Module 2 · MLOps: Deploying Machine Learning & Deep Learning Models
Packaging and Serving Models: lessons
From notebook to service: saving models, an API with FastAPI, and reproducible Docker containers.
3 lessons · 48 min
What this module teaches, what it asks of you first and how you practise it are on its syllabus page.
Open the syllabusSaving Models Reproducibly
14 minArtefacts, dependency versions, and why `model.pkl` alone is not enough to load the same model three months later.
Included with the trackA Model API with FastAPI
18 minA prediction endpoint with input validation, a health check and the model version in every response — a service other teams can call without knowing what scikit-learn is.
Included with the trackContainerising with Docker
16 minAn image that is small, fast to rebuild, and runs exactly the same on a laptop, in CI and on a server — because the environment ships with the code.
Included with the track