search

google-research / big_vision

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.
Apache License 2.0
2.2k stars 147 forks source link

Adds "LiT: Zero-Shot Transfer with Locked-image text Tuning". #6

Closed andsteing closed 2 years ago

andsteing commented 2 years ago

Paper: https://arxiv.org/abs/2111.07991

Co-authored-by: Alexander Kolesnikov akolesnikov@google.com Co-authored-by: Lucas Beyer lbeyer@google.com Co-authored-by: Xiaohua Zhai xzhai@google.com

google-cla[bot] commented 2 years ago

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

andsteing commented 2 years ago

Previewing the README

https://github.com/andsteing/big_vision/blob/lit/big_vision/configs/proj/image_text/README.md

Testing the Colab

https://colab.research.google.com/github/andsteing/big_vision/blob/lit/big_vision/configs/proj/image_text/lit.ipynb

and then modify 

!git clone --branch=main --depth=1 https://github.com/google-research/big_vision

to

!git clone --branch=lit --depth=1 https://github.com/andsteing/big_vision