microsoft / computervision-recipes

Best Practices, code samples, and documentation for Computer Vision.
MIT License
9.55k stars 1.18k forks source link

[FEATURE_REQUEST] Add vision transformers model to image classification #678

Open kbjiang opened 2 years ago

kbjiang commented 2 years ago

Description

The transformer-based image classification model is becoming popular. It will be nice to include it in this repo.

Expected behavior with the suggested feature

Other Comments

ShreyasJoshi7 commented 9 months ago

@kbjiang I have created a PR which demonstrates the inference of transformer-based image classification using DeiT. I would appreciate if you could have a look at it. Let me know if you need more things to be added to it. This is the link to the PR Cheers!