Skip to content

Latest commit

 

History

2 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DeepDrive

End-to-End Autonomous Driving with a CNN

Teaching a neural network to steer a car directly from what a camera sees.

Python TensorFlow OpenCV Unity License

Dataset Google Colab Research Paper Medium Developer


DeepDrive autonomous driving demo

Trained CNN steering the vehicle around the simulator track in real time.


Project Links

Resource Link
Dataset Google Drive folder
Training Notebook Open in Colab
NVIDIA DAVE-2 Paper arXiv:1604.07316
Full Write-Up (Medium) I Built a Self-Driving Car With a CNN
Developer jayeshjadhav.com

Installation

Step 1 — Clone the repository

git clone https://github.com/JayeshJadhav28/DeepDrive.git
cd DeepDrive

Step 2 — Create & activate an environment

conda create -n deepdrive python=3.7 -y
conda activate deepdrive

Step 3 — Install the requirements

pip install -r requirements.txt

Step 4 — Pin engineio (simulator compatibility)

pip install python-engineio==3.13.2

Step 5 — Pin socketio (simulator compatibility)

pip install python-socketio==4.2.1

Step 6 — Start driving

python drive.py

Author

Jayesh Jadhav jayeshjadhav.com

About

An end-to-end autonomous driving system that uses a Convolutional Neural Network (CNN) to predict steering commands from camera images and control a car in the Udacity Self-Driving Car Simulator. Inspired by NVIDIA's DAVE-2 architecture.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages