<div align="center">
<img width="100%" src="https://user-images.githubusercontent.com/15977946/225229448-36ff568d-a723-4248-bb19-2df4044ff8e8.png"/>
</div>
# RTMPose: Real-Time Multi-Person Pose Estimation toolkit based on MMPose
> [RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose](https://arxiv.org/abs/2303.07399)
<div align="center">
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/rtmpose-real-time-multi-person-pose/2d-human-pose-estimation-on-coco-wholebody-1)](https://paperswithcode.com/sota/2d-human-pose-estimation-on-coco-wholebody-1?p=rtmpose-real-time-multi-person-pose)
</div>
<div align="center">
English | [ç®ä½ä¸æ](README_CN.md)
</div>
______________________________________________________________________
## Abstract
Recent studies on 2D pose estimation have achieved excellent performance on public benchmarks, yet its application in the industrial community still suffers from heavy model parameters and high latency.
In order to bridge this gap, we empirically study five aspects that affect the performance of multi-person pose estimation algorithms: paradigm, backbone network, localization algorithm, training strategy, and deployment inference, and present a high-performance real-time multi-person pose estimation framework, **RTMPose**, based on MMPose.
Our RTMPose-m achieves **75.8% AP** on COCO with **90+ FPS** on an Intel i7-11700 CPU and **430+ FPS** on an NVIDIA GTX 1660 Ti GPU, and RTMPose-l achieves **67.0% AP** on COCO-WholeBody with **130+ FPS**.
To further evaluate RTMPose's capability in critical real-time applications, we also report the performance after deploying on the mobile device. Our RTMPose-s achieves **72.2% AP** on COCO with **70+ FPS** on a Snapdragon 865 chip, outperforming existing open-source libraries.
With the help of MMDeploy, our project supports various platforms like CPU, GPU, NVIDIA Jetson, and mobile devices and multiple inference backends such as ONNXRuntime, TensorRT, ncnn, etc.
![rtmpose_intro](https://user-images.githubusercontent.com/13503330/219269619-935499e5-bdd9-49ea-8104-3c7796dbd862.png)
______________________________________________________________________
## ð Table of Contents
- [𥳠ð What's New](#--whats-new-)
- [ð Introduction](#-introduction-)
- [ð Community](#-community-)
- [â¡ Pipeline Performance](#-pipeline-performance-)
- [ð Model Zoo](#-model-zoo-)
- [ð Visualization](#-visualization-)
- [ð Get Started](#-get-started-)
- [ð¨âð« How to Train](#-how-to-train-)
- [ðï¸ How to Deploy](#ï¸-how-to-deploy-)
- [ð Common Usage](#ï¸-common-usage-)
- [ð Inference Speed Test](#-inference-speed-test-)
- [ð Model Test](#-model-test-)
- [ð Citation](#-citation-)
## 𥳠ð What's New [ð](#-table-of-contents)
- Mar. 2023: RTMPose is released. RTMPose-m runs at 430+ FPS and achieves 75.8 mAP on COCO val set.
## ð Introduction [ð](#-table-of-contents)
<div align=center>
<img src="https://user-images.githubusercontent.com/13503330/221138554-110240d8-e887-4b9a-90b1-2fbdc982e9de.gif" width=400 height=300/><img src="https://user-images.githubusercontent.com/13503330/221125176-85015a13-9648-4f0d-a17c-1cbb469efacf.gif" width=250 height=300/><img src="https://user-images.githubusercontent.com/13503330/221125310-7eeb2212-907e-427f-97af-af799d70a4c5.gif" width=250 height=300/>
</div>
<div align=center>
<img src="https://user-images.githubusercontent.com/13503330/221125768-8e0d6754-e66d-4941-ac53-ded8db9b60f9.gif" width=450 height=300/><img src="https://user-images.githubusercontent.com/13503330/221125888-15c20faf-0ad5-4afb-828b-a71ccb064582.gif" width=450 height=300/>
</div>
<div align=center>
<img src="https://user-images.githubusercontent.com/13503330/221124560-af84b291-4300-4027-87ae-8c3a201c3f67.gif" width=300 height=350/><img src="https://user-images.githubusercontent.com/13503330/221138017-10431ab4-e515-4c32-8fa7-8748e2d17a58.gif" width=600 height=350/>
</div>
### ⨠Major Features
- ð **High efficiency and high accuracy**
| Model | AP(COCO) | CPU-FPS | GPU-FPS |
| :---: | :------: | :-----: | :-----: |
| t | 68.5 | 300+ | 940+ |
| s | 72.2 | 200+ | 710+ |
| m | 75.8 | 90+ | 430+ |
| l | 76.5 | 50+ | 280+ |
- ð ï¸ **Easy to deploy**
- Step-by-step deployment tutorials.
- Support various backends including
- ONNX
- TensorRT
- ncnn
- OpenVINO
- etc.
- Support various platforms including
- Linux
- Windows
- NVIDIA Jetson
- ARM
- etc.
- ðï¸ **Design for practical applications**
- Pipeline inference API and SDK for
- Python
- C++
- C#
- JAVA
- etc.
## ð Community [ð](#-table-of-contents)
RTMPose is a long-term project dedicated to the training, optimization and deployment of high-performance real-time pose estimation algorithms in practical scenarios, so we are looking forward to the power from the community. Welcome to share the training configurations and tricks based on RTMPose in different business applications to help more community users!
⨠⨠â¨
- **If you are a new user of RTMPose, we eagerly hope you can fill out this [Google Questionnaire](https://docs.google.com/forms/d/e/1FAIpQLSfzwWr3eNlDzhU98qzk2Eph44Zio6hi5r0iSwfO9wSARkHdWg/viewform?usp=sf_link)/[Chinese version](https://uua478.fanqier.cn/f/xxmynrki), it's very important for our work!**
⨠⨠â¨
Feel free to join our community group for more help:
- WeChat Group:
<div align=left>
<img src="https://user-images.githubusercontent.com/13503330/222647056-875bed70-85ec-455c-9016-c024772915c4.jpg" width=200 />
</div>
- Discord Group:
- ð https://discord.gg/raweFPmdzG ð
## â¡ Pipeline Performance [ð](#-table-of-contents)
**Notes**
- Pipeline latency is tested under skip-frame settings, the detection interval is 5 frames by defaults.
- Flip test is NOT used.
- Env Setup:
- torch >= 1.7.1
- onnxruntime 1.12.1
- TensorRT 8.4.3.1
- ncnn 20221128
- cuDNN 8.3.2
- CUDA 11.3
| Detection Config | Pose Config | Input Size<sup><br>(Det/Pose) | Model AP<sup><br>(COCO) | Pipeline AP<sup><br>(COCO) | Params (M)<sup><br>(Det/Pose) | Flops (G)<sup><br>(Det/Pose) | ORT-Latency(ms)<sup><br>(i7-11700) | TRT-FP16-Latency(ms)<sup><br>(GTX 1660Ti) | Download |
| :------------------------------------------------------------------ | :---------------------------------------------------------------------------- | :---------------------------: | :---------------------: | :------------------------: | :---------------------------: | :--------------------------: | :--------------------------------: | :---------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| [RTMDet-nano](./rtmdet/person/rtmdet_nano_320-8xb32_coco-person.py) | [RTMPose-t](./rtmpose/body_2d_keypoint/rtmpose-t_8xb256-420e_coco-256x192.py) | 320x320<br>256x192 | 40.3<br>67.1 | 64.4 | 0.99<br/>3.34 | 0.31<br/>0.36 | 12.403 | 2.467 | [det](https://download.openmmlab.com/mmpose/v1/projects/rtmpose/rtmdet_nano_8xb32-100e_coco-obj365-person-05d8511e.pth)<br/>[pose](https://download.openmmlab.com/mmpose/v1/projects/rtmpose/rtmpose-tiny_s
没有合适的资源?快使用搜索试试~ 我知道了~
MMPose 是一款基于 PyTorch 的姿态分析的开源工具箱,是 OpenMMLab 项目的成员之一
共1459个文件
py:763个
md:353个
yml:127个
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
1 下载量 111 浏览量
2023-05-29
08:28:44
上传
评论 1
收藏 12.24MB ZIP 举报
温馨提示
基于 PyTorch 的姿态估计算法库,支持人体、人手、人脸、动物、服装等多类物体的 2D/3D 姿态估计。
资源推荐
资源详情
资源评论
收起资源包目录
MMPose 是一款基于 PyTorch 的姿态分析的开源工具箱,是 OpenMMLab 项目的成员之一 (1459个子文件)
make.bat 760B
make.bat 760B
CITATION.cff 269B
setup.cfg 631B
readthedocs.css 183B
readthedocs.css 183B
datasets 35B
demo 10B
Dockerfile 1KB
Dockerfile 1KB
Dockerfile 527B
demo_coco.gif 1.53MB
.gitignore 2KB
MANIFEST.in 198B
pytest.ini 311B
MMPose_Tutorial.ipynb 876KB
ho105.jpeg 22KB
ca110.jpeg 9KB
S4_Seq2_Cam0_001033.jpg 619KB
000000000004.jpg 619KB
S8_Seq1_Cam8_002165.jpg 541KB
TS2_001850.jpg 249KB
000000037516.jpg 231KB
TS1_002001.jpg 223KB
image22568.jpg 195KB
PRI_1473.jpg 183KB
000000197388.jpg 163KB
000000.jpg 146KB
000000.jpg 145KB
000000196141.jpg 132KB
000000000785.jpg 131KB
7_Cheering_Cheering_7_16.jpg 125KB
000061.jpg 119KB
000000.jpg 109KB
005808361.jpg 104KB
000000040083.jpg 102KB
103319.jpg 97KB
060754485.jpg 96KB
000000.jpg 94KB
004645041.jpg 94KB
fa436c914fe4a8ec1ec5474af4d3820b84d17561.jpg 84KB
000000.jpg 83KB
051423444.jpg 83KB
image04476.jpg 81KB
005880453_01_l.jpg 80KB
005880453_01_r.jpg 80KB
784.jpg 80KB
003799.jpg 76KB
ff945ae2e729f24eea992814639d59b3bdec8bd8.jpg 75KB
d47f1b1ee9d3217e.jpg 74KB
003896.jpg 70KB
36_Football_americanfootball_ball_36_415.jpg 70KB
000817.jpg 69KB
S1_Directions_1.54138969_000001.jpg 69KB
S7_Greeting.55011271_000396.jpg 69KB
S8_WalkDog_1.55011271_000026.jpg 69KB
106848.jpg 68KB
000000.jpg 63KB
S5_SittingDown.54138969_002061.jpg 63KB
000001.jpg 55KB
000002.jpg 55KB
000004.jpg 54KB
000000.jpg 54KB
000003.jpg 53KB
054d9ce9201beffc76e5ff2169d2af2f027002ca.jpg 51KB
003464.jpg 38KB
00082740.jpg 37KB
00115300.jpg 37KB
00050180.jpg 36KB
001766.jpg 30KB
33.jpg 28KB
image2017.jpg 27KB
001805.jpg 24KB
9.jpg 21KB
00098035.jpg 19KB
00065475.jpg 19KB
052475643.jpg 19KB
00032915.jpg 18KB
image29590.jpg 17KB
00017620.jpg 17KB
ex2_2.flv_000040_l.jpg 16KB
ex2_2.flv_000040_r.jpg 16KB
00000355.jpg 16KB
image44669.jpg 15KB
10084.jpg 15KB
1402.jpg 13KB
image69148.jpg 12KB
sunglasses.jpg 10KB
850.jpg 10KB
810.jpg 10KB
10112.jpg 10KB
img_00000132.jpg 9KB
630.jpg 8KB
650.jpg 7KB
img_00000128.jpg 6KB
1400.jpg 5KB
1450.jpg 4KB
calibration_160906_band2.json 246KB
calibration_160906_band1.json 246KB
test_coco_wholebody.json 174KB
共 1459 条
- 1
- 2
- 3
- 4
- 5
- 6
- 15
资源评论
Java程序员-张凯
- 粉丝: 1w+
- 资源: 6735
下载权益
C知道特权
VIP文章
课程特权
开通VIP
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- 【老生谈算法】matlab实现非线性整数规划的遗传算法.doc
- MTB020C04RQ8-VB一款N+P-Channel沟道SOP8的MOSFET晶体管参数介绍与应用说明
- MTA40B03Q8-VB一款2个P-Channel沟道SOP8的MOSFET晶体管参数介绍与应用说明
- data.json全国省市区县 json数据
- MTA100N10KRN3-VB一款N-Channel沟道SOT23的MOSFET晶体管参数介绍与应用说明
- Unity 单机版斗地主游戏源码
- MacOs Sonoma懒人版镜像包附VM-unlock最新版
- Unity 插件之移动端影子生成插件(Mobile Fast Shadow 1.0.6)
- MTA025N03KSN3-VB一款N-Channel沟道SOT23的MOSFET晶体管参数介绍与应用说明
- MT4953ACTR-VB一款2个P-Channel沟道SOP8的MOSFET晶体管参数介绍与应用说明
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功