Diffusion Models - Live Coding Tutorial 2.0 смотреть онлайн

Edit: The previous video was not very readable in terms of code visibility. This one is for all of the viewers who had difficulty with the tiny font in the previous video. Same content, and better readability.

This is my live (to the most extent) coding video, where I implement from a scratch a diffusion model that generates 32 x 32 RGB images. The tutorial assumes a basic knowledge of deep learning and Python.

Links:
- The Jupiter notebook built in this video: https://github.com/dtransposed/code_videos/blob/main/Diffusion%20Model.ipynb
- My website: https://dtransposed.github.io
- My Twitter: https://twitter.com/dtransposed

Sources:
- Lil' Log - What are Diffusion Models: https://lilianweng.github.io/posts/2021-07-11-diffusion-models/
- Understanding Diffusion Models: A Unified Perspective: https://arxiv.org/abs/2208.11970
- Denoising Diffusion Probabilistic Models: https://arxiv.org/abs/2006.11239

Timestamps:
0:00 Introduction
0:32 Theoretical background
13:13 Live Coding - Forward diffusion
41:29 Live Coding - Training loop
1:00:05 - Live Coding - Overfitting one batch
1:03:36 - Live Coding - Reverse diffusion
1:13:40 - Live Coding - Training on CIFAR - 10 dataset
1:17:24 - Live Coding - Result evaluation
1:19:40 - (Bonus) Quick explanation of the UNet architecture used in the tutorial