Practical AI for the Raspberry Pi

EE292D Edge ML is a ten week Stanford class focused on running machine learning on edge devices. We're using Raspberry Pi 5 boards as our standard platform, and we teach you how to run vision, audio, and large language models locally, with no cloud connection (or charges). No prior knowledge of ML or programming is required.

We aim to make the lab assignments for this class as accessible as possible, so we're open sourcing all the code and documentation. If you want to learn how to run these models on a Pi yourself, here are links to the lab instructions:

• Lab 0: Set up your Raspberry Pi
• Lab 1: Run a Large Language Model
• Lab 2: Classify Images
• Lab 3: Locate People and Objects
• Lab 4: Understand Speech
• Lab 5: Translate Languages
• Lab 6: Train a Large Language Model

Fork Me!

I recommend forking this project on GitHub as the first step, so you have your own copy of the code and can save any changes you end up making.