AI Rank
EN
← 开源
tensorboy

pytorch_Realtime_Multi-Person_Pose_Estimation

Model DevelopmentArchitecturePython
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
1.37k
Star
405
Fork
+-1
本周
5
贡献者
创建于 2017-03-28 · 更新于 2026-10-13 · 今日第 10552 名
主要开发者
SimonhflstensorboyClementPinard

tensorboy/pytorch_Realtime_Multi-Person_Pose_Estimation 排名第 10,552，有 1,369 个星标。

同类别比较

tensorboy/pytorch_Realtime_Multi-Person_Pose_Estimation 排名第 10,552，此处有 8 个同类条目；zalandoresearch/pytorch-ts 排名第 10,553。

同类别比较
名称排名指标
Cysu/open-reid10,542
语言:
Python
星标数:
1,371
分叉数:
347
简介:
Open source person re-identification library in python
andersbll/deeppy10,543
语言:
Python
星标数:
1,371
分叉数:
298
简介:
Deep learning in Python
oxwhirl/smac10,545
语言:
Python
星标数:
1,371
分叉数:
243
简介:
SMAC: The StarCraft Multi-Agent Challenge
hiyouga/FastEdit10,549
语言:
Python
星标数:
1,369
分叉数:
103
简介:
🩹Editing large language models within 10 seconds⚡
zalandoresearch/pytorch-ts10,553
语言:
Python
星标数:
1,369
分叉数:
197
简介:
PyTorch based Probabilistic Time Series forecasting framework based on GluonTS backend
JonasGeiping/cramming10,554
语言:
Python
星标数:
1,368
分叉数:
105
简介:
Cramming the training of a (BERT-type) language model into limited compute.
k2-fsa/k210,557
语言:
Cuda
星标数:
1,368
分叉数:
241
简介:
FSA/FST algorithms, differentiable, with PyTorch compatibility.
raznem/parsera10,559
语言:
Python
星标数:
1,368
分叉数:
79
简介:
Lightweight library for scraping web-sites with LLMs
关键参数与规格
关键参数与规格
参数值
语言Python
类别Model Development
子类别Architecture
星标数1,369
分叉数405
贡献者5
创建日期2017-03-28
更新日期2026-10-13
1 天星标数0
7 天星标数-1
排名10,552
上次排名10,546
排名变化-6
7 天星标排名17,179
上次 7 天星标排名17,175
7 天星标排名变化-4
总星标排名8,726
上次总星标排名8,717
总星标排名变化-9
README 摘录

Introduction Multi Person PoseEstimation By PyTorch Results Require 1. git submodule init && git submodule update Demo Download converted pytorch model. Compile the C++ postprocessing: to run the picture demo. Evalute to evaluate the model on coco val2017 dataset. It should have for the rtpose, previous rtpose have because we do left and right flip for heatmap and PAF for the evaluation. 653 |-| Download link: rtpose Development environment The code is developed using python 3. The code is developed and tested

using 4 1080ti GPU cards. Other platforms or GPU cards are not fully tested. 1 Prepare the dataset to obtain the COCO 2017 images in , keypoints annotations in , make them look like this: 2. How to train the model Modify the data directory in and Related repository CVPR'17, Realtime Multi-Person Pose Estimation. Network Architecture testing architecture training architecture Contributions All contributions are welcomed. If you encounter any issue (including examples of images where it fails) feel free to

open an issue. Citation Please cite the paper in your publications if it helps your research:

常见问题

记录了多少星标和分叉？

tensorboy/pytorch_Realtime_Multi-Person_Pose_Estimation 有 1,369 个星标和 405 个分叉。

仓库排名是多少？

tensorboy/pytorch_Realtime_Multi-Person_Pose_Estimation 排名第 10,552。

记录的语言和类别是什么？

tensorboy/pytorch_Realtime_Multi-Person_Pose_Estimation 有 1,369 个星标，语言为 Python，类别为 Model Development。

哪个仓库排名最接近？

tensorboy/pytorch_Realtime_Multi-Person_Pose_Estimation 与 zalandoresearch/pytorch-ts 比较，后者排名第 10,553，有 1,369 个星标。

README

Introduction

Multi Person PoseEstimation By PyTorch

Results

Require

  1. Pytorch

Installation

  1. git submodule init && git submodule update

Demo

  • Download converted pytorch model.
  • Compile the C++ postprocessing: cd lib/pafprocess; sh make.sh
  • python demo/picture_demo.py to run the picture demo.
  • python demo/web_demo.py to run the web demo.

Evalute

  • python evaluate/evaluation.py to evaluate the model on coco val2017 dataset.
  • It should have mAP 0.653 for the rtpose, previous rtpose have mAP 0.577 because we do left and right flip for heatmap and PAF for the evaluation. c

Main Results

model name mAP Inference Time
[original rtpose] 0.653 -

Download link: rtpose

Development environment

The code is developed using python 3.6 on Ubuntu 18.04. NVIDIA GPUs are needed. The code is developed and tested using 4 1080ti GPU cards. Other platforms or GPU cards are not fully tested.

Quick start

1. Preparation

1.1 Prepare the dataset

  • cd training; bash getData.sh to obtain the COCO 2017 images in /data/root/coco/images/, keypoints annotations in /data/root/coco/annotations/, make them look like this:
${DATA_ROOT}
|-- coco
    |-- annotations
        |-- person_keypoints_train2017.json
        |-- person_keypoints_val2017.json
    |-- images
        |-- train2017
            |-- 000000000009.jpg
            |-- 000000000025.jpg
            |-- 000000000030.jpg
            |-- ... 
        |-- val2017
            |-- 000000000139.jpg
            |-- 000000000285.jpg
            |-- 000000000632.jpg
            |-- ...

2. How to train the model

  • Modify the data directory in train/train_VGG19.py and python train/train_VGG19.py

Related repository

Network Architecture

  • testing architecture

  • training architecture

Contributions

All contributions are welcomed. If you encounter any issue (including examples of images where it fails) feel free to open an issue.

Citation

Please cite the paper in your publications if it helps your research:

@InProceedings{cao2017realtime,
  title = {Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields},
  author = {Zhe Cao and Tomas Simon and Shih-En Wei and Yaser Sheikh},
  booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017}
  }
排名相邻
同类项目