Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
caoyunfei 9655269ad4 | 2 months ago | |
---|---|---|
app | 10 months ago | |
demo_data | 10 months ago | |
docs | 6 months ago | |
.gitignore | 10 months ago | |
Dockerfile | 2 months ago | |
LICENSE | 10 months ago | |
README.md | 10 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 | 2 months ago | |
run_model_server.py | 10 months ago |
NAFNet(Nonlinear Activation Free Network)提出了一个简单的基线,计算效率高。其不需要使用非线性激活函数(Sigmoid、ReLU、GELU、Softmax等),可以达到SOTA性能。本模型适用于智能手机拍摄的带噪图片。由于训练数据为SIDD,所有目前的去噪模型对手机拍摄的带噪图片效果良好,而其他类型的噪声可能表现不佳。
模型来源: https://www.modelscope.cn/models/damo/cv_nafnet_image-denoise_sidd/summary
引用:
@inproceedings{nafnet,
title = {Simple Baselines for Image Restoration},
author = {Chen, Liangyu and Chu, Xiaojie and Zhang, Xiangyu and Sun, Jian},
booktitle = {Proceedings of European Conference on Computer Vision (ECCV)},
year = {2022}
}
本模型基于 ServiceBoot微服务引擎 开发,参见: 《CubeAI模型开发指南》 。
本模型可发布至 CubeAI智立方平台 进行共享和部署,参见: 《CubeAI模型发布指南》 。
本模型还可直接基于git源代码在本机进行部署和运行,参见: 《CubeAI模型独立部署指南》 或 CubeAI Docker Builder 。
更多CubeAI模型样例请参见: 《CubeAI模型示范库》 。
测试和演示本模型时,如果需要用到视频流媒体服务,其环境搭建可参见:
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 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》