.
Args:
initial_instance_count (int): The initial number of instances to run
in the ``Endpoint`` created from this ``Model``.
instance_type (str): The EC2 instance type to deploy this Model to.
For example, 'ml.p2.xlarge', or 'local' for local mode.
serializer (:class:`~sagemaker.serializers.BaseSerializer`): A
serializer object, used to encode data for an inference endpoint
(default: None). If ``serializer`` is not None, then
``serializer`` will override the default serializer. The
default serializer is set by the ``predictor_cls``.
deserializer (:class:`~sagemaker.deserializers.BaseDeserializer`): A
deserializer object, used to decode data from an inference
endpoint (default: None). If ``deserializer`` is not None, then
``deserializer`` will override the default deserializer. The
default deserializer is set by the ``predictor_cls``.
accelerator_type (str): Type of Elastic Inference accelerator to
deploy this model for model loading and inference, for example,
'ml.eia1.medium'. If not specified, no Elastic Inference
accelerator will be attached to the endpoint. For more
information:
https://docs.aws.amazon.com/sagemaker/latest/dg/ei.html
endpoint_name (str): The name of the endpoint to create (default:
None). If not specified, a unique endpoint name will be created.
tags (List[dict[str, str]]): The list of tags to attach to this
specific endpoint.
kms_key (str): The ARN of the KMS key that is used to encrypt the
data on the storage volume attached to the instance hosting the
endpoint.
wait (bool): Whether the call should wait until the deployment of
this model completes (default: True).
data_capture_config (sagemaker.model_monitor.DataCaptureConfig): Specifies
configuration related to Endpoint data capture for use with
Amazon SageMaker Model Monitoring. Default: None.
Returns:
callable[string, sagemaker.session.Session] or None: Invocation of
``self.predictor_cls`` on the created endpoint name,
if ``self.predictor_cls``
is not None. Otherwise, return None.
"""
removed_kwargs("update_endpoint", kwargs)
# Set model specific parameters
if self.model:
enable_network_isolation = self.model.enable_network_isolation()
role = self.model.role
vpc_config = self.model.vpc_config
predictor_cls = self.model.predictor_cls
else:
enable_network_isolation = self.enable_network_isolation()
role = self.role
vpc_config = self.vpc_config
predictor_cls = self.predictor_cls
if role is None:
raise ValueError("Role can not be null for deploying a model")
if instance_type == "local" and not isinstance(self.sagemaker_session,
local.LocalSession):
self.sagemaker_session = local.LocalSession()
container_def = self.prepare_container_def(
instance_type, accelerator_type=accelerator_type)
self.sagemaker_session.create_model(
self.name,
role,
container_def,
vpc_config=vpc_config,
enable_network_isolation=enable_network_isolation,
tags=tags,
)
production_variant = sagemaker.production_variant(
self.name,
instance_type,
initial_instance_count,
accelerator_type=accelerator_type)
if endpoint_name:
self.endpoint_name = endpoint_name
else:
self.endpoint_name = self.name
data_capture_config_dict = None
if data_capture_config is not None:
data_capture_config_dict = data_capture_config._to_request_dict()
self.sagemaker_session.endpoint_from_production_variants(
name=self.endpoint_name,
production_variants=[production_variant],
tags=tags,
kms_key=kms_key,
wait=wait,
data_capture_config_dict=data_capture_config_dict,
)
if predictor_cls:
predictor = predictor_cls(self.endpoint_name,
self.sagemaker_session)
if serializer:
predictor.serializer = serializer
if deserializer:
predictor.deserializer = deserializer
return predictor
return None
def deploy(
self,
initial_instance_count,
instance_type,
serializer=None,
deserializer=None,
accelerator_type=None,
endpoint_name=None,
tags=None,
kms_key=None,
wait=True,
data_capture_config=None,
**kwargs,
):
"""Deploy this ``Model`` to an ``Endpoint`` and optionally return a
``Predictor``.
Create a SageMaker ``Model`` and ``EndpointConfig``, and deploy an
``Endpoint`` from this ``Model``. If ``self.predictor_cls`` is not None,
this method returns a the result of invoking ``self.predictor_cls`` on
the created endpoint name.
The name of the created model is accessible in the ``name`` field of
this ``Model`` after deploy returns
The name of the created endpoint is accessible in the
``endpoint_name`` field of this ``Model`` after deploy returns.
Args:
initial_instance_count (int): The initial number of instances to run
in the ``Endpoint`` created from this ``Model``.
instance_type (str): The EC2 instance type to deploy this Model to.
For example, 'ml.p2.xlarge', or 'local' for local mode.
serializer (:class:`~sagemaker.serializers.BaseSerializer`): A
serializer object, used to encode data for an inference endpoint
(default: None). If ``serializer`` is not None, then
``serializer`` will override the default serializer. The
default serializer is set by the ``predictor_cls``.
deserializer (:class:`~sagemaker.deserializers.BaseDeserializer`): A
deserializer object, used to decode data from an inference
endpoint (default: None). If ``deserializer`` is not None, then
``deserializer`` will override the default deserializer. The
default deserializer is set by the ``predictor_cls``.
accelerator_type (str): Type of Elastic Inference accelerator to
deploy this model for model loading and inference, for example,
'ml.eia1.medium'. If not specified, no Elastic Inference
accelerator will be attached to the endpoint. For more
information:
https://docs.aws.amazon.com/sagemaker/latest/dg/ei.html
endpoint_name (str): The name of the endpoint to create (default:
None). If not specified, a unique endpoint name will be created.
tags (List[dict[str, str]]): The list of tags to attach to this
specific endpoint.
kms_key (str): The ARN of the KMS key that is used to encrypt the
data on the storage volume attached to the instance hosting the
endpoint.
wait (bool): Whether the call should wait until the deployment of
this model completes (default: True).
data_capture_config (sagemaker.model_monitor.DataCaptureConfig): Specifies
configuration related to Endpoint data capture for use with
Amazon SageMaker Model Monitoring. Default: None.
Returns:
callable[string, sagemaker.session.Session] or None: Invocation of
``self.predictor_cls`` on the created endpoint name, if ``self.predictor_cls``
is not None. Otherwise, return None.
"""
removed_kwargs("update_endpoint", kwargs)
self._init_sagemaker_session_if_does_not_exist(instance_type)
if self.role is None:
raise ValueError("Role can not be null for deploying a model")
if instance_type.startswith("ml.inf") and not self._is_compiled_model:
LOGGER.warning(
"Your model is not compiled. Please compile your model before using Inferentia."
)
compiled_model_suffix = "-".join(instance_type.split(".")[:-1])
if self._is_compiled_model:
self._ensure_base_name_if_needed(self.image_uri)
if self._base_name is not None:
self._base_name = "-".join(
(self._base_name, compiled_model_suffix))
self._create_sagemaker_model(instance_type, accelerator_type, tags)
production_variant = sagemaker.production_variant(
self.name,
instance_type,
initial_instance_count,
accelerator_type=accelerator_type)
if endpoint_name:
self.endpoint_name = endpoint_name
else:
base_endpoint_name = self._base_name or utils.base_from_name(
self.name)
if self._is_compiled_model and not base_endpoint_name.endswith(
compiled_model_suffix):
base_endpoint_name = "-".join(
(base_endpoint_name, compiled_model_suffix))
self.endpoint_name = utils.name_from_base(base_endpoint_name)
data_capture_config_dict = None
if data_capture_config is not None:
data_capture_config_dict = data_capture_config._to_request_dict()
self.sagemaker_session.endpoint_from_production_variants(
name=self.endpoint_name,
production_variants=[production_variant],
tags=tags,
kms_key=kms_key,
wait=wait,
data_capture_config_dict=data_capture_config_dict,
)
if self.predictor_cls:
predictor = self.predictor_cls(self.endpoint_name,
self.sagemaker_session)
if serializer:
predictor.serializer = serializer
if deserializer:
predictor.deserializer = deserializer
return predictor
return None
