Snet.Yolo.Server 26.110.1

dotnet add package Snet.Yolo.Server --version 26.110.1
                    
NuGet\Install-Package Snet.Yolo.Server -Version 26.110.1
                    
This command is intended to be used within the Package Manager Console in Visual Studio, as it uses the NuGet module's version of Install-Package.
<PackageReference Include="Snet.Yolo.Server" Version="26.110.1" />
                    
For projects that support PackageReference, copy this XML node into the project file to reference the package.
<PackageVersion Include="Snet.Yolo.Server" Version="26.110.1" />
                    
Directory.Packages.props
<PackageReference Include="Snet.Yolo.Server" />
                    
Project file
For projects that support Central Package Management (CPM), copy this XML node into the solution Directory.Packages.props file to version the package.
paket add Snet.Yolo.Server --version 26.110.1
                    
#r "nuget: Snet.Yolo.Server, 26.110.1"
                    
#r directive can be used in F# Interactive and Polyglot Notebooks. Copy this into the interactive tool or source code of the script to reference the package.
#:package Snet.Yolo.Server@26.110.1
                    
#:package directive can be used in C# file-based apps starting in .NET 10 preview 4. Copy this into a .cs file before any lines of code to reference the package.
#addin nuget:?package=Snet.Yolo.Server&version=26.110.1
                    
Install as a Cake Addin
#tool nuget:?package=Snet.Yolo.Server&version=26.110.1
                    
Install as a Cake Tool

<h1 align="center">VisualIdentity</h1>

<p align="center"> <img width="120" height="120" src="https://api.shunnet.top/pic/nuget.png" alt="Snet Logo"/> </p>

<p align="center"> <b>基于 .NET 10 Yolo 多模型智能识别平台</b> </p>

<p align="center">

<img src="https://img.shields.io/badge/.NET-8.0-blue"/> <img src="https://img.shields.io/badge/.NET-10.0-blue"/> <img src="https://img.shields.io/badge/license-MIT-green"/> <img src="https://img.shields.io/github/stars/shunnet/VisualIdentity?style=social"/>

</p>

<p align="center"> 高效 · 灵活 · 易部署 </p>

<p align="center"> <a href="https://shunnet.top"><b>🌐 官方网站</b></a> · <a href="https://github.com/shunnet/VisualIdentity"><b>📦 GitHub</b></a> <a href="https://shunnet.top/EaiUj"><b>🎬 演示视频</b></a> </p>

🌟 项目简介

AI 应用落地 的过程中,模型管理多任务识别 一直是开发者的痛点。
无论是 检测、分类、分割、姿态估计、定向检测,往往都需要同时部署多个模型,传统方案在 效率易用性 上总会遇到瓶颈。

VisualIdentity 正是为了解决这一系列问题而生。
它结合了 .NET 10 的现代化能力、YoloDotNet 的高性能推理、以及 SQLite 的轻量级管理,为开发者提供一个 开箱即用 的智能识别平台。

✅ 多模型管理
✅ 单机多任务识别
✅ 跨平台部署

🎯 应用场景

  • 🏭 工业质检:瑕疵检测、异物识别
  • 🛒 零售分析:顾客行为、货架检测
  • 🛡️ 智能安防:异常行为、姿态识别
  • 🎓 科研教育:多模型实验平台
  • 🌐 边缘计算:轻量化部署到嵌入式或服务器

💡 ONNX 模型导出要求

  • 对于YOLOv26,导出时 opset=18
  • 对于YOLOv5u–YOLOv12,导出时 opset=17

[!重要] 使用正确的作集确保与 ONNX 运行时的最佳兼容性和性能。 有关如何将模型导出到 ONNX 的更多信息,请参见 https://docs.ultralytics.com/modes/export/

示例导出命令(Ultralytics CLI):

# For YOLOv5u–YOLOv12 (opset 17)
yolo export model=yolov8n.pt format=onnx opset=17

# For YOLOv26 (opset 18)
yolo export model=yolo26n.pt format=onnx opset=18

📦 NuGet 安装

dotnet add package Snet.Yolo.Server

(选择下方一项)
# CPU
dotnet add package YoloDotNet.ExecutionProvider.Cpu
# 硬件
dotnet add package YoloDotNet.ExecutionProvider.Cuda
dotnet add package YoloDotNet.ExecutionProvider.OpenVino
dotnet add package YoloDotNet.ExecutionProvider.CoreML
dotnet add package YoloDotNet.ExecutionProvider.DirectML

💡 调用示例

using SkiaSharp;
using Snet.Model.data;
using Snet.Yolo.Server;
using Snet.Yolo.Server.handler;
using Snet.Yolo.Server.models.data;
using Snet.Yolo.Server.models.@enum;
using YoloDotNet.ExecutionProvider.Cpu;
using YoloDotNet.Extensions;
using YoloDotNet.Models;

namespace Snet.Yolo.Test
{
    internal class Program
    {
        static async Task Main(string[] args)
        {
            //????? 为对应数据

            // 原始图片路径
            string imagePath = "?????";

            //模型路径
            string onnxModel = "?????";

            //识别类型
            OnnxType onnxType = OnnxType.ObjectDetection;

            //直接调用库来进行本地识别操作
            using SKImage image2 = SKImage.FromEncodedData(imagePath);

            // 调用识别
            OperateResult operateResult = await IdentityOperate.Instance(new Yolo.Server.models.data.IdentityData
            {
                Hardware = new CpuExecutionProvider(onnxModel),  //使用CPU进行运算
                IdentifyType = onnxType,
                SN = $"{onnxType}{onnxModel}"
            }).RunAsync(new ObjectDetectionData
            {
                Confidence = 0.23,
                Iou = 0.7,
                File = image2.Encode().ToArray()
            });

            // 转换结果
            List<ObjectDetection> results2 = operateResult.GetObjectDetectionResult().ToObjectDetection();

            //绘制结果
            using SKBitmap resultImage2 = image2.Draw(results2);

        }
    }
}

⚙️ 功能特性

🔹 多模型管理

  • 支持 增 / 删 / 改 / 查
  • 模型 版本化 & 快速切换
  • 一机多模型轻松维护

🔹 单机多任务流畅运行

  • 支持 检测 / OBB 定向检测 / 分类 / 分割 / 姿态估计
  • 基于 YoloDotNet 高速推理内核
  • 零配置,一键运行

🔹 跨平台 & 部署友好

  • 支持 Windows / Linux / Docker 部署
  • 提供轻量化配置,适配 边缘设备 & 服务器
  • 开箱即用,降低开发门槛

📚 依赖组件

Snet.DB

  • 集成 Dapper & SqlSugarCore
  • 支持高性能 SQL 映射与链式查询
  • 自动建表,高效开发
  • 保持轻量同时,具备 生产级性能

YoloDotNet

  • 适用于.NET的、超快速的、可投入生产的YOLO推理
  • YoloDotNet 是一个模块化、轻量级的C#库,用于实现实时计算机视觉以及.NET环境下基于YOLO的推理。

🔬 支持的任务

分类 (Classification) 检测 (Detection) OBB 定向检测 分割 (Segmentation) 姿态估计 (Pose)
<img src="https://user-images.githubusercontent.com/35733515/297393507-c8539bff-0a71-48be-b316-f2611c3836a3.jpg" width=300> <img src="https://user-images.githubusercontent.com/35733515/273405301-626b3c97-fdc6-47b8-bfaf-c3a7701721da.jpg" width=300> <img src="https://github.com/NickSwardh/YoloDotNet/assets/35733515/d15c5b3e-18c7-4c2c-9a8d-1d03fb98dd3c" width=300> <img src="https://github.com/NickSwardh/YoloDotNet/assets/35733515/3ae97613-46f7-46de-8c5d-e9240f1078e6" width=300> <img src="https://github.com/NickSwardh/YoloDotNet/assets/35733515/b7abeaed-5c00-4462-bd19-c2b77fe86260" width=300>
<sub>pexels.com</sub> <sub>pexels.com</sub> <sub>pexels.com</sub> <sub>pexels.com</sub> <sub>pexels.com</sub>

✅ 验证的YOLO模型

以下YOLO模型已使用YoloDotNet进行了测试和验证 官方Ultralytics导出和默认头部

分类 (Classification) 检测 (Detection) 分割 (Segmentation) 姿态估计 (Pose) OBB 定向检测
YOLOv8-cls<br>YOLOv11-cls<br>YOLOv12-cls<br>YOLOv26-cls YOLOv5u<br>YOLOv8<br>YOLOv9<br>YOLOv10<br>YOLOv11<br>YOLOv12<br>YOLOv26<br>RT-DETR YOLOv8-seg<br>YOLOv11-seg<br>YOLOv12-seg<br>YOLOv26-seg<br>YOLO-World (v2) YOLOv8-pose<br>YOLOv11-pose<br>YOLOv12-pose<br>YOLOv26-pose YOLOv8-obb<br>YOLOv11-obb<br>YOLOv12-obb<br>YOLOv26-obb<br>

⚡ 执行提供者

Provider Windows Linux macOS
CPU
CUDA / TensorRT
OpenVINO
CoreML
DirectML

ℹ️ 只能引用一个执行提供程序包 混合使用不同的提供程序会导致本地运行时冲突

🙏 致谢

📜 许可证

License: MIT

本项目基于 MIT 开源。
请阅读 LICENSE 获取完整条款。
⚠️ 软件按 “原样” 提供,作者不对使用后果承担责任。

🌍 查阅

👉 点击跳转

Product Compatible and additional computed target framework versions.
.NET net8.0 is compatible.  net8.0-android was computed.  net8.0-browser was computed.  net8.0-ios was computed.  net8.0-maccatalyst was computed.  net8.0-macos was computed.  net8.0-tvos was computed.  net8.0-windows was computed.  net9.0 was computed.  net9.0-android was computed.  net9.0-browser was computed.  net9.0-ios was computed.  net9.0-maccatalyst was computed.  net9.0-macos was computed.  net9.0-tvos was computed.  net9.0-windows was computed.  net10.0 is compatible.  net10.0-android was computed.  net10.0-browser was computed.  net10.0-ios was computed.  net10.0-maccatalyst was computed.  net10.0-macos was computed.  net10.0-tvos was computed.  net10.0-windows was computed. 
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.

NuGet packages

This package is not used by any NuGet packages.

GitHub repositories

This package is not used by any popular GitHub repositories.

Version Downloads Last Updated
26.110.1 80 4/20/2026
26.100.1 94 4/10/2026
26.99.1 106 4/9/2026
26.97.1 95 4/7/2026
26.83.1 106 3/24/2026
26.82.1 90 3/23/2026
26.78.1 96 3/19/2026
26.77.1 89 3/18/2026
26.75.2 95 3/16/2026
26.75.1 90 3/16/2026
26.68.1 90 3/9/2026
26.59.1 94 2/28/2026
26.56.1 98 2/25/2026
26.43.1 97 2/12/2026
26.41.1 100 2/10/2026
26.35.1 110 2/4/2026
26.21.1 119 1/21/2026
26.15.1 114 1/15/2026
26.13.1 109 1/13/2026
25.332.1 238 11/28/2025
Loading failed