A deep learning model created with Tensorflow and Keras + OpenCV to traverse the autonomous track used by Udacity Self-Driving Car Simulator
https://github.com/udacity/self-driving-car-sim
To test this model, clone this repo and use a virtual env(like venv or conda environment)
Install necessary modules by running:
pip install -requirements.txt
or
conda install --file requirements.txt
Run the sim_connect.py (Basic Flask, Socketio WSGL)
Run the simulator and choose autonomous mode
nvidia_model is the src file for nvidia_model
Sample IMG and driving_log files are also uploaded
Also added:
- traffic_signs_classifier for road sign classification
- lanes for lane detection (Hough Transform based)
For traffic_signs_classifier, german-traffic-signs can be used for training/validation