DeepLeague

Visit Tool

DeepLeague is an Open Source Coding & Development tool that leverages computer vision and deep learning on the League of Legends mini-map. It uses a dataset of over 100,000 labeled images to advance AI research within esports.

Claim this tool

No Views Yet

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is DeepLeague?

DeepLeague is an open-source project that applies computer vision and deep learning techniques to the popular game League of Legends. It focuses on analyzing the game's mini-map using a substantial dataset of over 100,000 labeled images, aiming to further AI research in the esports domain. The tool provides a framework for setting up and running analyses, primarily through a command-line interface that can process YouTube links, local MP4 files, or directories of images. It's designed for technical users familiar with Python, Conda, and Git, offering a platform for experimenting with AI models for game analysis and strategy. While the code was developed rapidly, it serves as a functional base for those interested in esports AI.

Best used for

Ideal for data scientists and developers who need to analyze League of Legends gameplay, conduct AI research in esports, and process game video data. Especially valuable for those looking to experiment with computer vision and deep learning models on a specific game context.

Common actions

analyze game data

research esports AI

process video data

apply computer vision

low-code/no-codeopen-sourcedeepfakecollaborationautomated workflowworkflowsface swappinggithub copilot"AI Agents"

Capabilities

Key features

Computer vision
Deep learning
League of Legends mini-map analysis
100,000+ labeled images dataset
VOD analysis
YouTube link processing
Local MP4 processing

Target Audience

data scientistdevelopergamer

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What are the system requirements to run DeepLeague?

DeepLeague requires Git, Conda, and Brew for setup, and has been confirmed to work on Mac OS, Linux (Ubuntu 16.04), and Windows 10 via a Linux subsystem. It also requires Python 3.6 and specific libraries like OpenCV, TensorFlow, and Keras.

What kind of video input does DeepLeague support for analysis?

DeepLeague can analyze League of Legends gameplay from various sources. It supports YouTube links, local MP4 video files, and directories containing images. For optimal results, it's crucial that the video input is 1080p, as the mini-map cropping and training are based on this resolution.

Is there a dataset available for DeepLeague, and how can I access it?

Yes, DeepLeague provides a dataset of over 100,000 labeled images, split into training, testing, and validation sets. This dataset, totaling 30GB, can be downloaded via a wget link. It contains cropped mini-map frames and bounding box information for AI research.

Trending

Subcategories trending in Coding & Development

Open Source & Models Code Assistants DevOps & Infrastructure No-Code / Low-Code Testing & QA Backend & APIs

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce