https://github.com/veb-101/keras-vision
Porting vision models to Keras 3 for easily accessibility. Contains MobileViT v1, MobileViT v2, fastvit
https://github.com/veb-101/keras-vision
cnn computer-vision deep-learning fastvit jax keras keras3 mobilevit mobilevitv1 mobilevitv2 pytorch self-attention tensorflow transformers
Last synced: 2 days ago
JSON representation
Porting vision models to Keras 3 for easily accessibility. Contains MobileViT v1, MobileViT v2, fastvit
- Host: GitHub
- URL: https://github.com/veb-101/keras-vision
- Owner: veb-101
- Created: 2024-04-07T16:04:51.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-04-20T16:12:27.000Z (6 months ago)
- Last Synced: 2025-09-07T08:21:32.230Z (about 1 month ago)
- Topics: cnn, computer-vision, deep-learning, fastvit, jax, keras, keras3, mobilevit, mobilevitv1, mobilevitv2, pytorch, self-attention, tensorflow, transformers
- Language: Jupyter Notebook
- Homepage:
- Size: 4.45 MB
- Stars: 14
- Watchers: 4
- Forks: 3
- Open Issues: 1
-
Metadata Files:
- Readme: Readme.md
Awesome Lists containing this project
README
[](https://www.python.org/) [](https://badge.fury.io/py/keras-vision) [](https://github.com/keras-team/keras/releases) 
Porting all models from everywhere to Keras to leverage multi-backend support.
Cause why not?🤷🏻♂️
# Table of Contents
- [Table of Contents](#table-of-contents)
- [Progress](#progress)
- [Updates](#updates)
- [Quick Setup](#quick-setup)
- [Stable PyPi Package](#stable-pypi-package)
- [OR](#or)
- [Latest Git Updates](#latest-git-updates)
- [Models Supported](#models-supported)
## Progress
- Working on adding MobileNet V4
## Updates
1. [2025-03-12] Finished adding **FastViT** image classification model by Apple added. The model weights are available at [url](https://huggingface.co/veb-101/apple-fastvit-Keras-3/tree/main).
2. [2025-02-22] Working (v1) FastViT classification code added.
3. [2024-06-24] Released MobileViT v2 - All Image Classification variants.
4. [2024-05-15] Fixed MobileViT v1 - Now works will all 3 backends. 🎉🎉
5. [2024-05-04] Converted MobileViT to Keras 3 and released weights of all 3 variants.
1. Jax backend currently not working, I'm working on a fix.
2. Release:
## Quick Setup
### Stable PyPi Package
```bash
pip install -U keras-vision
```
### OR
### Latest Git Updates
```bash
pip install git+https://github.com/veb-101/keras-vision.git
```
## Models Supported
# No.
Models
Paper
Additional Materials
Example notebook
Weights URL
1
MobileViT-V1
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
Blogpost: Building MobileViT In Keras 3
Colab link
🤗
2
MobileViT-V2
Separable Self-attention for Mobile Vision Transformers
--
Colab link
🤗
2
FastViT
FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization
--
Colab link
🤗
## Citation
* MobileViT-v1
```
@inproceedings{mehta2022mobilevit,
title={MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer},
author={Sachin Mehta and Mohammad Rastegari},
booktitle={International Conference on Learning Representations},
year={2022}
}
```
* MobileViT-v2
```
Mehta, S., & Rastegari, M. (2022). Separable Self-attention for Mobile Vision Transformers. ArXiv. https://arxiv.org/abs/2206.02680
```
* FastViT
```
@inproceedings{vasufastvit2023,
author = {Pavan Kumar Anasosalu Vasu and James Gabriel and Jeff Zhu and Oncel Tuzel and Anurag Ranjan},
title = {FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization},
booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
year = {2023}
}
```