Classifying vehicles from images is a difficult problem in Computer Science. This project attempts to create an app that leverages GoogleNet's successful neural network to identify makes and models of various automobiles using the device's camera. It explores the process of collecting training data, modifying an open sourced neural network model to produce a pipeline for training, and exporting a trained model in such a way that it can be used on a mobile device to classify cars in real time using Tensorflow's APIs.