# Vision Transformer (ViT) and Data-Efficient Image Transformer (DEIT)

**DISCLAIMER**: This implementation is still under development. No support will
be provided during the development phase.

- [![ViT Paper](http://img.shields.io/badge/Paper-arXiv.2010.11929-B3181B?logo=arXiv)](https://arxiv.org/abs/2010.11929)
- [![DEIT Paper](http://img.shields.io/badge/Paper-arXiv.2012.12877-B3181B?logo=arXiv)](https://arxiv.org/abs/2012.12877)

This repository is the implementations of Vision Transformer (ViT) and
Data-Efficient Image Transformer (DEIT) in TensorFlow 2.

* Paper title:
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/pdf/2010.11929.pdf).
- [Training data-efficient image transformers & distillation through attention](https://arxiv.org/pdf/2012.12877.pdf).