Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
huolongshe 0eaa589654 | 2 months ago | |
---|---|---|
app | 1 year ago | |
docs | 1 year ago | |
webapp | 11 months ago | |
.gitignore | 2 years ago | |
Dockerfile | 1 year ago | |
LICENSE | 2 years ago | |
README.md | 2 months ago | |
application.yml | 1 year ago | |
build-docker.sh | 1 year ago | |
pack_model.py | 1 year ago | |
pip-install-reqs.sh | 1 year ago | |
requirements.txt | 8 months ago | |
run_model_server.py | 1 year ago |
该模型基于卷积神经网络(CNN)实现手写数字识别,使用Keras框架实现,识别正确率为95%左右。
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》
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": <手写数字识别结果>|<错误描述>
}
API接口2:
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": <手写数字识别结果>|<错误描述>
}
API接口3:
API端点: /api/stream/predict
HTTP方法: POST
HTTP请求体:
<压缩图像的二进制字节流>
HTTP响应体:
{
"status": "ok"|"err",
"value": <手写数字识别结果>|<错误描述>
}
API接口4:
API端点: /api/data
HTTP方法: POST
HTTP请求体:
{
"action": "gen_demo_img"
"args": {}
}
HTTP响应体:
{
"status": "ok"|"err",
"value": <压缩图像的base64编码字符串>|<错误描述>
}
手写数字识别
TypeScript Python HTML Shell Text other
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》