MLOps
Tracking, versioning and deploying models and the data they depend on, so that a result can still be reproduced months after it was produced.
4 technologies
- Docker infrastructure Packages an application and its dependencies into a portable image.
- Kubernetes infrastructure Orchestrates containers across machines, handling scheduling and recovery.
- Weights & Biases tool Experiment tracking and visualisation for training runs.
- MLflow tool Open platform for tracking experiments and managing model lifecycle.