def create_parser():
parser = argparse.ArgumentParser(description='SageMaker Batch Transformation Job')
_utils.add_default_client_arguments(parser)
parser.add_argument('--job_name', type=str, required=False, help='The name of the transform job.', default='')
parser.add_argument('--model_name', type=str, required=True, help='The name of the model that you want to use for the transform job.')
parser.add_argument('--max_concurrent', type=int, required=False, help='The maximum number of parallel requests that can be sent to each instance in a transform job.', default='0')
parser.add_argument('--max_payload', type=int, required=False, help='The maximum allowed size of the payload, in MB.', default='6')
parser.add_argument('--batch_strategy', choices=['MultiRecord', 'SingleRecord', ''], type=str, required=False, help='The number of records to include in a mini-batch for an HTTP inference request.', default='')
parser.add_argument('--environment', type=_utils.yaml_or_json_str, required=False, help='The dictionary of the environment variables to set in the Docker container. Up to 16 key-value entries in the map.', default={})
parser.add_argument('--input_location', type=str, required=True, help='The S3 location of the data source that is associated with a channel.')
parser.add_argument('--data_type', choices=['ManifestFile', 'S3Prefix', 'AugmentedManifestFile', ''], type=str, required=False, help='Data type of the input. Can be ManifestFile, S3Prefix, or AugmentedManifestFile.', default='S3Prefix')
parser.add_argument('--content_type', type=str, required=False, help='The multipurpose internet mail extension (MIME) type of the data.', default='')
parser.add_argument('--split_type', choices=['None', 'Line', 'RecordIO', 'TFRecord', ''], type=str, required=False, help='The method to use to split the transform job data files into smaller batches.', default='None')
parser.add_argument('--compression_type', choices=['None', 'Gzip', ''], type=str, required=False, help='If the transform data is compressed, the specification of the compression type.', default='None')
parser.add_argument('--output_location', type=str, required=True, help='The Amazon S3 path where you want Amazon SageMaker to store the results of the transform job.')
parser.add_argument('--accept', type=str, required=False, help='The MIME type used to specify the output data.')
parser.add_argument('--assemble_with', choices=['None', 'Line', ''], type=str, required=False, help='Defines how to assemble the results of the transform job as a single S3 object. Either None or Line.')
parser.add_argument('--output_encryption_key', type=str, required=False, help='The AWS KMS key that Amazon SageMaker uses to encrypt the model artifacts.', default='')
parser.add_argument('--input_filter', type=str, required=False, help='A JSONPath expression used to select a portion of the input data to pass to the algorithm.', default='')
parser.add_argument('--output_filter', type=str, required=False, help='A JSONPath expression used to select a portion of the joined dataset to save in the output file for a batch transform job.', default='')
parser.add_argument('--join_source', choices=['None', 'Input', ''], type=str, required=False, help='Specifies the source of the data to join with the transformed data.', default='None')
parser.add_argument('--instance_type', type=str, required=False, help='The ML compute instance type for the transform job.', default='ml.m4.xlarge')
parser.add_argument('--instance_count', type=int, required=False, help='The number of ML compute instances to use in the transform job.')
parser.add_argument('--resource_encryption_key', type=str, required=False, help='The AWS KMS key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance(s).', default='')
parser.add_argument('--tags', type=_utils.yaml_or_json_str, required=False, help='An array of key-value pairs, to categorize AWS resources.', default={})
parser.add_argument('--output_location_file', type=str, required=True, help='File path where the program will write the Amazon S3 URI of the transform job results.')
return parser
def create_parser():
parser = argparse.ArgumentParser(description='SageMaker Training Job')
_utils.add_default_client_arguments(parser)
parser.add_argument('--job_name', type=str, required=False, help='The name of the training job.', default='')
parser.add_argument('--role', type=str, required=True, help='The Amazon Resource Name (ARN) that Amazon SageMaker assumes to perform tasks on your behalf.')
parser.add_argument('--image', type=str, required=False, help='The registry path of the Docker image that contains the training algorithm.', default='')
parser.add_argument('--algorithm_name', type=str, required=False, help='The name of the resource algorithm to use for the training job.', default='')
parser.add_argument('--metric_definitions', type=_utils.yaml_or_json_str, required=False, help='The dictionary of name-regex pairs specify the metrics that the algorithm emits.', default={})
parser.add_argument('--training_input_mode', choices=['File', 'Pipe'], type=str, help='The input mode that the algorithm supports. File or Pipe.', default='File')
parser.add_argument('--hyperparameters', type=_utils.yaml_or_json_str, help='Dictionary of hyperparameters for the the algorithm.', default={})
parser.add_argument('--channels', type=_utils.yaml_or_json_str, required=True, help='A list of dicts specifying the input channels. Must have at least one.')
parser.add_argument('--instance_type', required=True, choices=['ml.m4.xlarge', 'ml.m4.2xlarge', 'ml.m4.4xlarge', 'ml.m4.10xlarge', 'ml.m4.16xlarge', 'ml.m5.large', 'ml.m5.xlarge', 'ml.m5.2xlarge', 'ml.m5.4xlarge',
'ml.m5.12xlarge', 'ml.m5.24xlarge', 'ml.c4.xlarge', 'ml.c4.2xlarge', 'ml.c4.4xlarge', 'ml.c4.8xlarge', 'ml.p2.xlarge', 'ml.p2.8xlarge', 'ml.p2.16xlarge', 'ml.p3.2xlarge', 'ml.p3.8xlarge', 'ml.p3.16xlarge',
'ml.c5.xlarge', 'ml.c5.2xlarge', 'ml.c5.4xlarge', 'ml.c5.9xlarge', 'ml.c5.18xlarge'], type=str, help='The ML compute instance type.', default='ml.m4.xlarge')
parser.add_argument('--instance_count', required=True, type=int, help='The registry path of the Docker image that contains the training algorithm.', default=1)
parser.add_argument('--volume_size', type=int, required=True, help='The size of the ML storage volume that you want to provision.', default=1)
parser.add_argument('--resource_encryption_key', type=str, required=False, help='The AWS KMS key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance(s).', default='')
parser.add_argument('--max_run_time', type=int, required=True, help='The maximum run time in seconds for the training job.', default=86400)
parser.add_argument('--model_artifact_path', type=str, required=True, help='Identifies the S3 path where you want Amazon SageMaker to store the model artifacts.')
parser.add_argument('--output_encryption_key', type=str, required=False, help='The AWS KMS key that Amazon SageMaker uses to encrypt the model artifacts.', default='')
parser.add_argument('--vpc_security_group_ids', type=str, required=False, help='The VPC security group IDs, in the form sg-xxxxxxxx.')
parser.add_argument('--vpc_subnets', type=str, required=False, help='The ID of the subnets in the VPC to which you want to connect your hpo job.')
parser.add_argument('--network_isolation', type=_utils.str_to_bool, required=False, help='Isolates the training container.', default=True)
parser.add_argument('--traffic_encryption', type=_utils.str_to_bool, required=False, help='Encrypts all communications between ML compute instances in distributed training.', default=False)
### Start spot instance support
parser.add_argument('--spot_instance', type=_utils.str_to_bool, required=False, help='Use managed spot training.', default=False)
parser.add_argument('--max_wait_time', type=int, required=False, help='The maximum time in seconds you are willing to wait for a managed spot training job to complete.', default=86400)
parser.add_argument('--checkpoint_config', type=_utils.yaml_or_json_str, required=False, help='Dictionary of information about the output location for managed spot training checkpoint data.', default={})
### End spot instance support
parser.add_argument('--tags', type=_utils.yaml_or_json_str, required=False, help='An array of key-value pairs, to categorize AWS resources.', default={})
return parser
def create_parser():
parser = argparse.ArgumentParser(description='SageMaker Training Job')
_utils.add_default_client_arguments(parser)
parser.add_argument('--endpoint_config_name', type=str, required=False, help='The name of the endpoint configuration. If an existing endpoint is being updated, a suffix is automatically added if this config name exists.', default='')
parser.add_argument('--variant_name_1', type=str, required=False, help='The name of the production variant.', default='variant-name-1')
parser.add_argument('--model_name_1', type=str, required=True, help='The model name used for endpoint deployment.')
parser.add_argument('--initial_instance_count_1', type=int, required=False, help='Number of instances to launch initially.', default=1)
parser.add_argument('--instance_type_1', type=str, required=False, help='The ML compute instance type.', default='ml.m4.xlarge')
parser.add_argument('--initial_variant_weight_1', type=float, required=False, help='Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.', default=1.0)
parser.add_argument('--accelerator_type_1', choices=['ml.eia1.medium', 'ml.eia1.large', 'ml.eia1.xlarge', ''], type=str, required=False, help='The size of the Elastic Inference (EI) instance to use for the production variant.', default='')
parser.add_argument('--variant_name_2', type=str, required=False, help='The name of the production variant.', default='variant-name-2')
parser.add_argument('--model_name_2', type=str, required=False, help='The model name used for endpoint deployment.', default='')
parser.add_argument('--initial_instance_count_2', type=int, required=False, help='Number of instances to launch initially.', default=1)
parser.add_argument('--instance_type_2', type=str, required=False, help='The ML compute instance type.', default='ml.m4.xlarge')
parser.add_argument('--initial_variant_weight_2', type=float, required=False, help='Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.', default=1.0)
parser.add_argument('--accelerator_type_2', choices=['ml.eia1.medium', 'ml.eia1.large', 'ml.eia1.xlarge', ''], type=str, required=False, help='The size of the Elastic Inference (EI) instance to use for the production variant.', default='')
parser.add_argument('--variant_name_3', type=str, required=False, help='The name of the production variant.', default='variant-name-3')
parser.add_argument('--model_name_3', type=str, required=False, help='The model name used for endpoint deployment.', default='')
parser.add_argument('--initial_instance_count_3', type=int, required=False, help='Number of instances to launch initially.', default=1)
parser.add_argument('--instance_type_3', type=str, required=False, help='The ML compute instance type.', default='ml.m4.xlarge')
parser.add_argument('--initial_variant_weight_3', type=float, required=False, help='Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.', default=1.0)
parser.add_argument('--accelerator_type_3', choices=['ml.eia1.medium', 'ml.eia1.large', 'ml.eia1.xlarge', ''], type=str, required=False, help='The size of the Elastic Inference (EI) instance to use for the production variant.', default='')
parser.add_argument('--resource_encryption_key', type=str, required=False, help='The AWS KMS key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance(s).', default='')
parser.add_argument('--endpoint_config_tags', type=_utils.yaml_or_json_str, required=False, help='An array of key-value pairs, to categorize AWS resources.', default={})
parser.add_argument('--endpoint_name', type=str, required=False, help='The name of the endpoint.', default='')
parser.add_argument('--endpoint_tags', type=_utils.yaml_or_json_str, required=False, help='An array of key-value pairs, to categorize AWS resources.', default={})
parser.add_argument('--update_endpoint', type=_utils.str_to_bool, required=False, help='If True, update endpoint if it exists else creates one', default=False)
parser.add_argument('--endpoint_name_output_path', type=str, default='/tmp/endpoint-name', help='Local output path for the file containing the name of the created endpoint.')
return parser
def create_parser():
parser = argparse.ArgumentParser(description='SageMaker Ground Truth Job')
_utils.add_default_client_arguments(parser)
parser.add_argument('--role', type=str.strip, required=True, help='The Amazon Resource Name (ARN) that Amazon SageMaker assumes to perform tasks on your behalf.')
parser.add_argument('--job_name', type=str.strip, required=True, help='The name of the labeling job.')
parser.add_argument('--label_attribute_name', type=str.strip, required=False, help='The attribute name to use for the label in the output manifest file. Default is the job name.', default='')
parser.add_argument('--manifest_location', type=str.strip, required=True, help='The Amazon S3 location of the manifest file that describes the input data objects.')
parser.add_argument('--output_location', type=str.strip, required=True, help='The Amazon S3 location to write output data.')
parser.add_argument('--output_encryption_key', type=str.strip, required=False, help='The AWS KMS key that Amazon SageMaker uses to encrypt the model artifacts.', default='')
parser.add_argument('--task_type', type=str.strip, required=True, help='Built in image classification, bounding box, text classification, or semantic segmentation, or custom. If custom, please provide pre- and post-labeling task lambda functions.')
parser.add_argument('--worker_type', type=str.strip, required=True, help='The workteam for data labeling, either public, private, or vendor.')
parser.add_argument('--workteam_arn', type=str.strip, required=False, help='The ARN of the work team assigned to complete the tasks.')
parser.add_argument('--no_adult_content', type=_utils.str_to_bool, required=False, help='If true, your data is free of adult content.', default='False')
parser.add_argument('--no_ppi', type=_utils.str_to_bool, required=False, help='If true, your data is free of personally identifiable information.', default='False')
parser.add_argument('--label_category_config', type=str.strip, required=False, help='The S3 URL of the JSON structured file that defines the categories used to label the data objects.', default='')
parser.add_argument('--max_human_labeled_objects', type=_utils.str_to_int, required=False, help='The maximum number of objects that can be labeled by human workers.', default=0)
parser.add_argument('--max_percent_objects', type=_utils.str_to_int, required=False, help='The maximum percentatge of input data objects that should be labeled.', default=0)
parser.add_argument('--enable_auto_labeling', type=_utils.str_to_bool, required=False, help='Enables auto-labeling, only for bounding box, text classification, and image classification.', default=False)
parser.add_argument('--initial_model_arn', type=str.strip, required=False, help='The ARN of the final model used for a previous auto-labeling job.', default='')
parser.add_argument('--resource_encryption_key', type=str.strip, required=False, help='The AWS KMS key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance(s).', default='')
parser.add_argument('--ui_template', type=str.strip, required=True, help='The Amazon S3 bucket location of the UI template.')
parser.add_argument('--pre_human_task_function', type=str.strip, required=False, help='The ARN of a Lambda function that is run before a data object is sent to a human worker.', default='')
parser.add_argument('--post_human_task_function', type=str.strip, required=False, help='The ARN of a Lambda function implements the logic for annotation consolidation.', default='')
parser.add_argument('--task_keywords', type=str.strip, required=False, help='Keywords used to describe the task so that workers on Amazon Mechanical Turk can discover the task.', default='')
parser.add_argument('--title', type=str.strip, required=True, help='A title for the task for your human workers.')
parser.add_argument('--description', type=str.strip, required=True, help='A description of the task for your human workers.')
parser.add_argument('--num_workers_per_object', type=_utils.str_to_int, required=True, help='The number of human workers that will label an object.')
parser.add_argument('--time_limit', type=_utils.str_to_int, required=True, help='The amount of time that a worker has to complete a task in seconds')
parser.add_argument('--task_availibility', type=_utils.str_to_int, required=False, help='The length of time that a task remains available for labelling by human workers.', default=0)
parser.add_argument('--max_concurrent_tasks', type=_utils.str_to_int, required=False, help='The maximum number of data objects that can be labeled by human workers at the same time.', default=0)
parser.add_argument('--workforce_task_price', type=_utils.str_to_float, required=False, help='The price that you pay for each task performed by a public worker in USD. Specify to the tenth fractions of a cent. Format as "0.000".', default=0.000)
parser.add_argument('--tags', type=_utils.str_to_json_dict, required=False, help='An array of key-value pairs, to categorize AWS resources.', default='{}')
return parser
def create_parser():
parser = argparse.ArgumentParser(
description='SageMaker Hyperparameter Tuning Job')
_utils.add_default_client_arguments(parser)
parser.add_argument('--team_name',
type=str,
required=True,
help='The name of your work team.')
parser.add_argument('--description',
type=str,
required=True,
help='A description of the work team.')
parser.add_argument(
'--user_pool',
type=str,
required=False,
help=
'An identifier for a user pool. The user pool must be in the same region as the service that you are calling.',
default='')
parser.add_argument(
'--user_groups',
type=str,
required=False,
help='A list of identifiers for user groups separated by commas.',
default='')
parser.add_argument(
'--client_id',
type=str,
required=False,
help=
'An identifier for an application client. You must create the app client ID using Amazon Cognito.',
default='')
parser.add_argument(
'--sns_topic',
type=str,
required=False,
help=
'The ARN for the SNS topic to which notifications should be published.',
default='')
parser.add_argument(
'--tags',
type=_utils.yaml_or_json_str,
required=False,
help='An array of key-value pairs, to categorize AWS resources.',
default={})
parser.add_argument(
'--workteam_arn_output_path',
type=str,
default='/tmp/workteam-arn',
help=
'Local output path for the file containing the ARN of the workteam.')
return parser
def create_parser():
parser = argparse.ArgumentParser(description='SageMaker Training Job')
_utils.add_default_client_arguments(parser)
parser.add_argument('--model_name', type=str, required=True, help='The name of the new model.')
parser.add_argument('--role', type=str, required=True, help='The Amazon Resource Name (ARN) that Amazon SageMaker assumes to perform tasks on your behalf.')
parser.add_argument('--container_host_name', type=str, required=False, help='When a ContainerDefinition is part of an inference pipeline, this value uniquely identifies the container for the purposes of logging and metrics.', default='')
parser.add_argument('--image', type=str, required=False, help='The Amazon EC2 Container Registry (Amazon ECR) path where inference code is stored.', default='')
parser.add_argument('--model_artifact_url', type=str, required=False, help='S3 path where Amazon SageMaker to store the model artifacts.', default='')
parser.add_argument('--environment', type=_utils.yaml_or_json_str, required=False, help='The dictionary of the environment variables to set in the Docker container. Up to 16 key-value entries in the map.', default={})
parser.add_argument('--model_package', type=str, required=False, help='The name or Amazon Resource Name (ARN) of the model package to use to create the model.', default='')
parser.add_argument('--secondary_containers', type=_utils.yaml_or_json_str, required=False, help='A list of dicts that specifies the additional containers in the inference pipeline.', default={})
parser.add_argument('--vpc_security_group_ids', type=str, required=False, help='The VPC security group IDs, in the form sg-xxxxxxxx.', default='')
parser.add_argument('--vpc_subnets', type=str, required=False, help='The ID of the subnets in the VPC to which you want to connect your hpo job.', default='')
parser.add_argument('--network_isolation', type=_utils.str_to_bool, required=False, help='Isolates the training container.', default=True)
parser.add_argument('--tags', type=_utils.yaml_or_json_str, required=False, help='An array of key-value pairs, to categorize AWS resources.', default={})
parser.add_argument('--model_name_output_path', type=str, default='/tmp/model-name', help='Local output path for the file containing the name of the model SageMaker created.')
return parser
def create_parser():
parser = argparse.ArgumentParser(
description='SageMaker Hyperparameter Tuning Job')
_utils.add_default_client_arguments(parser)
parser.add_argument(
'--job_name',
type=str,
required=False,
help=
'The name of the tuning job. Must be unique within the same AWS account and AWS region.'
)
parser.add_argument(
'--role',
type=str,
required=True,
help=
'The Amazon Resource Name (ARN) that Amazon SageMaker assumes to perform tasks on your behalf.'
)
parser.add_argument(
'--image',
type=str,
required=False,
help=
'The registry path of the Docker image that contains the training algorithm.',
default='')
parser.add_argument(
'--algorithm_name',
type=str,
required=False,
help=
'The name of the resource algorithm to use for the hyperparameter tuning job.',
default='')
parser.add_argument(
'--training_input_mode',
choices=['File', 'Pipe'],
type=str,
required=False,
help='The input mode that the algorithm supports. File or Pipe.',
default='File')
parser.add_argument(
'--metric_definitions',
type=_utils.yaml_or_json_str,
required=False,
help=
'The dictionary of name-regex pairs specify the metrics that the algorithm emits.',
default={})
parser.add_argument(
'--strategy',
choices=['Bayesian', 'Random'],
type=str,
required=False,
help=
'How hyperparameter tuning chooses the combinations of hyperparameter values to use for the training job it launches.',
default='Bayesian')
parser.add_argument(
'--metric_name',
type=str,
required=True,
help='The name of the metric to use for the objective metric.')
parser.add_argument(
'--metric_type',
choices=['Maximize', 'Minimize'],
type=str,
required=True,
help='Whether to minimize or maximize the objective metric.')
parser.add_argument(
'--early_stopping_type',
choices=['Off', 'Auto'],
type=str,
required=False,
help='Whether to minimize or maximize the objective metric.',
default='Off')
parser.add_argument(
'--static_parameters',
type=_utils.yaml_or_json_str,
required=False,
help=
'The values of hyperparameters that do not change for the tuning job.',
default={})
parser.add_argument(
'--integer_parameters',
type=_utils.yaml_or_json_str,
required=False,
help=
'The array of IntegerParameterRange objects that specify ranges of integer hyperparameters that you want to search.',
default=[])
parser.add_argument(
'--continuous_parameters',
type=_utils.yaml_or_json_str,
required=False,
help=
'The array of ContinuousParameterRange objects that specify ranges of continuous hyperparameters that you want to search.',
default=[])
parser.add_argument(
'--categorical_parameters',
type=_utils.yaml_or_json_str,
required=False,
help=
'The array of CategoricalParameterRange objects that specify ranges of categorical hyperparameters that you want to search.',
default=[])
parser.add_argument(
'--channels',
type=_utils.yaml_or_json_str,
required=True,
help=
'A list of dicts specifying the input channels. Must have at least one.'
)
parser.add_argument(
'--output_location',
type=str,
required=True,
help=
'The Amazon S3 path where you want Amazon SageMaker to store the results of the transform job.'
)
parser.add_argument(
'--output_encryption_key',
type=str,
required=False,
help=
'The AWS KMS key that Amazon SageMaker uses to encrypt the model artifacts.',
default='')
parser.add_argument('--instance_type',
type=str,
required=False,
help='The ML compute instance type.',
default='ml.m4.xlarge')
parser.add_argument(
'--instance_count',
type=int,
required=False,
help='The number of ML compute instances to use in each training job.',
default=1)
parser.add_argument(
'--volume_size',
type=int,
required=False,
help='The size of the ML storage volume that you want to provision.',
default=30)
parser.add_argument(
'--max_num_jobs',
type=int,
required=True,
help=
'The maximum number of training jobs that a hyperparameter tuning job can launch.'
)
parser.add_argument(
'--max_parallel_jobs',
type=int,
required=True,
help=
'The maximum number of concurrent training jobs that a hyperparameter tuning job can launch.'
)
parser.add_argument(
'--max_run_time',
type=int,
required=False,
help='The maximum run time in seconds per training job.',
default=86400)
parser.add_argument(
'--resource_encryption_key',
type=str,
required=False,
help=
'The AWS KMS key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance(s).',
default='')
parser.add_argument(
'--vpc_security_group_ids',
type=str,
required=False,
help='The VPC security group IDs, in the form sg-xxxxxxxx.')
parser.add_argument(
'--vpc_subnets',
type=str,
required=False,
help=
'The ID of the subnets in the VPC to which you want to connect your hpo job.'
)
parser.add_argument('--network_isolation',
type=_utils.str_to_bool,
required=False,
help='Isolates the training container.',
default=True)
parser.add_argument(
'--traffic_encryption',
type=_utils.str_to_bool,
required=False,
help=
'Encrypts all communications between ML compute instances in distributed training.',
default=False)
parser.add_argument(
'--warm_start_type',
choices=['IdenticalDataAndAlgorithm', 'TransferLearning', ''],
type=str,
required=False,
help=
'Specifies either "IdenticalDataAndAlgorithm" or "TransferLearning"')
parser.add_argument(
'--parent_hpo_jobs',
type=str,
required=False,
help=
'List of previously completed or stopped hyperparameter tuning jobs to be used as a starting point.',
default='')
### Start spot instance support
parser.add_argument('--spot_instance',
type=_utils.str_to_bool,
required=False,
help='Use managed spot training.',
default=False)
parser.add_argument(
'--max_wait_time',
type=int,
required=False,
help=
'The maximum time in seconds you are willing to wait for a managed spot training job to complete.',
default=86400)
parser.add_argument(
'--checkpoint_config',
type=_utils.yaml_or_json_str,
required=False,
help=
'Dictionary of information about the output location for managed spot training checkpoint data.',
default={})
### End spot instance support
parser.add_argument(
'--tags',
type=_utils.yaml_or_json_str,
required=False,
help='An array of key-value pairs, to categorize AWS resources.',
default={})
return parser
def create_parser():
parser = argparse.ArgumentParser(description='SageMaker Processing Job')
_utils.add_default_client_arguments(parser)
parser.add_argument('--job_name',
type=str,
required=False,
help='The name of the processing job.',
default='')
parser.add_argument(
'--role',
type=str,
required=True,
help=
'The Amazon Resource Name (ARN) that Amazon SageMaker assumes to perform tasks on your behalf.'
)
parser.add_argument(
'--image',
type=str,
required=True,
help=
'The registry path of the Docker image that contains the processing container.',
default='')
parser.add_argument('--instance_type',
required=True,
type=str,
help='The ML compute instance type.',
default='ml.m4.xlarge')
parser.add_argument(
'--instance_count',
required=True,
type=int,
help=
'The number of ML compute instances to use in each processing job.',
default=1)
parser.add_argument(
'--volume_size',
type=int,
required=False,
help='The size of the ML storage volume that you want to provision.',
default=30)
parser.add_argument(
'--resource_encryption_key',
type=str,
required=False,
help=
'The AWS KMS key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance(s).',
default='')
parser.add_argument(
'--output_encryption_key',
type=str,
required=False,
help=
'The AWS KMS key that Amazon SageMaker uses to encrypt the processing artifacts.',
default='')
parser.add_argument(
'--max_run_time',
type=int,
required=False,
help='The maximum run time in seconds for the processing job.',
default=86400)
parser.add_argument(
'--environment',
type=_utils.yaml_or_json_str,
required=False,
help=
'The dictionary of the environment variables to set in the Docker container. Up to 16 key-value entries in the map.',
default={})
parser.add_argument(
'--container_entrypoint',
type=_utils.yaml_or_json_str,
required=False,
help=
'The entrypoint for the processing job. This is in the form of a list of strings that make a command.',
default=[])
parser.add_argument(
'--container_arguments',
type=_utils.yaml_or_json_str,
required=False,
help='A list of string arguments to be passed to a processing job.',
default=[])
parser.add_argument(
'--input_config',
type=_utils.yaml_or_json_str,
required=False,
help='Parameters that specify Amazon S3 inputs for a processing job.',
default=[])
parser.add_argument(
'--output_config',
type=_utils.yaml_or_json_str,
required=True,
help='Parameters that specify Amazon S3 outputs for a processing job.',
default=[])
parser.add_argument(
'--vpc_security_group_ids',
type=str,
required=False,
help='The VPC security group IDs, in the form sg-xxxxxxxx.')
parser.add_argument(
'--vpc_subnets',
type=str,
required=False,
help=
'The ID of the subnets in the VPC to which you want to connect your hpo job.'
)
parser.add_argument('--network_isolation',
type=_utils.str_to_bool,
required=False,
help='Isolates the processing container.',
default=True)
parser.add_argument(
'--traffic_encryption',
type=_utils.str_to_bool,
required=False,
help=
'Encrypts all communications between ML compute instances in distributed training.',
default=False)
parser.add_argument(
'--tags',
type=_utils.yaml_or_json_str,
required=False,
help='An array of key-value pairs, to categorize AWS resources.',
default={})
parser.add_argument(
'--job_name_output_path',
type=str,
default='/tmp/job-name',
help=
'Local output path for the file containing the name of the processing job.'
)
parser.add_argument(
'--output_artifacts_output_path',
type=str,
default='/tmp/output-artifacts',
help=
'Local output path for the file containing the dictionary describing the output S3 artifacts.'
)
return parser
def create_parser():
parser = argparse.ArgumentParser(description='SageMaker Training Job')
_utils.add_default_client_arguments(parser)
parser.add_argument('--endpoint_config_name',
type=str.strip,
required=False,
help='The name of the endpoint configuration.',
default='')
parser.add_argument('--variant_name_1',
type=str.strip,
required=False,
help='The name of the production variant.',
default='variant-name-1')
parser.add_argument('--model_name_1',
type=str.strip,
required=True,
help='The model name used for endpoint deployment.')
parser.add_argument('--initial_instance_count_1',
type=_utils.str_to_int,
required=False,
help='Number of instances to launch initially.',
default=1)
parser.add_argument(
'--instance_type_1',
choices=[
'ml.m4.xlarge', 'ml.m4.2xlarge', 'ml.m4.4xlarge', 'ml.m4.10xlarge',
'ml.m4.16xlarge', 'ml.m5.large', 'ml.m5.xlarge', 'ml.m5.2xlarge',
'ml.m5.4xlarge', 'ml.m5.12xlarge', 'ml.m5.24xlarge',
'ml.c4.xlarge', 'ml.c4.2xlarge', 'ml.c4.4xlarge', 'ml.c4.8xlarge',
'ml.p2.xlarge', 'ml.p2.8xlarge', 'ml.p2.16xlarge', 'ml.p3.2xlarge',
'ml.p3.8xlarge', 'ml.p3.16xlarge', 'ml.c5.xlarge', 'ml.c5.2xlarge',
'ml.c5.4xlarge', 'ml.c5.9xlarge', 'ml.c5.18xlarge', ''
],
type=str.strip,
required=False,
help='The ML compute instance type.',
default='ml.m4.xlarge')
parser.add_argument(
'--initial_variant_weight_1',
type=_utils.str_to_float,
required=False,
help=
'Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.',
default=1.0)
parser.add_argument(
'--accelerator_type_1',
choices=['ml.eia1.medium', 'ml.eia1.large', 'ml.eia1.xlarge', ''],
type=str.strip,
required=False,
help=
'The size of the Elastic Inference (EI) instance to use for the production variant.',
default='')
parser.add_argument('--variant_name_2',
type=str.strip,
required=False,
help='The name of the production variant.',
default='variant-name-2')
parser.add_argument('--model_name_2',
type=str.strip,
required=False,
help='The model name used for endpoint deployment.',
default='')
parser.add_argument('--initial_instance_count_2',
type=_utils.str_to_int,
required=False,
help='Number of instances to launch initially.',
default=1)
parser.add_argument(
'--instance_type_2',
choices=[
'ml.m4.xlarge', 'ml.m4.2xlarge', 'ml.m4.4xlarge', 'ml.m4.10xlarge',
'ml.m4.16xlarge', 'ml.m5.large', 'ml.m5.xlarge', 'ml.m5.2xlarge',
'ml.m5.4xlarge', 'ml.m5.12xlarge', 'ml.m5.24xlarge',
'ml.c4.xlarge', 'ml.c4.2xlarge', 'ml.c4.4xlarge', 'ml.c4.8xlarge',
'ml.p2.xlarge', 'ml.p2.8xlarge', 'ml.p2.16xlarge', 'ml.p3.2xlarge',
'ml.p3.8xlarge', 'ml.p3.16xlarge', 'ml.c5.xlarge', 'ml.c5.2xlarge',
'ml.c5.4xlarge', 'ml.c5.9xlarge', 'ml.c5.18xlarge', ''
],
type=str.strip,
required=False,
help='The ML compute instance type.',
default='ml.m4.xlarge')
parser.add_argument(
'--initial_variant_weight_2',
type=_utils.str_to_float,
required=False,
help=
'Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.',
default=1.0)
parser.add_argument(
'--accelerator_type_2',
choices=['ml.eia1.medium', 'ml.eia1.large', 'ml.eia1.xlarge', ''],
type=str.strip,
required=False,
help=
'The size of the Elastic Inference (EI) instance to use for the production variant.',
default='')
parser.add_argument('--variant_name_3',
type=str.strip,
required=False,
help='The name of the production variant.',
default='variant-name-3')
parser.add_argument('--model_name_3',
type=str.strip,
required=False,
help='The model name used for endpoint deployment.',
default='')
parser.add_argument('--initial_instance_count_3',
type=_utils.str_to_int,
required=False,
help='Number of instances to launch initially.',
default=1)
parser.add_argument(
'--instance_type_3',
choices=[
'ml.m4.xlarge', 'ml.m4.2xlarge', 'ml.m4.4xlarge', 'ml.m4.10xlarge',
'ml.m4.16xlarge', 'ml.m5.large', 'ml.m5.xlarge', 'ml.m5.2xlarge',
'ml.m5.4xlarge', 'ml.m5.12xlarge', 'ml.m5.24xlarge',
'ml.c4.xlarge', 'ml.c4.2xlarge', 'ml.c4.4xlarge', 'ml.c4.8xlarge',
'ml.p2.xlarge', 'ml.p2.8xlarge', 'ml.p2.16xlarge', 'ml.p3.2xlarge',
'ml.p3.8xlarge', 'ml.p3.16xlarge', 'ml.c5.xlarge', 'ml.c5.2xlarge',
'ml.c5.4xlarge', 'ml.c5.9xlarge', 'ml.c5.18xlarge', ''
],
type=str.strip,
required=False,
help='The ML compute instance type.',
default='ml.m4.xlarge')
parser.add_argument(
'--initial_variant_weight_3',
type=_utils.str_to_float,
required=False,
help=
'Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.',
default=1.0)
parser.add_argument(
'--accelerator_type_3',
choices=['ml.eia1.medium', 'ml.eia1.large', 'ml.eia1.xlarge', ''],
type=str.strip,
required=False,
help=
'The size of the Elastic Inference (EI) instance to use for the production variant.',
default='')
parser.add_argument(
'--resource_encryption_key',
type=str.strip,
required=False,
help=
'The AWS KMS key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance(s).',
default='')
parser.add_argument(
'--endpoint_config_tags',
type=_utils.str_to_json_dict,
required=False,
help='An array of key-value pairs, to categorize AWS resources.',
default='{}')
parser.add_argument('--endpoint_name',
type=str.strip,
required=False,
help='The name of the endpoint.',
default='')
parser.add_argument(
'--endpoint_tags',
type=_utils.str_to_json_dict,
required=False,
help='An array of key-value pairs, to categorize AWS resources.',
default='{}')
return parser
