无服务器计算上的模型训练

from azure.ai.ml import command
from azure.ai.ml import command 
from azure.ai.ml import MLClient # Handle to the workspace
from azure.identity import DefaultAzureCredential # Authentication package

credential = DefaultAzureCredential()
# Get a handle to the workspace. You can find the info on the workspace tab on studio.ml.azure.cn
ml_client = MLClient(
    credential=credential,
    subscription_id="<Azure subscription id>", 
    resource_group_name="<Azure resource group>",
    workspace_name="<Azure Machine Learning Workspace>",
)
job = command(
    command="echo 'hello world'",
    environment="azureml://registries/azureml/environments/sklearn-1.5/labels/latest",
)
# submit the command job
ml_client.create_or_update(job)

$schema: https://azuremlschemas.azureedge.net/latest/commandJob.schema.json
command: echo "hello world"
environment:
  image: library/python:latest

from azure.ai.ml import command
from azure.ai.ml import MLClient      # Handle to the workspace
from azure.identity import DefaultAzureCredential     # Authentication package
from azure.ai.ml.entities import ResourceConfiguration
from azure.ai.ml.entities import UserIdentityConfiguration 

credential = DefaultAzureCredential()
# Get a handle to the workspace. You can find the info on the workspace tab on studio.ml.azure.cn
ml_client = MLClient(
    credential=credential,
    subscription_id="<Azure subscription id>", 
    resource_group_name="<Azure resource group>",
    workspace_name="<Azure Machine Learning Workspace>",
)
job = command(
    command="echo 'hello world'",
    environment="azureml://registries/azureml/environments/sklearn-1.5/labels/latest",
         identity=UserIdentityConfiguration(),
    queue_settings={
      "job_tier": "Standard"  
    }
)
job.resources = ResourceConfiguration(instance_type="Standard_E4s_v3", instance_count=1)
# submit the command job
ml_client.create_or_update(job)

$schema: https://azuremlschemas.azureedge.net/latest/commandJob.schema.json
command: echo "hello world"
environment:
  image: library/python:latest
queue_settings:
   job_tier: Standard #Possible Values are Standard, Spot. Default is Standard.
identity:
  type: user_identity #Possible values are Managed, user_identity
resources:
  instance_count: 1
  instance_type: Standard_E4s_v3 

如果要指定类型或实例计数，使用 ResourceConfiguration 类。

# Create the AutoML classification job with the related factory-function.
from azure.ai.ml.entities import ResourceConfiguration 

classification_job = automl.classification(
    experiment_name=exp_name,
    training_data=my_training_data_input,
    target_column_name="y",
    primary_metric="accuracy",
    n_cross_validations=5,
    enable_model_explainability=True,
    tags={"my_custom_tag": "My custom value"},
)

# Limits are all optional
classification_job.set_limits(
    timeout_minutes=600,
    trial_timeout_minutes=20,
    max_trials=max_trials,
    # max_concurrent_trials = 4,
    # max_cores_per_trial: -1,
    enable_early_termination=True,
)

# Training properties are optional
classification_job.set_training(
    blocked_training_algorithms=[ClassificationModels.LOGISTIC_REGRESSION],
    enable_onnx_compatible_models=True,
)

# Serverless compute resources used to run the job
classification_job.resources = 
ResourceConfiguration(instance_type="Standard_E4s_v3", instance_count=6)

如果要指定类型或实例计数，添加 resources 部分。

$schema: https://azuremlsdk2.blob.core.windows.net/preview/0.0.1/autoMLJob.schema.json
type: automl
experiment_name: dpv2-cli-automl-classifier-experiment
description: A Classification job using bank marketing
# Serverless compute is used to run this AutoML job. 
# Through serverless compute, Azure Machine Learning takes care of creating, scaling, deleting, patching and managing compute, along with providing managed network isolation, reducing the burden on you.

task: classification
log_verbosity: debug
primary_metric: accuracy

target_column_name: "y"

#validation_data_size: 0.20
#n_cross_validations: 5
#test_data_size: 0.1

training_data:
  path: "./training-mltable-folder"
  type: mltable
validation_data:
  path: "./validation-mltable-folder"
  type: mltable
test_data:
  path: "./test-mltable-folder"
  type: mltable

limits:
  timeout_minutes: 180
  max_trials: 40
  max_concurrent_trials: 5
  trial_timeout_minutes: 20
  enable_early_termination: true
  exit_score: 0.92

featurization:
  mode: custom
  transformer_params:
    imputer:
      - fields: ["job"]
        parameters:
          strategy: most_frequent
  blocked_transformers:
    - WordEmbedding
training:
  enable_model_explainability: true
  allowed_training_algorithms:
    - gradient_boosting
    - logistic_regression
# Resources to run this serverless job
resources:
  instance_type="Standard_E4s_v3"
  instance_count=5

对于管道作业，将 "serverless" 指定为默认计算类型以使用无服务器计算。

# Construct pipeline
@pipeline()
def pipeline_with_components_from_yaml(
    training_input,
    test_input,
    training_max_epochs=20,
    training_learning_rate=1.8,
    learning_rate_schedule="time-based",
):
    """E2E dummy train-score-eval pipeline with components defined via yaml."""
    # Call component obj as function: apply given inputs & parameters to create a node in pipeline
    train_with_sample_data = train_model(
        training_data=training_input,
        max_epochs=training_max_epochs,
        learning_rate=training_learning_rate,
        learning_rate_schedule=learning_rate_schedule,
    )

    score_with_sample_data = score_data(
        model_input=train_with_sample_data.outputs.model_output, test_data=test_input
    )
    score_with_sample_data.outputs.score_output.mode = "upload"

    eval_with_sample_data = eval_model(
        scoring_result=score_with_sample_data.outputs.score_output
    )

    # Return: pipeline outputs
    return {
        "trained_model": train_with_sample_data.outputs.model_output,
        "scored_data": score_with_sample_data.outputs.score_output,
        "evaluation_report": eval_with_sample_data.outputs.eval_output,
    }


pipeline_job = pipeline_with_components_from_yaml(
    training_input=Input(type="uri_folder", path=parent_dir + "/data/"),
    test_input=Input(type="uri_folder", path=parent_dir + "/data/"),
    training_max_epochs=20,
    training_learning_rate=1.8,
    learning_rate_schedule="time-based",
)

# set pipeline to use serverless compute
pipeline_job.settings.default_compute = "serverless"

对于管道作业，将 azureml:serverless 指定为默认计算类型以使用无服务器计算。

$schema: https://azuremlschemas.azureedge.net/latest/pipelineJob.schema.json
type: pipeline
display_name: 1b_e2e_registered_components
description: E2E dummy train-score-eval pipeline with registered components
# Serverless compute is used to run this pipeline job. 
# Through serverless compute, Azure Machine Learning takes care of creating, scaling, deleting, patching and managing compute, along with providing managed network isolation, reducing the burden on you.
inputs:
  pipeline_job_training_max_epocs: 20
  pipeline_job_training_learning_rate: 1.8
  pipeline_job_learning_rate_schedule: 'time-based'

outputs: 
  pipeline_job_trained_model:
    mode: upload
  pipeline_job_scored_data:
    mode: upload
  pipeline_job_evaluation_report:
    mode: upload

settings:
 default_compute: azureml:serverless

jobs:
  train_job:
    type: command
    component: azureml:my_train@latest
    inputs:
      training_data: 
        type: uri_folder 
        path: ./data      
      max_epocs: ${{parent.inputs.pipeline_job_training_max_epocs}}
      learning_rate: ${{parent.inputs.pipeline_job_training_learning_rate}}
      learning_rate_schedule: ${{parent.inputs.pipeline_job_learning_rate_schedule}}
    outputs:
      model_output: ${{parent.outputs.pipeline_job_trained_model}}
    services:
      my_vscode:
        type: vs_code
      my_jupyter_lab:
        type: jupyter_lab
      my_tensorboard:
        type: tensor_board
        log_dir: "outputs/tblogs"
    #  my_ssh:
    #    type: tensor_board
    #    ssh_public_keys: <paste the entire pub key content>
    #    nodes: all # Use the `nodes` property to pick which node you want to enable interactive services on. If `nodes` are not selected, by default, interactive applications are only enabled on the head node.

  score_job:
    type: command
    component: azureml:my_score@latest
    inputs:
      model_input: ${{parent.jobs.train_job.outputs.model_output}}
      test_data: 
        type: uri_folder 
        path: ./data
    outputs:
      score_output: ${{parent.outputs.pipeline_job_scored_data}}

  evaluate_job:
    type: command
    component: azureml:my_eval@latest
    inputs:
      scoring_result: ${{parent.jobs.score_job.outputs.score_output}}
    outputs:
      eval_output: ${{parent.outputs.pipeline_job_evaluation_report}}