fehimornek/DeepForSpeed

ConvNet learns to play Need For Speed

41
/ 100
Emerging

This project helps AI researchers and students test self-driving car algorithms in a simulated, game-based environment. It takes screen captures from Need For Speed: Most Wanted and controller inputs (steering, acceleration) as data, training a convolutional neural network to drive autonomously. The output is a model that can control a car in the game.

247 stars. No commits in the last 6 months.

Use this if you are an AI student or researcher looking for a fun and accessible platform to experiment with and benchmark different neural network architectures for autonomous driving.

Not ideal if you need a highly accurate, real-world driving simulator or a production-ready autonomous driving solution.

AI research autonomous driving simulation neural network testing reinforcement learning (simulated) computer vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

247

Forks

24

Language

Python

License

GPL-3.0

Last pushed

Mar 19, 2022

Commits (30d)

0

Get this data via API

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

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