What it does
YOLOv5 is a computer-vision model, AI that understands images. Its main job is "object detection": finding things in a picture or video and drawing a box around each one with a label. It can also outline the exact shape of objects and sort whole images into categories.
It runs on images, videos, webcams, screen captures and live streams. Its makers describe it as fast, accurate and easy to use, and it comes in several sizes, from small and quick to large and more accurate.
You can also train it on your own pictures to recognise new kinds of objects, and export it to run on phones and other devices. Its makers now point new users to their newer Ultralytics YOLO models.
Who it's for
Developers, researchers and students working on projects that need a computer to recognise things in images.
Can I use it without coding?
Developers only. Needs Python and command-line use, plus a good graphics card for training. New to this? Start here.
Can I run it?
- Cost
- Free, with optional paid extrasThe open-source version is free; the makers also sell a hosted or pro version.
- 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