def __init__(
self,
model_data,
image,
role=None,
predictor_cls=None,
env=None,
name=None,
vpc_config=None,
sagemaker_session=None,
enable_network_isolation=False,
model_kms_key=None,
):
"""Initialize an SageMaker ``Model``.
Args:
model_data (str): The S3 location of a SageMaker model data
``.tar.gz`` file.
image (str): A Docker image URI.
role (str): An AWS IAM role (either name or full ARN). The Amazon
SageMaker training jobs and APIs that create Amazon SageMaker
endpoints use this role to access training data and model
artifacts. After the endpoint is created, the inference code
might use the IAM role if it needs to access some AWS resources.
It can be null if this is being used to create a Model to pass
to a ``PipelineModel`` which has its own Role field. (default:
None)
predictor_cls (callable[string, sagemaker.session.Session]): A
function to call to create a predictor (default: None). If not
None, ``deploy`` will return the result of invoking this
function on the created endpoint name.
env (dict[str, str]): Environment variables to run with ``image``
when hosted in SageMaker (default: None).
name (str): The model name. If None, a default model name will be
selected on each ``deploy``.
vpc_config (dict[str, list[str]]): The VpcConfig set on the model
(default: None)
* 'Subnets' (list[str]): List of subnet ids.
* 'SecurityGroupIds' (list[str]): List of security group ids.
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.
enable_network_isolation (Boolean): Default False. if True, enables
network isolation in the endpoint, isolating the model
container. No inbound or outbound network calls can be made to
or from the model container.
model_kms_key (str): KMS key ARN used to encrypt the repacked
model archive file if the model is repacked
"""
LOGGER.warning(
fw_utils.parameter_v2_rename_warning("image", "image_uri"))
self.model_data = model_data
self.image = image
self.role = role
self.predictor_cls = predictor_cls
self.env = env or {}
self.name = name
self.vpc_config = vpc_config
self.sagemaker_session = sagemaker_session
self._model_name = None
self.endpoint_name = None
self._is_compiled_model = False
self._enable_network_isolation = enable_network_isolation
self.model_kms_key = model_kms_key
def __init__(self,
training_steps=None,
evaluation_steps=None,
checkpoint_path=None,
py_version=None,
framework_version=None,
model_dir=None,
requirements_file="",
image_name=None,
script_mode=False,
distributions=None,
**kwargs):
"""Initialize a ``TensorFlow`` estimator.
Args:
training_steps (int): Perform this many steps of training. `None`, the default means
train forever.
evaluation_steps (int): Perform this many steps of evaluation. `None`, the default
means that evaluation runs until input from eval_input_fn is exhausted (or another
exception is raised).
checkpoint_path (str): Identifies S3 location where checkpoint data during model
training can be saved (default: None). For distributed model training, this
parameter is required.
py_version (str): Python version you want to use for executing your model training
code (default: 'py2').
framework_version (str): TensorFlow version you want to use for executing your model
training code. If not specified, this will default to 1.11.
model_dir (str): S3 location where the checkpoint data and models can be exported to
during training (default: None). It will be passed in the training script as one of
the command line arguments. If not specified, one is provided based on
your training configuration:
* *distributed training with MPI* - ``/opt/ml/model``
* *single-machine training or distributed training without MPI* - \
``s3://{output_path}/model``
* *Local Mode with local sources (file:// instead of s3://)* - \
``/opt/ml/shared/model``
requirements_file (str): Path to a ``requirements.txt`` file (default: ''). The path
should be within and relative to ``source_dir``. Details on the format can be
found in the Pip User Guide:
<https://pip.pypa.io/en/stable/reference/pip_install/#requirements-file-format>
image_name (str): If specified, the estimator will use this image for training and
hosting, instead of selecting the appropriate SageMaker official image based on
framework_version and py_version. It can be an ECR url or dockerhub image and tag.
Examples:
123.dkr.ecr.us-west-2.amazonaws.com/my-custom-image:1.0
custom-image:latest.
script_mode (bool): If set to True will the estimator will use the Script Mode
containers (default: False). This will be ignored if py_version is set to 'py3'.
distributions (dict): A dictionary with information on how to run distributed training
(default: None). Currently we support distributed training with parameter servers
and MPI.
To enable parameter server use the following setup:
.. code:: python
{
'parameter_server':
{
'enabled': True
}
}
To enable MPI:
.. code:: python
{
'mpi':
{
'enabled': True
}
}
**kwargs: Additional kwargs passed to the Framework constructor.
.. tip::
You can find additional parameters for initializing this class at
:class:`~sagemaker.estimator.Framework` and
:class:`~sagemaker.estimator.EstimatorBase`.
"""
if framework_version is None:
logger.warning(
fw.empty_framework_version_warning(defaults.TF_VERSION,
self.LATEST_VERSION))
self.framework_version = framework_version or defaults.TF_VERSION
if not py_version:
py_version = "py3" if self._only_python_3_supported() else "py2"
if py_version == "py2":
logger.warning(
fw.python_deprecation_warning(self.__framework_name__,
defaults.LATEST_PY2_VERSION))
if distributions is not None:
logger.warning(
fw.parameter_v2_rename_warning("distribution", distributions))
train_instance_type = kwargs.get("train_instance_type")
fw.warn_if_parameter_server_with_multi_gpu(
training_instance_type=train_instance_type,
distributions=distributions)
if "enable_sagemaker_metrics" not in kwargs:
# enable sagemaker metrics for TF v1.15 or greater:
if fw.is_version_equal_or_higher([1, 15], self.framework_version):
kwargs["enable_sagemaker_metrics"] = True
super(TensorFlow, self).__init__(image_name=image_name, **kwargs)
self.checkpoint_path = checkpoint_path
self.py_version = py_version
self.training_steps = training_steps
self.evaluation_steps = evaluation_steps
self.model_dir = model_dir
self.script_mode = script_mode
self.distributions = distributions or {}
self._validate_args(
py_version=py_version,
script_mode=script_mode,
framework_version=self.framework_version,
training_steps=training_steps,
evaluation_steps=evaluation_steps,
requirements_file=requirements_file,
checkpoint_path=checkpoint_path,
)
self._validate_requirements_file(requirements_file)
self.requirements_file = requirements_file
def __init__(self,
entry_point,
source_dir=None,
hyperparameters=None,
py_version="py2",
framework_version=None,
image_name=None,
distributions=None,
**kwargs):
"""This ``Estimator`` executes an MXNet script in a managed MXNet
execution environment, within a SageMaker Training Job. The managed
MXNet environment is an Amazon-built Docker container that executes
functions defined in the supplied ``entry_point`` Python script.
Training is started by calling
:meth:`~sagemaker.amazon.estimator.Framework.fit` on this Estimator.
After training is complete, calling
:meth:`~sagemaker.amazon.estimator.Framework.deploy` creates a hosted
SageMaker endpoint and returns an
:class:`~sagemaker.amazon.mxnet.model.MXNetPredictor` instance that can
be used to perform inference against the hosted model.
Technical documentation on preparing MXNet scripts for SageMaker
training and using the MXNet Estimator is available on the project
home-page: https://github.com/aws/sagemaker-python-sdk
Args:
entry_point (str): Path (absolute or relative) to the Python source
file which should be executed as the entry point to training.
If ``source_dir`` is specified, then ``entry_point``
must point to a file located at the root of ``source_dir``.
source_dir (str): Path (absolute, relative or an S3 URI) to a directory
with any other training source code dependencies aside from the entry
point file (default: None). If ``source_dir`` is an S3 URI, it must
point to a tar.gz file. Structure within this directory are preserved
when training on Amazon SageMaker.
hyperparameters (dict): Hyperparameters that will be used for
training (default: None). The hyperparameters are made
accessible as a dict[str, str] to the training code on
SageMaker. For convenience, this accepts other types for keys
and values, but ``str()`` will be called to convert them before
training.
py_version (str): Python version you want to use for executing your
model training code (default: 'py2'). One of 'py2' or 'py3'.
framework_version (str): MXNet version you want to use for executing
your model training code. List of supported versions
https://github.com/aws/sagemaker-python-sdk#mxnet-sagemaker-estimators.
If not specified, this will default to 1.2.1.
image_name (str): If specified, the estimator will use this image for training and
hosting, instead of selecting the appropriate SageMaker official image based on
framework_version and py_version. It can be an ECR url or dockerhub image and tag.
Examples:
* ``123412341234.dkr.ecr.us-west-2.amazonaws.com/my-custom-image:1.0``
* ``custom-image:latest``
distributions (dict): A dictionary with information on how to run distributed
training (default: None). To have parameter servers launched for training,
set this value to be ``{'parameter_server': {'enabled': True}}``.
**kwargs: Additional kwargs passed to the
:class:`~sagemaker.estimator.Framework` constructor.
.. tip::
You can find additional parameters for initializing this class at
:class:`~sagemaker.estimator.Framework` and
:class:`~sagemaker.estimator.EstimatorBase`.
"""
if framework_version is None:
logger.warning(
empty_framework_version_warning(defaults.MXNET_VERSION,
self.LATEST_VERSION))
self.framework_version = framework_version or defaults.MXNET_VERSION
if "enable_sagemaker_metrics" not in kwargs:
# enable sagemaker metrics for MXNet v1.6 or greater:
if is_version_equal_or_higher([1, 6], self.framework_version):
kwargs["enable_sagemaker_metrics"] = True
super(MXNet, self).__init__(entry_point,
source_dir,
hyperparameters,
image_name=image_name,
**kwargs)
if py_version == "py2":
logger.warning(
python_deprecation_warning(self.__framework_name__,
defaults.LATEST_PY2_VERSION))
if distributions is not None:
logger.warning(
parameter_v2_rename_warning("distributions", "distribution"))
train_instance_type = kwargs.get("train_instance_type")
warn_if_parameter_server_with_multi_gpu(
training_instance_type=train_instance_type,
distributions=distributions)
self.py_version = py_version
self._configure_distribution(distributions)
