Coding a Diffusion Model from Scratch: Filippo Maria Bianchi (UiT The Arctic University of Norway)

Filippo Maria Bianchi, an associate professor at UiT The Arctic University of Norway, provided a tutorial for the NLDL 2024 winter school (13 Jan 2024).


Abstract:

Renowned for their exceptional capabilities in synthesizing realistic images, audio, and video, DDPMs have marked a new era in generative modeling. In this introductory tutorial, we will dive into the world of Denoising Diffusion Probabilistic Models (DDPM) by unraveling the theory behind these groundbreaking generative models. In particular, we will closely look at the vanilla DDPM by implementing it from scratch using Pytorch and then using it to generate images from the popular Fashion MNIST dataset. At the end of the tutorial, you will have gained a robust understanding of DDPMs and also acquired the practical skills to build and apply these models to real data.