A simple solution for monitoring ML systems.

A simple solution for monitoring ML systems.

A simple solution for monitoring ML systems.

“This blog post aims to provide a simple, open-source solution for monitoring ML systems. We’ll discuss industry-standard monitoring tools and practices for software systems and how they can be adapted to monitor ML systems. To illustrate this, we’ll use a scikit-learn model trained on the UCI Wine Quality dataset and served via FastAPI (see Github repo here). We’ll collect metrics from the server using Prometheus and visualize the results in a Grafana dashboard. All of the services will be deployed on a Kubernetes cluster; if you’re not familiar with Kubernetes, feel free to take a quick read through my introduction to Kubernetes blog post.

Source: www.jeremyjordan.me/ml-monitoring/