What it does
YOLOv3 is a well-known "object detection" model. It looks at an image or video frame and draws boxes around the things it recognises, each with a label. It can work on photos, videos, webcams, screenshots and live streams.
This project packages three versions of the model with tools to train it on your own pictures, test how accurate it is and convert it to other formats for phones and other devices.
Who it's for
Developers and students working on computer vision projects.
Can I use it without coding?
Developers only. You run it with Python commands or code. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Computer
- Works best on a powerful computer or one with a graphics card (GPU)
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (AGPL-3.0): Free to use; if you run a changed version as an online service, you must share your source code.
- More on staying safe