Skip to content
Quick navigationFind a place or open a tool
All labs Vision AI lab

All labs ยท ๐Ÿ‘๏ธ Vision AI lab

How vision AI works: transformers, YOLO, ReID & tracking

Look inside the models behind self-driving cars and smart cameras. Watch attention light up inside a transformer, step through how YOLO finds objects in one pass, compare YOLO versions from v1 to YOLO26, see how a ReID model recognises the same person on another camera โ€“ and how all of it joins up into a tracker. Then code each piece yourself in Python.

๐Ÿ‘‹ Free demo: try the first 2 lessons and the first tool. Subscribe to unlock everything here and in all the other labs โ€“ USD 10 a month (USD 100 a year), or included with lessons. โœจ SubscribeLog in

Activity workspace

Pick an activity. Its mission, controls and live result stay together.

My saved work

โ–ถ See it working

๐Ÿ‘๏ธ Vision AI lab โ€“ See inside transformers, YOLO (v1 to YOLO26), ReID and tracking: attention you can hover, NMS step by step, a live tracker โ€“ then code each piece in Python.