关于GCU、沐曦GPGPU、MLU、0卡V100资源4月7日恢复上架的公告>>> 关于共建具身智能开源数据集的倡议>>> 关于云脑任务中统一路径访问方式的公告>>> 关于将启智集群GPU资源迁移至智算集群的公告>>>
gbstack
/
PaddleDetection
Not watched
1
0
Fork 0
Code
Releases 0 Wiki Activity
Issues 0 Pull Requests 0 Datasets Cloudbrain
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
1322 Commits
5 Branches
196 MiB
39 Download
 
 
 
 
 
 
Branch: paa-on-develop
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'paa-on-develop'
${ noResults }
PaddleDetection/static/application/christmas
Manuel Garcia 84c8958dae
Optimize imports (#3601) 		2 years ago
..
blazeface Optimize imports (#3601) 2 years ago
demo_images root -> static (#2398) 3 years ago
element_source fix christmas app bug (#2474) 3 years ago
solov2 Optimize imports (#3601) 2 years ago
solov2_blazeface Optimize imports (#3601) 2 years ago
README.md fix christmas app bug (#2474) 3 years ago
test_main.py Optimize imports (#3601) 2 years ago
test_server.py root -> static (#2398) 3 years ago

README.md

人像圣诞特效自动生成工具

通过SOLOv2实例分割模型分割人像，并通过BlazeFace关键点模型检测人脸关键点，然后根据两个模型输出结果更换圣诞风格背景并为人脸加上圣诞老人胡子、圣诞眼镜及圣诞帽等特效。本项目通过PaddleHub可直接发布Server服务，供本地调试与前端直接调用接口。您可通过以下二维码中微信小程序直接体验：

环境搭建

环境依赖

  • paddlepaddle >= 2.0.0rc0

  • paddlehub >= 2.0.0b1

模型准备

  • 首先要获取模型，可在模型配置文件里配置solov2与blazeface_keypoint，训练模型，并导出模型。也可直接下载我们准备好模型：
    blazeface_keypoint模型和
    solov2模型。
    注意： 下载的模型需要解压后使用。

  • 然后将两个模型文件夹中的文件(infer_cfg.yml、__model__和__params__)分别拷贝至blazeface/blazeface_keypoint/ 和 solov2/solov2_r101_vd_fpn_3x/文件夹内。

hub安装blazeface和solov2模型

hub install solov2
hub install blazeface

hub安装solov2_blazeface圣诞特效自动生成串联模型

$ hub install solov2_blazeface

开始测试

本地测试

python test_main.py

运行成功后，预测结果会保存到chrismas_final.png。

serving测试

  • step1: 启动服务
export CUDA_VISIBLE_DEVICES=0
hub serving start -m solov2_blazeface -p 8880
  • step2: 在服务端发送预测请求
python test_server.py

运行成功后，预测结果会保存到chrismas_final.png。

效果展示

Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

PaddleDetection

Python Jupyter Notebook Markdown C++ Java other

Please read the following content carefully:

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》

Agree and continue
Disagree, exit