I wanted to learn how to Convolutional Neural Networks worked, so I created my own model to classify images from the CIFAR-10 dataset. I attempted to document my learning progress, so maybe others may find this useful. I thought the most useful part of this exercise was learning how to load data (without crashing my computer) and apply transforms to the data without using PyTorch’s built-in DataLoader. You can find my all my code here!
Ultimately, I was able to achieve 88% test accuracy, which is pretty close to the human accuracy benchmark of ~94%!