MLOps with Azure DevOps
Download as PPTX, PDF1 like679 views
MLOps refers to applying DevOps practices and principles to machine learning. This allows for machine learning models and projects to be developed and deployed using automated pipelines for continuous integration and delivery. MLOps benefits include making machine learning work reproducible and auditable, enabling validation of models, and providing observability through monitoring of models after deployment. MLOps uses the same development practices as software engineering to ensure quality control for machine learning.
MLOps with Azure DevOps
- 1. MLOps – DevOps for ML Marco Parenzan (twitter: @marco_parenzan)
- 12. DevOps + ML = MLOps
- 13. © Microsoft Corporation Reproducibility / Auditability MLOps Benefits Validation Automation / Observability • Code drives generation and deployments • Pipelines are reproducible and verifiable • All artifacts can be tagged and audited • SWE best practices for quality control • Offline comparisons of model quality • Minimize bias and enable explainability • Controlled rollout capabilities • Live comparison of predicted vs. expected performance • Results fed back to watch for drift and improve model
- 14. «The italian way »
- 17. .NET 5 INFRASTRUCTURE .NET STANDARD DESKTOP WEB CLOUD MOBILE GAMING IoT AI WPF Windows Forms UWP ASP.NET Xamarin UnityAzure ARM32 ARM64 ML.NET .NET for Apache Spark
- 19. Azure DevOps
- 21. Azure Boards Offri valore agli utenti più velocemente utilizzando strumenti agili comprovati per pianificare, monitorare e discutere il lavoro in tutti i tuoi team. Azure Pipelines Compila, testa e distribuisci con CI/CD che funziona con qualsiasi linguaggio, piattaforma e cloud. Connettersi a GitHub o qualsiasi altro provider Git e distribuire continuamente. Azure Repos Ottieni repository Git privati illimitati e ospitati nel cloud e collabora per creare codice migliore con richieste pull e gestione avanzata dei file. Azure Test Plans Testare e spedire con sicurezza utilizzandostrumentiditestmanualied esplorativi. Azure Artifacts Crea, ospita e condividi pacchetti con il tuo team e aggiungi elementi alle pipeline CI/CD con un solo clic.
- 22. Maven Target any cloud, on-prem or both and deploy to the servers you need
- 26. App developer using Azure DevOps Build appCollaborate Test app Release app Monitor app
- 27. App developer using Azure DevOps Build appCollaborate Test app Release app Monitor app Data scientist using Azure Machine Learning
- 28. Code, dataset, and environment versioning Build appCollaborate Test app Release app Monitor app App developer using Azure DevOps Data scientist using Azure Machine Learning
- 29. Model validation & profiling Train model Validate model Build appCollaborate Test app Release app Monitor app App developer using Azure DevOps Data scientist using Azure Machine Learning
- 30. Model packaging Simple deployment across cloud and edge Train model Validate model Deploy model Build appCollaborate Test app Release app Monitor app App developer using Azure DevOps Data scientist using Azure Machine Learning
- 31. Model management & monitoring Model performance analysis Train model Validate model Deploy model Monitor model Retrain model Build appCollaborate Test app Release app Monitor app App developer using Azure DevOps Data scientist using Azure Machine Learning
- 32. Train model Validate model Deploy model Monitor model Retrain model Build appCollaborate Test app Release app Monitor app Azure Machine Learning extension for Azure DevOps App developer using Azure DevOps Data scientist using Azure Machine Learning
- 33. Train model Validate model Deploy model Monitor model Retrain model Build appCollaborate Test app Release app Monitor app Audit trail management and model interpretability App developer using Azure DevOps Data scientist using Azure Machine Learning
- 35. Marco Parenzan (twitter: @marco_parenzan)