pipeline.yml

$schema: https://azuremlschemas.azureedge.net/latest/pipelineJob.schema.json
type: pipeline
display_name: mnist-batch-identification-using-parallel
description: The hello world pipeline job with inline parallel job
tags:
  tag: tagvalue
  owner: sdkteam

jobs:
  prepare_data:
    type: command
    compute: azureml:cpu-cluster
    command: >-
      python prepare_data.py --output_folder ${{outputs.mnist_png}};
      python dump_mltable.py --output_folder ${{outputs.mnist_png}};
    code: ./script
    outputs:
      mnist_png:
        type: mltable
        mode: rw_mount

    environment:
        name: "prepare_data_environment"
        version: 1
        image: mcr.microsoft.com/azureml/openmpi4.1.0-ubuntu20.04
        conda_file: ./environment/environment_prepare.yml

  predict_digits_mnist:
    type: parallel
    compute: azureml:cpu-cluster
    inputs:
      job_data_path:
        type: mltable
        path: ${{parent.jobs.prepare_data.outputs.mnist_png}}
        mode: eval_mount
      score_model:
        type: uri_folder
        path: ./mnist_models
        mode: download
    outputs:
      job_output_file:
        type: uri_file
        mode: rw_mount

    mini_batch_size: "5"
    resources:
      instance_count: 2
    mini_batch_error_threshold: 5
    logging_level: "DEBUG"
    input_data: ${{inputs.job_data_path}}
    max_concurrency_per_instance: 2
    retry_settings:
      max_retries: 2
      timeout: 60

    task:
      type: run_function
      code: ./script
      entry_script: digit_identification.py
      environment:
        name: "batch_environment"
        version: 1
        image: mcr.microsoft.com/azureml/openmpi4.1.0-ubuntu20.04
        conda_file: ./environment/environment_parallel.yml
      program_arguments: >-
        --model ${{inputs.score_model}}
      append_row_to: ${{outputs.job_output_file}}
      
  view_prediction_result:
    type: command
    compute: azureml:cpu-cluster
    inputs:
      inference_result: ${{parent.jobs.predict_digits_mnist.outputs.job_output_file}}
    command: >-
      cat ${{inputs.inference_result}}
    environment: azureml:AzureML-sklearn-1.0-ubuntu20.04-py38-cpu:1