Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
huolongshe fb24ee5e14 | 2 months ago | |
---|---|---|
app | 10 months ago | |
demo_data | 10 months ago | |
docs | 10 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 |
CurricularFace为目前人脸识别的SOTA方法之一,其主要思想是采用课程学习的思想动态关注训练数据中的难例样本。此前的方法在训练中对于错分类的样本,要么未充分挖掘难例导致性能问题,要么在训练初期关注难例导致收敛问题。基于此,CurricularFace提出Adaptive Curriculum Learning Loss, 在训练过程中动态调整easy和hard样本的重要性,使训练初期关注简单样本,训练后期关注难例样本,而对难易样本分配不同重要性是通过设计一个代表收敛进度的指示函数来自适应调整的。
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": "add_face"
"args": {
"name": <姓名>,
"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": 1(添加人脸成功)|0(图像中无人脸或有多余一个人脸)|-1(已经存在相似人脸)
}
API接口2:
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": [<识别结果>, <gps信息>, <带姓名标注的base64编码图像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:
{
"status": "ok"|"err",
"value": [<识别结果>, <gps信息>, <带姓名标注的base64编码图像URL>]
}
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:
{
"status": "ok"|"err",
"value": [<识别结果>, <gps信息>, <带姓名标注的base64编码图像URL>]
}
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》