lanl / vision_transformers_explained

This folder of code contains code and notebooks to supplement the "Vision Transformers Explained" series published on Towards Data Science written by Skylar Callis.

Vision Transformers Explained

This folder of code contains code and notebooks to supplement the Vision Transformers Explained series written by Skylar Callis for Towards Data Science. These articles can be read on Medium or in their equivalent Jupyter Notebook:

• Vision Transformers, Explained
  • Jupyter Notebook
• Attention for Vision Transformers, Explained
  • Jupyter Notebook
• Position Embeddings for Vision Transformers, Explained
  • Jupyter Notebook
• Tokens-to-Token Vision Transformers, Explained
  • Jupyter Notebook

This project were developed by Skylar Callis while working as a post-bachelors student at Los Alamos National Laboratory (LANL) from 2022 - 2024. To see what they are up to these days, visit Skylar's Website .

The Vision Transformers Explained code has been approved by LANL for a BSD-3 open source license under O#4693. The written components have been approved for release as LA-UR-23–33876.

The GitHub page for this code can be found here.