This repository creates a convolutional neural network using pytorch to perform classification on the MNIST dataset. The MNIST dataset contains 60,000 images in the training set and 10,000 images in the test set. Each image is a 28x28 grayscale image of a handwritten digit 0-9. The program can run the network on an individual image, display the image, and the networks prediction. The network can achieve over 99% accuracy with the hyperparameters currently set, running 10 epochs with batch sizes of 100. Below you can see a sample output of a random handwritten digit and the networks prediction.
