Home BlogDataset Training AI to Analyze Esports

Training AI to Analyze Esports

by Joshua New

Data scientist Farzain Majeed has published an algorithm called DeepLeague, and a training dataset, capable of watching footage of the video game League of Legends and tracking player movements, similar to how sports analytics systems would convert player actions on the field to data. The dataset consists of 100,000 labeled images Majeed generated of League of Legends characters moving around the game map. Majeed made DeepLeague and its data freely available as open source to encourage the development of analytics systems for esports.

Get the data.

You may also like

Show Buttons
Hide Buttons