Udacity Machine Learning Engineer Nanodegree, Capstone Project
This project focuses on using deep learning to enable traffic sign recognition without internet connectivity on a mobile device.
The following libraries are required to run the notebooks (Python 3.5)
- Tensorflow
- Keras
- OpenCV
- Numpy
- sklearn
- Matplotlib
- PIL
- Pandas
- Pickle
The dataset can be obtained from here.
- Extract the zip file into the root folder, i.e the GTSRB folder should be in the same directory as the notebooks.
The android project requires the OpenCV-android-sdk to be present in the same directory that contains the project folder. The OpenCV-android-sdk can be downloaded from here
If there is a problem building the project and you just want to use the APK, it can be obtained from here