This code utilises the data collected using car simulator to train a CNN model to learn to auto drive a car on the track
You can install all dependencies by running one of the following commands
You need a anaconda or miniconda to use the environment setting.
conda env create -f environments.ymlVisit This Kaggle Notebook and modify the code accordingly
-
Run the car simulator in autonomous mode
-
Test one of the models by running the the script:
python drive.py <path to model_file>
#Example
python drive.py models/model_50000.
├── car-simulator.ipynb
├── car_simulator.py
├── Data
│ └── driving_log.csv
├── drive.py
├── environments.yml
├── models
│ ├── model_0
| .
| .
│ └── model_195000
└── README.md
Credits to the paper 'End to End Learning for Self-Driving Cars' from Bojarski et al.