veb-101/keras-vision
Porting vision models to Keras 3 for easily accessibility. Contains MobileViT v1, MobileViT v2, fastvit
This project helps machine learning engineers and researchers quickly integrate advanced computer vision models like MobileViT and FastViT into their Keras 3 projects. It provides pre-ported models and weights, allowing users to leverage these efficient architectures for tasks like image classification without complex setup. The end output is a vision model ready for training or inference within a Keras 3 environment.
No commits in the last 6 months. Available on PyPI.
Use this if you are a machine learning engineer or researcher who wants to use state-of-the-art, efficient vision transformer models within your Keras 3 deep learning workflows.
Not ideal if you are looking for a pre-trained application to solve an out-of-the-box image classification problem without any coding or model integration.
Stars
15
Forks
3
Language
Jupyter Notebook
License
—
Category
Last pushed
Apr 20, 2025
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/veb-101/keras-vision"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
JunkyByte/easy_ViTPose
Easy and fast 2d human and animal multi pose estimation using SOTA ViTPose [Y. Xu et al., 2022]...
vishal-n2403/Unsupervised-Domain-Adaptation-and-ViTs
ViT + MAE for UDA on Sentinel-1/2 (SAR/optical) land-cover classification with CORAL & DANN. PyTorch.
mach-12/vit
(ViT) Vision Image Transformer PyTorch Implementation
ceasedfonts/PicReco
Image Classification using Google ViT, Transformers and Streamlit