https://github.com/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.
https://github.com/lanl/vision_transformers_explained
Last synced: 8 months ago
JSON representation
This folder of code contains code and notebooks to supplement the "Vision Transformers Explained" series published on Towards Data Science written by Skylar Callis.
- Host: GitHub
- URL: https://github.com/lanl/vision_transformers_explained
- Owner: lanl
- License: other
- Created: 2024-01-24T20:18:44.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-05-09T23:53:28.000Z (about 2 years ago)
- Last Synced: 2024-06-27T00:19:17.255Z (almost 2 years ago)
- Language: Jupyter Notebook
- Homepage:
- Size: 46.9 MB
- Stars: 45
- Watchers: 5
- Forks: 11
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE.txt
- Citation: CITATION.cff
Awesome Lists containing this project
README
[//]: <> (THIS IS A MARKDOWN FILE, VIEW IN A MARKDOWN VIEWER OR CONVERT)
# 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*](https://towardsdatascience.com/). These articles can be read on Medium or in their equivalent Jupyter Notebook:
- [Vision Transformers, Explained](https://towardsdatascience.com/vision-transformers-explained-a9d07147e4c8)
- [Jupyter Notebook](https://github.com/lanl/vision_transformers_explained/blob/main/notebooks/VisionTransformersExplained.ipynb)
- [Attention for Vision Transformers, Explained](https://towardsdatascience.com/attention-for-vision-transformers-explained-70f83984c673)
- [Jupyter Notebook](https://github.com/lanl/vision_transformers_explained/blob/main/notebooks/AttentionExplained.ipynb)
- [Position Embeddings for Vision Transformers, Explained](https://towardsdatascience.com/position-embeddings-for-vision-transformers-explained-a6f9add341d5)
- [Jupyter Notebook](https://github.com/lanl/vision_transformers_explained/blob/main/notebooks/PositionEmbeddingExplained.ipynb)
- [Tokens-to-Token Vision Transformers, Explained](https://towardsdatascience.com/tokens-to-token-vision-transformers-explained-2fa4e2002daa)
- [Jupyter Notebook](https://github.com/lanl/vision_transformers_explained/blob/main/notebooks/TokensToTokenViTExplained.ipynb)
This project were developed by **Skylar Callis** while working as a post-bachelors student at [Los Alamos National Laboratory (LANL)](https://www.lanl.gov/?source=globalheader) from 2022 - 2024. To see what they are up to these days, visit [Skylar's Website ](https://skylar-jean.com).
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](https://github.com/lanl/vision_transformers_explained).