Run object detection with Arm Runtime for YOLO26 on Raspberry Pi 5
Introduction
Run your first object detection with YOLO26n
Understand the runtime and example code
Compare with a general purpose runtime
Next Steps
Run object detection with Arm Runtime for YOLO26 on Raspberry Pi 5
Who is this for?
Python developers who want to run object detection on Raspberry Pi 5 and understand how and why to use the custom, optimized Arm runtime for YOLO26.
What will you learn?
After completing this Learning Path, you'll be able to perform the following tasks:
- Run YOLO26n detection on Raspberry Pi 5 using the custom Arm Runtime.
- Explain how the Python example loads and calls the custom runtime.
- Understand how the runtime works, and how it differs from general purpose runtimes.
- Export YOLO26n to NCNN and compare inference latency.
Prerequisites
Before starting, you'll need the following prerequisites:
- A Raspberry Pi 5 running 64-bit Raspberry Pi OS Trixie with Python 3.13
- Basic Python and Linux command-line knowledge
- Basic familiarity with object detection and YOLO
Summary
This summary was drafted with an approved AI-assisted workflow and reviewed by Arm contributors before publication. Human technical review remains part of the process so the final page reflects engineering rigor, accuracy, and Arm editorial standards.
You’ll run YOLO26n detection on Raspberry Pi 5 with Arm Runtime, inspect its Python example, and compare CPU inference with NCNN. You’ll start with the supplied video. Then, you’ll inspect how runtime setup loads converted weights and prepares XNNPACK operations for reuse across frames. Finally, you’ll export the checkpoint to NCNN and compare latency with the same dataset, input size, batch, and system conditions.