Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
huolongshe 1b24defb7b | 2 months ago | |
---|---|---|
app | 11 months ago | |
demo_data | 11 months ago | |
docs | 11 months ago | |
.gitignore | 11 months ago | |
Dockerfile | 11 months ago | |
LICENSE | 11 months ago | |
README.md | 2 months ago | |
application.yml | 11 months ago | |
build-docker.sh | 11 months ago | |
pack_model.py | 11 months ago | |
pip-install-reqs.sh | 11 months ago | |
requirements.txt | 9 months ago | |
run_model_server.py | 11 months ago |
本模型封装自魔搭(ModelScope)社区项目:BSHM通用抠图。通用抠图对输入图像中的主体进行抠图处理,支持商品、人物、动物、植物、汽车等等,无需任何额外输入,实现端到端通用万物抠图,输出四通道抠图结果。模型分为粗分割和精细抠图两个子网络,将人像抠图复杂问题拆解,先粗分割再精细化分割,两部分网络均为unet结构。粗分割网络从输入图片预测人像语义分割mask,精细分割网络基于原图和粗语义分割mask预测精细的抠图结果。
https://modelscope.cn/models/damo/cv_unet_universal-matting/summary
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1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": [], <图像的base64编码URL字符串>
}
No Description
Python Shell Text Dockerfile
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》