NVlabs/FasterViT

[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention

54
/ 100
Established

This project provides pre-trained models and code for fast and accurate image analysis. It takes raw image data as input and produces classifications (like what's in the image) or detects specific objects within the image. This is for machine learning engineers or researchers who need to build high-performance computer vision systems.

907 stars. No commits in the last 6 months. Available on PyPI.

Use this if you are developing computer vision applications that require both high accuracy and fast processing of images, such as for object detection or image classification.

Not ideal if you are not working with image-based data or do not have experience with deep learning frameworks like PyTorch.

computer-vision image-classification object-detection deep-learning AI-model-development
Stale 6m
Maintenance 2 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 17 / 25

How are scores calculated?

Stars

907

Forks

69

Language

Python

License

Last pushed

Jul 22, 2025

Commits (30d)

0

Dependencies

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/NVlabs/FasterViT"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.