https://github.com/kamalkraj/vision-transformer

Vision Transformer using TensorFlow 2.0
https://github.com/kamalkraj/vision-transformer

image-classification tensorflow transformer vit

Last synced: 8 days ago
JSON representation

Vision Transformer using TensorFlow 2.0

• Host: GitHub
• URL: https://github.com/kamalkraj/vision-transformer
• Owner: kamalkraj
• License: apache-2.0
• Created: 2020-10-06T11:03:50.000Z (about 4 years ago)
• Default Branch: main
• Last Pushed: 2020-10-07T08:01:58.000Z (about 4 years ago)
• Last Synced: 2023-03-03T03:12:12.271Z (over 1 year ago)
• Topics: image-classification, tensorflow, transformer, vit
• Language: Python
• Homepage: https://openreview.net/forum?id=YicbFdNTTy
• Size: 161 KB
• Stars: 90
• Watchers: 4
• Forks: 20
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Vision Transformer



## [Abstract](https://openreview.net/forum?id=YicbFdNTTy)

Abstract: While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional networks, or used to replace certain components of convolutional networks while keeping their overall structure in place. We show that this reliance on CNNs is not necessary and a pure transformer can perform very well on image classification tasks when applied directly to sequences of image patches. When pre-trained on large amounts of data and transferred to multiple recognition benchmarks (ImageNet, CIFAR-100, VTAB, etc), Vision Transformer attains excellent results compared to state-of-the-art convolutional networks while requiring substantially fewer computational resources to train.

Vision Transformer implemented using TF 2.0.

example usage can found in `cifar.ipynb`

PyTorch version [here](https://github.com/lucidrains/vit-pytorch) 

## Citations

```bibtex

@inproceedings{

    anonymous2021an,

    title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},

    author={Anonymous},

    booktitle={Submitted to International Conference on Learning Representations},

    year={2021},

    url={https://openreview.net/forum?id=YicbFdNTTy},

    note={under review}

}