YifanXu74/Evo-ViT
Official implement of Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer
This project offers an optimized approach for accelerating image classification tasks using Vision Transformers. It takes a collection of images, such as those from the ImageNet dataset, and processes them to quickly identify and categorize the objects or scenes within them. The primary users are researchers or practitioners working on computer vision applications who need faster image processing without sacrificing accuracy.
No commits in the last 6 months.
Use this if you are a machine learning researcher or engineer building computer vision models and need to speed up image classification or object recognition without re-training.
Not ideal if you are a business user looking for a ready-to-use image classification product or a software developer needing a general-purpose image manipulation library.
Stars
74
Forks
6
Language
Python
License
MIT
Category
Last pushed
Jul 13, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/YifanXu74/Evo-ViT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Jittor/jittor
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
zhanghang1989/ResNeSt
ResNeSt: Split-Attention Networks
berniwal/swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
NVlabs/FasterViT
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with...
ViTAE-Transformer/ViTPose
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose...