Introduction to CNNs Without using MNIST!

The MNIST dataset is the most overused dataset for getting started with image classification. MNIST dataset comprising of 10-class handwritten digits introduced by Yann LeCun in 1998 come up over and over again, in scientific papers, blog posts, and so on. It contains 28 28 (also 32x32) grayscale images of handwritten digits, each with integers between 0 and 9. The reason MNIST is so popular has to do with its size, allowing deep learning practitioners to quickly check, train, and publish their algorithms. There are certain variations and limitations of MNIST.