Reading: the comparison is fair only if the data and the budget are controlled. The trap is attributing to the CNN a gain that comes from an augmentation or a longer training not granted to the baseline.
Goal: compare MLP and convolution on Fashion-MNIST. Duration: 4 hours.
Fashion-MNIST contains grayscale 28×28 images, spread across ten clothing
categories. The initial download requires Internet through torchvision.
Preview — the rest of the lesson is for enrolled readers.
Your access is tied to your account, not to this link. Sign in with the same email you used in class: your course is waiting, no need to enter the code again.
Sign inNo account yet? Create oneThe first modules of the course are open to everyone. For the rest you have three options: buy this course once and for all, subscribe, or enter the code handed out in class.