name: Kubeflow - Launch TFJob
description: Kubeflow TFJob launcher
inputs:
- {name: Name,                      type: String,                       description: 'TFJob name.'}
- {name: Namespace,                 type: String,   default: kubeflow,  description: 'TFJob namespace.'}
- {name: Version,                   type: String,   default: v1,        description: 'TFJob version.'}
- {name: ActiveDeadlineSeconds,     type: Integer,  default: -1,        description: 'Specifies the duration (in seconds) since startTime during which the job can remain active before it is terminated. Must be a positive integer. This setting applies only to pods where restartPolicy is OnFailure or Always.'}
- {name: BackoffLimit,              type: Integer,  default: -1,        description: 'Number of retries before marking this job as failed.'}
- {name: ttl Seconds After Finished,   type: Integer,  default: -1,        description: 'Defines the TTL for cleaning up finished TFJobs.'}
- {name: CleanPodPolicy,            type: String,   default: Running,   description: 'Defines the policy for cleaning up pods after the TFJob completes.'}
- {name: PS Spec,                   type: JSON,     default: '{}',      description: 'TFJob ps replicaSpecs.'}
- {name: Worker Spec,               type: JSON,     default: '{}',      description: 'TFJob worker replicaSpecs.'}
- {name: Chief Spec,                type: JSON,     default: '{}',      description: 'TFJob chief replicaSpecs.'}
- {name: Evaluator Spec,            type: JSON,     default: '{}',      description: 'TFJob evaluator replicaSpecs.'}
- {name: Tfjob Timeout Minutes,     type: Integer,  default: 1440,      description: 'Time in minutes to wait for the TFJob to complete.'}
- {name: Delete Finished Tfjob,     type: Bool,     default: 'True' ,   description: 'Whether to delete the tfjob after it is finished.'}
outputs:
- {name: mlpipeline-ui-metadata, description: 'Model ARTIFACT OUTPUT'}
implementation:
  container:
    image: chuckshow/kubeflow-tfjob-launcher:latest
    command: [python, /ml/launch_tfjob.py]
    args: [
      --name,                     {inputValue: Name},
      --namespace,                {inputValue: Namespace},
      --version,                  {inputValue: Version},
      --activeDeadlineSeconds,    {inputValue: ActiveDeadlineSeconds},
      --backoffLimit,             {inputValue: BackoffLimit},
      --cleanPodPolicy,           {inputValue: CleanPodPolicy},
      --ttlSecondsAfterFinished,  {inputValue: ttl Seconds After Finished},
      --psSpec,                   {inputValue: PS Spec},
      --workerSpec,               {inputValue: Worker Spec},
      --chiefSpec,                {inputValue: Chief Spec},
      --evaluatorSpec,            {inputValue: Evaluator Spec},
      --tfjobTimeoutMinutes,      {inputValue: Tfjob Timeout Minutes},
      --deleteAfterDone,          {inputValue: Delete Finished Tfjob}
    ]
    fileOutputs:
      mlpipeline-ui-metadata: '/mlpipeline-ui-metadata.json'