Custom Layers in Keras

Keras is a very powerful open source Python library which 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. There are many in-built layers in Keras like Conv2D, MaxPooling2D, Dense, Flatten etc for different use cases and applications. In this project we are going to create custom(Parametric ReLU) layer and use it in the NN model to solve a multi classification problem (We will be using MNIST dataset) . We will be using the popular MNIST dataset. We will load the data using utils and then visualize it.