Modellformate

Sobald deine Modell-Training-Pipeline erfolgreich ausgeführt wurde, musst du dein Modell in einem Format speichern, das sich für die Ablage und die Bereitstellung innerhalb der ML-Serving-Anwendung eignet.

In diesem Kapitel hast du zwei gängige Formate dafür kennengelernt.

Für deinen Use Case hast du festgestellt, dass du dein Modell in einer Programmiersprache trainieren und es dann in einer völlig anderen laden und bereitstellen möchtest.

Welches Format bietet dir diese Art von Flexibilität?

Diese Übung ist Teil des Kurses

<Kurs>MLOps-Bereitstellung und Lebenszyklus</Kurs>

Interaktive praktische Übung

Verwandle Theorie mit einer unserer interaktiven Übungen in die Praxis

Diese Übung ist Teil des Kurses

<Kurs>MLOps-Bereitstellung und Lebenszyklus</Kurs>

Hohe SchwierigkeitSchwierigkeitsgrad

4.8+

Kurs kostenlos starten

This chapter gives a high-level overview of MLOps principles and framework components important for deployment and life cycling.

Exercise 1: The modern MLOps framework Exercise 2: ML workflows Exercise 3: MLOps benefits Exercise 4: Life-cycling stages Exercise 5: App vs. model Exercise 6: Decommissioning Exercise 7: The model life cycle: recap Exercise 8: MLOps components Exercise 9: Automated sequence Exercise 10: Stores and registries Exercise 11: DevOps or MLOps?

This chapter is dedicated to all the considerations we need to make already in the development phase, in order to ensure a smooth ride when we reach the operations. Our ultimate goal is to explain how to train the model using MLOps best practices and build a model package that enables smooth deployment, reproducibility and post-deployment monitoring.

Exercise 1: Deployment-getriebene Entwicklung Exercise 2: Dein Machine-Learning-Modell testen Exercise 3: Der beste Zeitpunkt für den Start der Bereitstellung Exercise 4: Profiling, Versionierung und Feature Stores Exercise 5: Eigenschaften von Feature Stores Exercise 6: Vorteile von Profiling und Feature Store Exercise 7: Reproduzierbarkeit sicherstellen Exercise 8: Modell-Build-Pipelines in CI/CD Exercise 9: Verschiedene Pipelines Exercise 10: Eigenschaften der Model-Build-Pipeline Exercise 11: CI/CD-Integration Exercise 12: Modell-Packaging Exercise 13: Modellformate

Aktuelle Übung

Exercise 14: Vollständiges Paket

This chapter deals with critical model operations questions such as: - What are the different ways in which we can serve our models? - What is an API, and what are its key functionalities? - How do we thoroughly test our service before making it available to the end users? - How do we update models in production without service disturbance? You will learn about batch prediction, real-time prediction, input and output data validation, unit testing, integration testing, canary deployment, and much more.

Exercise 1: Serving modes Exercise 2: Offline or online?Exercise 3: When time matters - a bit Exercise 4: Building the API Exercise 5: Client-server Exercise 6: API functionalities Exercise 7: Deployment progression and testing Exercise 8: Which test is it?Exercise 9: Progression through environments Exercise 10: Tests per environment Exercise 11: Model deployment strategies Exercise 12: A fitting deployment strategy Exercise 13: Order of risk Exercise 14: Shadow of the shadow

This final chapter is dedicated to monitoring and maintaining ML services after they are deployed, as well as to model governance. You will cover crucial concepts such as verification latency, covariate shift, concept drift, human-in-the-loop systems, and more.

Exercise 1: Monitoring ML services Exercise 2: Shift vs drift Exercise 3: Latency Exercise 4: Already?Exercise 5: Monitoring and alerting Exercise 6: The monitoring system Exercise 7: Alerting Exercise 8: Model maintenance Exercise 9: Data-centric vs Model-centric Exercise 10: Human-in-the-Loop Exercise 11: Model governance Exercise 12: Elements of governance Exercise 13: Stages of governance Exercise 14: Risk classification Exercise 15: Wrap up