Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
huolongshe bab9792d18 | 2 months ago | |
---|---|---|
app | 10 months ago | |
demo_data | 10 months ago | |
docs | 6 months ago | |
.gitignore | 10 months ago | |
Dockerfile | 10 months ago | |
LICENSE | 10 months ago | |
README.md | 2 months ago | |
application.yml | 10 months ago | |
build-docker.sh | 10 months ago | |
pack_model.py | 10 months ago | |
pip-install-reqs.sh | 10 months ago | |
requirements.txt | 9 months ago | |
run_model_server.py | 10 months ago |
输入一张人物图像,实现端到端的人体关键点检测,输出图像中所有人体的15点人体关键点坐标。体关键点模型基于HRNet的backbone,充分利用多分辨率的特征融合,良好支持日常人体姿态,尤其是在瑜伽、健身等场景下多遮挡、非常见、多卧姿姿态上具有SOTA的检测精度。
模型来源: https://www.modelscope.cn/models/damo/cv_hrnetv2w32_body-2d-keypoints_image/summary
引用:
@inproceedings{cheng2020bottom,
title={HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation},
author={Bowen Cheng and Bin Xiao and Jingdong Wang and Honghui Shi and Thomas S. Huang and Lei Zhang},
booktitle={CVPR},
year={2020}
}
@inproceedings{SunXLW19,
title={Deep High-Resolution Representation Learning for Human Pose Estimation},
author={Ke Sun and Bin Xiao and Dong Liu and Jingdong Wang},
booktitle={CVPR},
year={2019}
}
@article{wang2019deep,
title={Deep High-Resolution Representation Learning for Visual Recognition},
author={Wang, Jingdong and Sun, Ke and Cheng, Tianheng and Jiang, Borui and Deng, Chaorui and Zhao, Yang and Liu, Dong and Mu, Yadong and Tan, Mingkui and Wang, Xinggang and Liu, Wenyu and Xiao, Bin},
journal={TPAMI},
year={2019}
}
本模型基于 ServiceBoot微服务引擎 进行服务化封装,参见: 《CubeAI模型开发指南》
$ sh pip-install-reqs.sh
$ serviceboot start
或
$ python3 run_model_server.py
一键式本地容器化部署和运行,参见: 《CubeAI模型独立部署指南》 或 CubeAI Docker Builder
本模型服务可一键发布至 CubeAI智立方平台 进行共享和部署,参见: 《CubeAI模型发布指南》
本模型提供了4个API接口:
API接口1:
API端点: /api/data
HTTP方法: POST
HTTP请求体:
{
"action": "predict",
"args": {
"img": <压缩图像的base64编码字符串(或其Data URL表示)>
}
}
HTTP响应体:
{
"status": "ok"|"err",
"value": [<results>, <base64编码压缩图像URL>]
}
API接口2:
API端点: /api/data
HTTP方法: POST
HTTP请求体:
{
"action": "predict_video",
"args": {
"url": <云端视频流媒体URL, 例如: rtmp://localhost/live/ch1>
}
}
HTTP响应体:
{
"status": "ok"|"err",
"value": <(流媒体当前帧图像)AI处理结果的base64编码压缩图像URL>
}
API接口3:
API端点: /api/stream/predict
HTTP方法: POST
HTTP请求体: <二进制编码的压缩图像字节流>
HTTP响应体: 同API接口1
API接口4:
API端点: /api/file/predict
HTTP方法: POST
HTTP请求体: <用于HTTP文件上传的XHR格式请求体>
HTTP响应体: 同API接口1
No Description
Python Shell Dockerfile Text
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》