Build Your Own Image Classifier with CNTK (or Tensorflow), Keras and OpenCV

Finally you have decided to get in to AI and trying to learn how to get started. You may have noticed that nearly every “getting started” guide you come across image classification uses either the MNIST or CIFAR-10 datasets which are built into Keras and other deep learning libraries. You just call one of those functions and the data is automatically loaded for you. But, what about if you want to train a models with your own images? In this session, I will go with a different take that will show how to setup your model training environment, build and operationalize your first neural network and Convolutional Neural Network with your custom image dataset.