Working with Images & Logistic Regression in PyTorch

This tutorial covers the following topics:

Working with images in PyTorch (using the MNIST dataset)
Splitting a dataset into training, validation, and test sets
Creating PyTorch models with custom logic by extending the nn.Module class
Interpreting model outputs as probabilities using Softmax and picking predicted labels
Picking a useful evaluation metric (accuracy) and loss function (cross-entropy) for classification problems
Setting up a training loop that also evaluates the model using the validation set
Testing the model manually on randomly picked examples
Saving and loading model checkpoints to avoid retraining from scratch

import jovian

jovian.commit(project='03-logistic-regression')

Working with Images

In this tutorial, we'll use our existing knowledge of PyTorch and linear regression to solve a very different kind of problem: image classification. We'll use the famous MNIST Handwritten Digits Database as our training dataset. It consists of 28px by 28px grayscale images of handwritten digits (0 to 9) and labels for each image indicating which digit it represents. Here are some sample images from the dataset:

mnist-sample