CVNets: High Performance Library for Computer Vision
2022-06-04Code Available6· sign in to hype
Sachin Mehta, Farzad Abdolhosseini, Mohammad Rastegari
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/apple/ml-cvnetsOfficialIn paperpytorch★ 1,968
- github.com/apple/corenetpytorch★ 7,008
- github.com/microndla/mobilevitv3pytorch★ 276
- github.com/2023-MindSpore-4/Code12/tree/main/d2l/chapter_12_computational-performancemindspore★ 0
Abstract
We introduce CVNets, a high-performance open-source library for training deep neural networks for visual recognition tasks, including classification, detection, and segmentation. CVNets supports image and video understanding tools, including data loading, data transformations, novel data sampling methods, and implementations of several standard networks with similar or better performance than previous studies. Our source code is available at: https://github.com/apple/ml-cvnets.