Oleffa/LeagueAI

LeagueAI software framework for League of Legends that provides information about the state of the game based on Image Recognition using OpenCV and Pytorch.

49
/ 100
Emerging

Implements YOLOv3 object detection trained on synthetically generated datasets created by extracting 3D models from the League client and compositing them onto in-game screenshots with domain randomization. Automatically generates labeled training data by combining masked object PNGs with real map backgrounds, enabling scalable dataset creation without manual annotation. Detects game entities (champions, minions, towers) to feed a vision-based agent that plays with human-equivalent input constraints.

242 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

242

Forks

66

Language

TeX

License

GPL-3.0

Last pushed

Nov 26, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Oleffa/LeagueAI"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.