Facial Expression Recognition using Keras

Keras is a very powerful open source Python library which is runs on top of top of other open source machine libraries like TensorFlow, Theano etc, used for developing and evaluating deep learning models and leverages various optimization techniques. In this project we will implement facial expression recognition using Keras. Our dataset ( already divided into train and test set) consists of images of different facial expressions downloaded from Kaggle repo. In order to make the most of our training examples, we will "augment" them via a no. of random transformations which inturn helps prevent model overfitting and helps the model generalize better. We will be using convnet for this task.