https://github.com/soumik12345/vision-transformer

Tensorflow 2.x implementation of Vision-Transformer model
https://github.com/soumik12345/vision-transformer

cifar10 classification image-classification keras tensorflow2 transformer vision-transformer

Last synced: 21 days ago
JSON representation

Tensorflow 2.x implementation of Vision-Transformer model

• Host: GitHub
• URL: https://github.com/soumik12345/vision-transformer
• Owner: soumik12345
• Created: 2020-10-21T05:25:22.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2021-01-29T19:43:49.000Z (over 4 years ago)
• Last Synced: 2025-05-12T13:12:12.324Z (about 2 months ago)
• Topics: cifar10, classification, image-classification, keras, tensorflow2, transformer, vision-transformer
• Language: Python
• Homepage: https://openreview.net/pdf?id=YicbFdNTTy
• Size: 332 KB
• Stars: 19
• Watchers: 1
• Forks: 4
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Vision Transformer

Unofficial Tensorflow 2.x implementation of the Transformer based Image Classification model proposed by the paper [AN IMAGE IS WORTH 16X16 WORDS:

TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE](https://openreview.net/pdf?id=YicbFdNTTy). The paper is currently under double-blind review.

![](./assets/model.png)

GELU implementation has been taken from the latest master branch of [EchoAI](https://github.com/digantamisra98/Echo/).