Running the Latest YOLO v10 Model on Different Hardware
Computer vision can be an important part of ML apps of different scales, from $20,000 Tesla Bots or self-driving cars to smart doorbells and vacuum cleaners. It is also a challenging task because, compared to a cloud infrastructure, on “real” edge devices, the hardware specs are often much more constrained.
YOLO (You Only Look Once) is a popular object detection library; its first version was made in 2015. YOLO is particularly interesting for embedded devices because it can run almost anywhere; there are not only Python but also C++ (ONNX and OpenVINO) and Rust versions available. A year ago, I tested YOLO v8 on a Raspberry Pi 4. Nowadays, many things have changed — a new Raspberry Pi 5 became available, and a newer YOLO v10 was released. So I expect a new model on new hardware to work faster and more precisely.
The code presented in this article is cross-platform, so readers who don’t have a Raspberry Pi can run it on a Windows, Linux, or OS X computer as well.
Without further ado, let’s see how it works!
Raspberry Pi
For someone who may have never heard about the Raspberry Pi, let’s make a short…