Teaching a neural network to steer a car directly from what a camera sees.
| 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 |
Step 1 — Clone the repository
git clone https://github.com/JayeshJadhav28/DeepDrive.git
cd DeepDriveStep 2 — Create & activate an environment
conda create -n deepdrive python=3.7 -y
conda activate deepdriveStep 3 — Install the requirements
pip install -r requirements.txtStep 4 — Pin engineio (simulator compatibility)
pip install python-engineio==3.13.2Step 5 — Pin socketio (simulator compatibility)
pip install python-socketio==4.2.1Step 6 — Start driving
python drive.pyJayesh Jadhav jayeshjadhav.com
