Home Projects probing-vits
probing-vits
Jupyter Notebook

probing-vits

Probing the representations of Vision Transformers.

by sayakpaul · GitHub
Stars
Forks
License
Created
Last commit
Category
attentionexplaining-vitsimage-recognitionApache-2.0Jupyter Notebook
View on GitHub
In plain words

Explore and analyze how Vision Transformers learn to recognize images with provided tools and resources.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
probing-vits — GitHub preview card
📈 Star history
342341
2026-07-202026-08-31
📈 Track probing-vits

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Probing the representations of Vision Transformers.

probing-vits has 341 stars on GitHub. It has been forked 22 times. probing-vits is written mainly in Jupyter Notebook. It has been in active development since 2022. probing-vits is available under the Apache-2.0 license. Its main topics are attention, explaining-vits, image-recognition, keras.

Frequently asked questions

What is probing-vits?

Probing the representations of Vision Transformers.

Is probing-vits open source?

probing-vits is an open-source project. It is released under the Apache-2.0 license.

Is probing-vits free?

Yes. probing-vits is free and open source — you can use, modify and self-host it.

What license does probing-vits use?

probing-vits is available under the Apache-2.0 license.

What language is probing-vits written in?

probing-vits is written mainly in Jupyter Notebook.

🏅 Maintainer of this project?
olud.ai badge — probing-vits

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=sayakpaul-probing-vits)](https://olud.ai/project/sayakpaul-probing-vits.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.