YOWOv2: A Stronger yet Efficient Multi-level Detection Framework for Real-time Spatio-temporal Action Detection
English | 简体中文
非常感谢大家的star!YOWOv2是我业余时间做的一个尝试,是对上一代的YOWO的一次致敬。YOWO曾是我很喜欢的一个工作,但如今我已不再继续研究这一方向,因此,无法再回答大家的各种问题,对此,我深感抱歉,还望大家能够谅解。YOWOv2是一个完全开放的项目,不包含任何的license,因此,请尽管做任何你想做的改进或优化,无需经过我的同意。只要这个项目能对世界进步带去哪怕是微乎其微的促进和贡献,我也足够开心了~如果您觉得我们这个工作还行,不妨引用我们挂在Arxiv上的论文链接吧(在README的最下方)。
Thank you very much for everyone's star. YOWOv2 is an attempt I made in my spare time. It is a tribute to YOWO because I used to like YOWO very much. However, I am no longer deeply involved in the field of spatiotemporal motion detection, so I am not in a position to answer some of everyone's issues. For this, I am deeply sorry. YOWOv2 is a completely open spatiotemporal action detection project. I have not added any license to the project, so please feel free to do whatever you want without my consent. As long as my work can make even a small contribution to the progress of the world, I will be very happy. If you think our work is useful, you could cite our article posted on Arxiv (at the bottom of README).
- We recommend you to use Anaconda to create a conda environment:
conda create -n yowo python=3.6
- Then, activate the environment:
conda activate yowo
- Requirements:
pip install -r requirements.txt