https://github.com/fehimornek/DeepForSpeed

ConvNet learns to play Need For Speed
https://github.com/fehimornek/DeepForSpeed

convolutional-neural-networks deep-learning neural-network self-driving-car

Last synced: 7 months ago
JSON representation

ConvNet learns to play Need For Speed

• Host: GitHub
• URL: https://github.com/fehimornek/DeepForSpeed
• Owner: fehimornek
• License: gpl-3.0
• Created: 2022-01-09T20:45:07.000Z (over 3 years ago)
• Default Branch: master
• Last Pushed: 2022-03-19T10:07:20.000Z (about 3 years ago)
• Last Synced: 2024-11-08T07:03:27.645Z (7 months ago)
• Topics: convolutional-neural-networks, deep-learning, neural-network, self-driving-car
• Language: Python
• Homepage:
• Size: 3.84 MB
• Stars: 248
• Watchers: 7
• Forks: 27
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.txt

Awesome Lists containing this project

README

        
# DeepForSpeed: Data Wanted

## A self-driving car in Need For Speed

The inspiration comes from how Nvidia built a self-driving car with just a single convolutional

neural network instead of many fancy algorithms combined. Here my goal is to replicate 

the amazing results they've gotten but inside a game. But i also tried to create it as a platform/interface 

in which different architectures can be tested relatively easily, so it can also be used as a benchmark.

So it's like a fun driving simulator (of course not an accurate one) that you can test your own neural networks 

at and maybe conduct some experiments.

## Watch The Latest Version

[![Watch the video](https://img.youtube.com/vi/t0iqfM36mRc/maxresdefault.jpg)](https://youtu.be/t0iqfM36mRc)

note: this is a cherry picked example and many times model will not perform this well. Im hoping to change that in future versions.

## Things used

> Python 3.9

> 

> Pytorch 1.10

>

> Numpy

> 

> OpenCV

> 

> Matplotlib

> 

> Need For Speed: Most Wanted 2005

> 

> Base architecture

> 

> 

## How to use it

There is different ways to use it depending on what you want. Additional info can be found inside the scripts.

Creating and processing data



Using models



## Pull requests

TLDR: Basically any improvements are really appreciated.

- Other Neural Network architectures

- Refinements in the code

- Trained Models

- Anything you can get done on future updates part

## For Future Updates:

- Add tensorflow board

- Only use np arrays instead of both lists and np arrays in data

- RGB images instead of gray images

- Train on more data

- Increase data resolution

- Controller or a steering wheel to get the input

- Different activation functions

- Try Weight Decay

- Add merging data function for easing data creation

- Save models whilst training

### References:

paper by nvidia: https://images.nvidia.com/content/tegra/automotive/images/2016/solutions/pdf/end-to-end-dl-using-px.pdf

Sentdex's PyGta5 playlist: https://www.youtube.com/watch?v=ks4MPfMq8aQ&list=PLQVvvaa0QuDeETZEOy4VdocT7TOjfSA8a

NFS:MW mods are taken from:  https://github.com/ExOptsTeam/NFSMWExOpts