MNIST Image Dataset
Learn about PyTorch by building an actual neural network that performs a simple but familiar task.
We'll cover the following...
The MNIST dataset
We will develop a neural network that will learn to classify images of hand-written digits.
The MNIST dataset is a well-known set of images often used to measure and compare the performance of machine learning algorithms. It contains 60,000 images to be used for training a machine learning model, and 10,000 images for testing its performance.
The images are 28 by 28 pixels in size, and are monochrome, not colour. The pixels have a numerical value for how light or dark that pixel is and, depending on where you get the data from, the values will be in the range 0 - 255.
A look at the data
It is a good habit to explore any new data to get a feel for it before we attack it with tools and algorithms!
The MNIST data folder mnist_data contains the following files:
- The