"description": "A brief summary of the model package", "description": "Metadata information related to model package version", "description": "SageMaker inference image uri", "description": "Overview about the inference", "description": "Location of the model artifact", "description": "SageMaker Model Arn or Non SageMaker Model id", "description": "Algorithm used to solve the problem", "description": "Problem being solved with the model", "description": "Overview about the model", "description": "Default model card schema", Provide model content similar to the following example. When creating a model card using the SageMaker Python SDK, model content must be in the model card JSON schema and provided as a string. For more information and sample reports, see theĮxample metrics folder in the Amazon SageMaker Model Governance - Model Monitor, upload them to Amazon S3 and provide an S3 URI toĪutomatically parse evaluation metrics. If you haveĮxisting JSON format evaluation reports generated by SageMaker Clarify or Model card JSON schemaĮvaluation details for a model card must be provided in JSON format. High-risk models and help your organization comply with any existing rules about puttingĬertain models into production. Use these risk rating fields to label unknown, low, medium, or This risk rating can be unknown, low, medium, Given the varied risk profiles of a model, model cards provideĪ field for you to categorize a model’s risk rating. Model that approves loan applications might be a higher risk model than one that detects Risk ratingsĭevelopers create ML models for use cases with varying levels of risk. Should be used in production, the scenarios in which is appropriate to use a model, andĪdditional considerations such as the type of data to use with the model or anyĪssumptions made during development. The intended uses of a model go beyond technical details and describe how a model Use cases for which the model was not intendedĪssumptions made when developing the model 参考: 違反のスキーマ (constraint_violations.Use cases for which the model was intended hourly (), enable_cloudwatch_metrics = True, ) suggested_constraints (), schedule_cron_expression = CronExpressionGenerator. baseline_statistics (), constraints = my_default_monitor. endpoint, output_s3_uri = s3_report_path, statistics = my_default_monitor. create_monitoring_schedule ( monitor_schedule_name = monitor_schedule_name, endpoint_input = predictor. client ( ' s3 ' ) current_endpoint_capture_prefix = ' /model_monitor/monitoring_report ' my_default_monitor. 参考: Amazon SageMaker Model Monitor を活用したデータドリフト検知の解説 | Amazon Web Services ブログ SageMaker Model MonitorとSageMaker Clarifyを使用して、ML監視を実践してみます。
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |