keras-vision

Building Vision models in Keras3 for framework-agnostic training and inference.


Keywords
keras3, tensorflow, Jax, PyTorch, Vision, cnn, computer-vision, deep-learning, keras, mobilevit, self-attention, transformers
License
Apache-2.0
Install
pip install keras-vision==0.1

Documentation

PyPI - Python Version PyPI version Keras PyPI - Downloads

Porting all models from everywhere to Keras to leverage multi-backend support.

Cause why not?🤷🏻‍♂️

Table of Contents

Progress

  • Working on adding MobileNet V4

Updates

  1. [2024-06-24] Released MobileViT v2 - All Image Classification variants.
  2. [2024-05-15] Fixed MobileViT v1 - Now works will all 3 backends. 🎉🎉
  3. [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: https://github.com/veb-101/keras-vision/releases/tag/v0.4

Quick Setup

Stable PyPi Package

pip install -U keras-vision

OR

Latest Git Updates

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 Releases v0.4
1 MobileViT-V2 Separable Self-attention for Mobile Vision Transformers -- Colab link Releases v0.5