def prepare_container_def(self, instance_type):
"""Return a container definition with framework configuration set in model environment variables.
This also uploads user-supplied code to S3.
Args:
instance_type (str): The EC2 instance type to deploy this Model to. For example, 'ml.p2.xlarge'.
Returns:
dict[str, str]: A container definition object usable with the CreateModel API.
"""
deploy_image = self.image
if not deploy_image:
region_name = self.sagemaker_session.boto_region_name
deploy_image = create_image_uri(region_name, self.__framework_name__, instance_type,
self.framework_version, self.py_version)
deploy_key_prefix = self.key_prefix or self.name or name_from_image(deploy_image)
self._upload_code(deploy_key_prefix)
deploy_env = dict(self.env)
deploy_env.update(self._framework_env_vars())
if self.model_server_workers:
deploy_env[MODEL_SERVER_WORKERS_PARAM_NAME.upper()] = str(self.model_server_workers)
return sagemaker.container_def(deploy_image, self.model_data, deploy_env)
def prepare_container_def(self, instance_type, accelerator_type=None):
"""Return a container definition with framework configuration set in model environment
variables.
Args:
instance_type (str): The EC2 instance type to deploy this Model to. For example,
'ml.m5.xlarge'.
accelerator_type (str): The Elastic Inference accelerator type to deploy to the
instance for loading and making inferences to the model. For example,
'ml.eia1.medium'.
Note: accelerator types are not supported by XGBoostModel.
Returns:
dict[str, str]: A container definition object usable with the CreateModel API.
"""
deploy_image = self.image
if not deploy_image:
image_tag = "{}-{}-{}".format(self.framework_version, "cpu",
self.py_version)
deploy_image = default_framework_uri(
self.__framework_name__,
self.sagemaker_session.boto_region_name, image_tag)
deploy_key_prefix = model_code_key_prefix(self.key_prefix, self.name,
deploy_image)
self._upload_code(deploy_key_prefix)
deploy_env = dict(self.env)
deploy_env.update(self._framework_env_vars())
if self.model_server_workers:
deploy_env[MODEL_SERVER_WORKERS_PARAM_NAME.upper()] = str(
self.model_server_workers)
return sagemaker.container_def(deploy_image, self.model_data,
deploy_env)
def prepare_container_def(self, instance_type=None, accelerator_type=None):
"""Return a container definition with framework configuration.
The framework configuration is set in model environment variables.
Args:
instance_type (str): The EC2 instance type to deploy this Model to.
accelerator_type (str): The Elastic Inference accelerator type to deploy to the
instance for loading and making inferences to the model. This parameter is
unused because accelerator types are not supported by XGBoostModel.
Returns:
dict[str, str]: A container definition object usable with the CreateModel API.
"""
deploy_image = self.image_uri
if not deploy_image:
deploy_image = self.serving_image_uri(
self.sagemaker_session.boto_region_name, instance_type)
deploy_key_prefix = model_code_key_prefix(self.key_prefix, self.name,
deploy_image)
self._upload_code(key_prefix=deploy_key_prefix,
repack=self.enable_network_isolation())
deploy_env = dict(self.env)
deploy_env.update(self._script_mode_env_vars())
if self.model_server_workers:
deploy_env[MODEL_SERVER_WORKERS_PARAM_NAME.upper()] = str(
self.model_server_workers)
model_data = (self.repacked_model_data
if self.enable_network_isolation() else self.model_data)
return sagemaker.container_def(deploy_image, model_data, deploy_env)
def prepare_container_def(self, instance_type, accelerator_type=None):
"""Return a container definition with framework configuration set in
model environment variables.
This also uploads user-supplied code to S3.
Args:
instance_type (str): The EC2 instance type to deploy this Model to.
For example, 'ml.p2.xlarge'.
accelerator_type (str): The Elastic Inference accelerator type to
deploy to the instance for loading and making inferences to the
model. For example, 'ml.eia1.medium'.
Returns:
dict[str, str]: A container definition object usable with the
CreateModel API.
"""
deploy_image = self.image
if not deploy_image:
region_name = self.sagemaker_session.boto_region_name
deploy_image = self.serving_image_uri(
region_name, instance_type, accelerator_type=accelerator_type)
deploy_key_prefix = model_code_key_prefix(self.key_prefix, self.name,
deploy_image)
self._upload_code(deploy_key_prefix)
deploy_env = dict(self.env)
deploy_env.update(self._framework_env_vars())
if self.model_server_workers:
deploy_env[MODEL_SERVER_WORKERS_PARAM_NAME.upper()] = str(
self.model_server_workers)
return sagemaker.container_def(deploy_image, self.model_data,
deploy_env)
def test_tf_deploy_model_server_workers_unset(sagemaker_session):
tf = _build_tf(sagemaker_session)
tf.fit(inputs=s3_input('s3://mybucket/train'))
tf.deploy(initial_instance_count=1, instance_type='ml.c2.2xlarge')
assert MODEL_SERVER_WORKERS_PARAM_NAME.upper() not in sagemaker_session.method_calls[3][1][2]['Environment']
def prepare_container_def(self, instance_type):
"""Return a container definition with framework configuration set in model environment variables.
This also uploads user-supplied code to S3.
Args:
instance_type (str): The EC2 instance type to deploy this Model to. For example, 'ml.p2.xlarge'.
Returns:
dict[str, str]: A container definition object usable with the CreateModel API.
"""
deploy_image = self.image
if not deploy_image:
region_name = self.sagemaker_session.boto_region_name
deploy_image = create_image_uri(region_name, self.__framework_name__, instance_type,
self.framework_version, self.py_version)
deploy_key_prefix = model_code_key_prefix(self.key_prefix, self.name, deploy_image)
self._upload_code(deploy_key_prefix)
deploy_env = dict(self.env)
deploy_env.update(self._framework_env_vars())
if self.model_server_workers:
deploy_env[MODEL_SERVER_WORKERS_PARAM_NAME.upper()] = str(self.model_server_workers)
return sagemaker.container_def(deploy_image, self.model_data, deploy_env)
def test_tf_deploy_model_server_workers_unset(sagemaker_session):
tf = _build_tf(sagemaker_session)
tf.fit(inputs=s3_input('s3://mybucket/train'))
tf.deploy(initial_instance_count=1, instance_type='ml.c2.2xlarge')
assert MODEL_SERVER_WORKERS_PARAM_NAME.upper() not in sagemaker_session.method_calls[3][1][2]['Environment']
def prepare_container_def(self, instance_type, accelerator_type=None):
"""Return a container definition with framework configuration set in model environment variables.
Args:
instance_type (str): The EC2 instance type to deploy this Model to. For example, 'ml.p2.xlarge'.
accelerator_type (str): The Elastic Inference accelerator type to deploy to the instance for loading and
making inferences to the model. For example, 'ml.eia1.medium'.
Returns:
dict[str, str]: A container definition object usable with the CreateModel API.
"""
mms_version = parse_version(self.framework_version) >= parse_version(self._LOWEST_MMS_VERSION)
deploy_image = self.image
if not deploy_image:
region_name = self.sagemaker_session.boto_session.region_name
framework_name = self.__framework_name__
if mms_version:
framework_name += '-serving'
deploy_image = create_image_uri(region_name, framework_name, instance_type,
self.framework_version, self.py_version, accelerator_type=accelerator_type)
deploy_key_prefix = model_code_key_prefix(self.key_prefix, self.name, deploy_image)
self._upload_code(deploy_key_prefix, mms_version)
deploy_env = dict(self.env)
deploy_env.update(self._framework_env_vars())
if self.model_server_workers:
deploy_env[MODEL_SERVER_WORKERS_PARAM_NAME.upper()] = str(self.model_server_workers)
return sagemaker.container_def(deploy_image, self.repacked_model_data or self.model_data, deploy_env)
def prepare_container_def(
self, instance_type, accelerator_type=None
) -> Dict[str, str]:
"""
Return a container definition with framework configuration set in
model environment variables.
Parameters
----------
instance_type:
The EC2 instance type to deploy this Model to.
Example::
'ml.c5.xlarge' # CPU,
'ml.p2.xlarge' # GPU.
accelerator_type:
The Elastic Inference accelerator type to
deploy to the instance for loading and making inferences to the model.
Example::
"ml.eia1.medium"
Returns
--------
Dict[str, str]:
A container definition object usable with the CreateModel API.
"""
is_mms_version = parse_version(
self.framework_version
) >= parse_version(self._LOWEST_MMS_VERSION)
deploy_image = self.image
# TODO implement proper logic handling images when none are provided by user
# Example implementation:
# https://github.com/aws/sagemaker-python-sdk/blob/master/src/sagemaker/mxnet/model.py
logger.info(f"Using image: {deploy_image}")
deploy_key_prefix = model_code_key_prefix(
self.key_prefix, self.name, deploy_image
)
self._upload_code(deploy_key_prefix, is_mms_version)
deploy_env = dict(self.env)
deploy_env.update(self._framework_env_vars())
if self.model_server_workers:
deploy_env[MODEL_SERVER_WORKERS_PARAM_NAME.upper()] = str(
self.model_server_workers
)
return sagemaker.container_def(
deploy_image,
self.repacked_model_data or self.model_data,
deploy_env,
)
def test_tf_deploy_model_server_workers(sagemaker_session):
tf = _build_tf(sagemaker_session)
tf.fit(inputs=s3_input("s3://mybucket/train"))
tf.deploy(initial_instance_count=1,
instance_type="ml.c2.2xlarge",
model_server_workers=2)
assert ("2" == sagemaker_session.method_calls[3][1][2]["Environment"][
MODEL_SERVER_WORKERS_PARAM_NAME.upper()])
def prepare_container_def(self,
instance_type=None,
accelerator_type=None,
serverless_inference_config=None):
"""A container definition with framework configuration set in model environment variables.
Args:
instance_type (str): The EC2 instance type to deploy this Model to.
For example, 'ml.p2.xlarge'.
accelerator_type (str): The Elastic Inference accelerator type to
deploy to the instance for loading and making inferences to the
model.
serverless_inference_config (sagemaker.serverless.ServerlessInferenceConfig):
Specifies configuration related to serverless endpoint. Instance type is
not provided in serverless inference. So this is used to find image URIs.
Returns:
dict[str, str]: A container definition object usable with the
CreateModel API.
"""
deploy_image = self.image_uri
if not deploy_image:
if instance_type is None and serverless_inference_config is None:
raise ValueError(
"Must supply either an instance type (for choosing CPU vs GPU) or an image URI."
)
region_name = self.sagemaker_session.boto_session.region_name
deploy_image = self.serving_image_uri(
region_name,
instance_type,
accelerator_type=accelerator_type,
serverless_inference_config=serverless_inference_config,
)
deploy_key_prefix = model_code_key_prefix(self.key_prefix, self.name,
deploy_image)
self._upload_code(deploy_key_prefix, repack=True)
deploy_env = dict(self.env)
deploy_env.update(self._script_mode_env_vars())
if self.model_server_workers:
deploy_env[MODEL_SERVER_WORKERS_PARAM_NAME.upper()] = str(
self.model_server_workers)
return sagemaker.container_def(
deploy_image, self.repacked_model_data or self.model_data,
deploy_env)
def prepare_container_def(
self, instance_type=None, accelerator_type=None, serverless_inference_config=None
):
"""Container definition with framework configuration set in model environment variables.
Args:
instance_type (str): The EC2 instance type to deploy this Model to.
This parameter is unused because Scikit-learn supports only CPU.
accelerator_type (str): The Elastic Inference accelerator type to
deploy to the instance for loading and making inferences to the
model. This parameter is unused because accelerator types
are not supported by SKLearnModel.
serverless_inference_config (sagemaker.serverless.ServerlessInferenceConfig):
Specifies configuration related to serverless endpoint. Instance type is
not provided in serverless inference. So this is used to find image URIs.
Returns:
dict[str, str]: A container definition object usable with the
CreateModel API.
"""
if accelerator_type:
raise ValueError("Accelerator types are not supported for Scikit-Learn.")
deploy_image = self.image_uri
if not deploy_image:
deploy_image = self.serving_image_uri(
self.sagemaker_session.boto_region_name, instance_type
)
deploy_key_prefix = model_code_key_prefix(self.key_prefix, self.name, deploy_image)
self._upload_code(key_prefix=deploy_key_prefix, repack=self.enable_network_isolation())
deploy_env = dict(self.env)
deploy_env.update(self._script_mode_env_vars())
if self.model_server_workers:
deploy_env[MODEL_SERVER_WORKERS_PARAM_NAME.upper()] = str(self.model_server_workers)
model_data_uri = (
self.repacked_model_data if self.enable_network_isolation() else self.model_data
)
return sagemaker.container_def(deploy_image, model_data_uri, deploy_env)
def prepare_container_def(self, instance_type=None, accelerator_type=None):
"""Return a container definition with framework configuration.
Framework configuration is set in model environment variables.
Args:
instance_type (str): The EC2 instance type to deploy this Model to.
For example, 'ml.p2.xlarge'.
accelerator_type (str): The Elastic Inference accelerator type to
deploy to the instance for loading and making inferences to the
model. For example, 'ml.eia1.medium'.
Returns:
dict[str, str]: A container definition object usable with the
CreateModel API.
"""
deploy_image = self.image_uri
if not deploy_image:
if instance_type is None:
raise ValueError(
"Must supply either an instance type (for choosing CPU vs GPU) or an image URI."
)
region_name = self.sagemaker_session.boto_session.region_name
deploy_image = self.serving_image_uri(
region_name, instance_type, accelerator_type=accelerator_type)
deploy_key_prefix = model_code_key_prefix(self.key_prefix, self.name,
deploy_image)
self._upload_code(deploy_key_prefix, self._is_mms_version())
deploy_env = dict(self.env)
deploy_env.update(self._framework_env_vars())
if self.model_server_workers:
deploy_env[MODEL_SERVER_WORKERS_PARAM_NAME.upper()] = str(
self.model_server_workers)
return sagemaker.container_def(
deploy_image, self.repacked_model_data or self.model_data,
deploy_env)