def __init__(
self,
name: str,
sagemaker_session,
role,
model_data: str,
entry_point: str,
source_dir: str = None,
dependencies: List = None,
depends_on: List[str] = None,
**kwargs,
):
"""Constructs a TrainingStep, given an `EstimatorBase` instance.
In addition to the estimator instance, the other arguments are those that are supplied to
the `fit` method of the `sagemaker.estimator.Estimator`.
Args:
name (str): The name of the training step.
estimator (EstimatorBase): A `sagemaker.estimator.EstimatorBase` instance.
inputs (TrainingInput): A `sagemaker.inputs.TrainingInput` instance. Defaults to `None`.
"""
# yeah, go ahead and save the originals for now
self._model_data = model_data
self.sagemaker_session = sagemaker_session
self.role = role
if isinstance(model_data, Properties):
self._model_prefix = model_data
self._model_archive = "model.tar.gz"
else:
self._model_prefix = "/".join(self._model_data.split("/")[:-1])
self._model_archive = self._model_data.split("/")[-1]
self._entry_point = entry_point
self._entry_point_basename = os.path.basename(self._entry_point)
self._source_dir = source_dir
self._dependencies = dependencies
# the real estimator and inputs
repacker = SKLearn(
framework_version=FRAMEWORK_VERSION,
instance_type=INSTANCE_TYPE,
entry_point=REPACK_SCRIPT,
source_dir=self._source_dir,
dependencies=self._dependencies,
sagemaker_session=self.sagemaker_session,
role=self.role,
hyperparameters={
"inference_script": self._entry_point_basename,
"model_archive": self._model_archive,
},
**kwargs,
)
repacker.disable_profiler = True
inputs = TrainingInput(self._model_prefix)
# super!
super(_RepackModelStep, self).__init__(name=name,
depends_on=depends_on,
estimator=repacker,
inputs=inputs)
def __init__(
self,
name: str,
sagemaker_session,
role,
model_data: str,
entry_point: str,
display_name: str = None,
description: str = None,
source_dir: str = None,
dependencies: List = None,
depends_on: Optional[List[Union[str, Step, "StepCollection"]]] = None,
retry_policies: List[RetryPolicy] = None,
subnets=None,
security_group_ids=None,
**kwargs,
):
"""Base class initializer.
Args:
name (str): The name of the training step.
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.
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 an AWS resource.
model_data (str): The S3 location of a SageMaker model data `.tar.gz` file.
entry_point (str): Path (absolute or relative) to the local Python
source file which should be executed as the entry point to
inference. If ``source_dir`` is specified, then ``entry_point``
must point to a file located at the root of ``source_dir``.
If 'git_config' is provided, 'entry_point' should be
a relative location to the Python source file in the Git repo.
Example:
With the following GitHub repo directory structure:
>>> |----- README.md
>>> |----- src
>>> |----- train.py
>>> |----- test.py
You can assign entry_point='src/train.py'.
display_name (str): The display name of this `_RepackModelStep` step (default: None).
description (str): The description of this `_RepackModelStep` (default: None).
source_dir (str): A relative location to a directory with other training
or model hosting source code dependencies aside from the entry point
file in the Git repo (default: None). Structure within this
directory are preserved when training on Amazon SageMaker.
dependencies (list[str]): A list of paths to directories (absolute
or relative) with any additional libraries that will be exported
to the container (default: []). The library folders will be
copied to SageMaker in the same folder where the entrypoint is
copied. If 'git_config' is provided, 'dependencies' should be a
list of relative locations to directories with any additional
libraries needed in the Git repo.
.. admonition:: Example
The following call
>>> Estimator(entry_point='train.py',
... dependencies=['my/libs/common', 'virtual-env'])
results in the following inside the container:
>>> $ ls
>>> opt/ml/code
>>> |------ train.py
>>> |------ common
>>> |------ virtual-env
This is not supported with "local code" in Local Mode.
depends_on (List[Union[str, Step, StepCollection]]): The list of `Step`/`StepCollection`
names or `Step` instances or `StepCollection` instances that the current `Step`
depends on (default: None).
retry_policies (List[RetryPolicy]): The list of retry policies for the current step
(default: None).
subnets (list[str]): List of subnet ids. If not specified, the re-packing
job will be created without VPC config (default: None).
security_group_ids (list[str]): List of security group ids. If not
specified, the re-packing job will be created without VPC config (default: None).
**kwargs: additional arguments for the repacking job.
"""
self._model_data = model_data
self.sagemaker_session = sagemaker_session
self.role = role
self._entry_point = entry_point
self._entry_point_basename = os.path.basename(self._entry_point)
self._source_dir = source_dir
self._dependencies = dependencies
# convert dependencies array into space-delimited string
dependencies_hyperparameter = None
if self._dependencies:
dependencies_hyperparameter = " ".join(self._dependencies)
# the real estimator and inputs
repacker = SKLearn(
framework_version=FRAMEWORK_VERSION,
instance_type=INSTANCE_TYPE,
entry_point=REPACK_SCRIPT,
source_dir=self._source_dir,
dependencies=self._dependencies,
sagemaker_session=self.sagemaker_session,
role=self.role,
hyperparameters={
"inference_script": self._entry_point_basename,
"model_archive": self._model_data,
"dependencies": dependencies_hyperparameter,
"source_dir": self._source_dir,
},
subnets=subnets,
security_group_ids=security_group_ids,
**kwargs,
)
repacker.disable_profiler = True
inputs = TrainingInput(self._model_data)
# super!
super(_RepackModelStep, self).__init__(
name=name,
display_name=display_name,
description=description,
depends_on=depends_on,
retry_policies=retry_policies,
estimator=repacker,
inputs=inputs,
)