zoukankan      html  css  js  c++  java
  • test

    https://github.com/MVIG-SJTU/AlphaPose/tree/pytorch

    News!

    This pytorch version of AlphaPose runs at 20 fps on COCO validation set (4.6 people per image on average) and achieves 71 AP!

    AlphaPose

    Alpha Pose is an accurate multi-person pose estimator, which is the first open-source system that achieves 70+ mAP (72.3 mAP) on COCO dataset and 80+ mAP (82.1 mAP) on MPII dataset. To match poses that correspond to the same person across frames, we also provide an efficient online pose tracker called Pose Flow. It is the first open-source online pose tracker that achieves both 60+ mAP (66.5 mAP) and 50+ MOTA (58.3 MOTA) on PoseTrack Challenge dataset.

    AlphaPose supports both Linux and Windows!

    Installation

    Windows Version please check out doc/win_install.md

    1. Get the code.
    git clone -b pytorch https://github.com/MVIG-SJTU/AlphaPose.git
    1. Install pytorch 0.4.0
    chmod +x install.sh
    ./install.sh
    1. Download the models manually: duc_se.pth (2018/08/30) (Google Drive | Baidu pan), yolov3.weights(Google Drive | Baidu pan). Place them into ./models/sppe and ./models/yolo respectively.

    Quick Start

    • Input dir: Run AlphaPose for all images in a folder with:
    python3 demo.py --indir ${img_directory} --outdir examples/res 
    
    • Video: Run AlphaPose for a video and save the rendered video with:
    python3 video_demo.py --video ${path to video} --outdir examples/res --save_video
    
    • Webcam: Run AlphaPose using webcam and visualize the results with:
    python3 webcam_demo.py --webcam 0 --outdir examples/res --vis
    
    • Input list: Run AlphaPose for images in a list and save the rendered images with:
    python3 demo.py --list examples/list-coco-demo.txt --indir ${img_directory} --outdir examples/res --save_img
    
    • Note: If you meet OOM(out of memory) problem, decreasing the pose estimation batch until the program can run on your computer:
    python3 demo.py --indir ${img_directory} --outdir examples/res --posebatch 30
    
    • Speeding up: Checkout the speed_up.md for more details.
    • For more: Checkout the run.md for more options

    FAQ

    Check out faq.md for faq.

    Contributors

    Pytorch version of AlphaPose is developed and maintained by Jiefeng LiHao-Shu Fang and Cewu Lu.

    Citation

    Please cite these papers in your publications if it helps your research:

    @inproceedings{fang2017rmpe,
      title={{RMPE}: Regional Multi-person Pose Estimation},
      author={Fang, Hao-Shu and Xie, Shuqin and Tai, Yu-Wing and Lu, Cewu},
      booktitle={ICCV},
      year={2017}
    }
    
    @ARTICLE{2018arXiv180200977X,
      author = {Xiu, Yuliang and Li, Jiefeng and Wang, Haoyu and Fang, Yinghong and Lu, Cewu},
      title = {{Pose Flow}: Efficient Online Pose Tracking},
      journal = {ArXiv e-prints},
      eprint = {1802.00977},
      year = {2018}
    }
    

    License

    AlphaPose is freely available for free non-commercial use, and may be redistributed under these conditions. For commercial queries, contact Cewu Lu

  • 相关阅读:
    什么是数据挖掘?
    Oracle 泵导入导出
    如何创建一个 mongo 数据库并为它添加一个认证用户?
    如何提高 windows 的使用效率?--巧用运行命令
    在 vs2017 中使用 C# 7 新特性。
    什么是按引用传递和按值传递?
    Vue、Vuex+Cookie 实现自动登陆 。
    Web.config 灵活配置
    远程终端
    js框架总结
  • 原文地址:https://www.cnblogs.com/herd/p/9607205.html
Copyright © 2011-2022 走看看