AlgorithmSpecification

class aws_cdk.aws_stepfunctions_tasks.AlgorithmSpecification(*, algorithm_name=None, metric_definitions=None, training_image=None, training_input_mode=None)

Bases: object

__init__(*, algorithm_name=None, metric_definitions=None, training_image=None, training_input_mode=None)

Specify the training algorithm and algorithm-specific metadata.

Parameters

  • algorithm_name (Optional[str]) – Name of the algorithm resource to use for the training job. This must be an algorithm resource that you created or subscribe to on AWS Marketplace. If you specify a value for this parameter, you can’t specify a value for TrainingImage. Default: - No algorithm is specified

  • metric_definitions (Optional[List[MetricDefinition]]) – List of metric definition objects. Each object specifies the metric name and regular expressions used to parse algorithm logs. Default: - No metrics

  • training_image (Optional[DockerImage]) – Registry path of the Docker image that contains the training algorithm. Default: - No Docker image is specified

  • training_input_mode (Optional[InputMode]) – Input mode that the algorithm supports. Default: ‘File’ mode

stability :stability: experimental

Attributes

algorithm_name

Name of the algorithm resource to use for the training job.

This must be an algorithm resource that you created or subscribe to on AWS Marketplace. If you specify a value for this parameter, you can’t specify a value for TrainingImage.

default :default: - No algorithm is specified

stability :stability: experimental

Return type

Optional[str]

metric_definitions

List of metric definition objects.

Each object specifies the metric name and regular expressions used to parse algorithm logs.

default :default: - No metrics

stability :stability: experimental

Return type

Optional[List[MetricDefinition]]

training_image

Registry path of the Docker image that contains the training algorithm.

default :default: - No Docker image is specified

stability :stability: experimental

Return type

Optional[DockerImage]

training_input_mode

Input mode that the algorithm supports.

default :default: ‘File’ mode

stability :stability: experimental

Return type

Optional[InputMode]