OpenVinoSharp.win 2.0.4

Suggested Alternatives

OpenVINO.CSharp.Windows

Additional Details

This version of the package has been deprecated and may contain related errors during use. Its functionality is incomplete, so it is recommended to use the latest version of the package: OpenVINO.CSharp.Windows
Thank you for your support.
该版本程序包已经废弃,在使用时可能会存在相关错误,其功能不完善,因此推荐大家使用最新版本的程序包:OpenVINO.CSharp.Windows
感谢大家支持。

There is a newer version of this package available.
See the version list below for details.
dotnet add package OpenVinoSharp.win --version 2.0.4
NuGet\Install-Package OpenVinoSharp.win -Version 2.0.4
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="OpenVinoSharp.win" Version="2.0.4" />
For projects that support PackageReference, copy this XML node into the project file to reference the package.
paket add OpenVinoSharp.win --version 2.0.4
#r "nuget: OpenVinoSharp.win, 2.0.4"
#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.
// Install OpenVinoSharp.win as a Cake Addin
#addin nuget:?package=OpenVinoSharp.win&version=2.0.4

// Install OpenVinoSharp.win as a Cake Tool
#tool nuget:?package=OpenVinoSharp.win&version=2.0.4

![OpenVinoSharp](https://socialify.git.ci/guojin-yan/OpenVinoSharp/image?description=1&descriptionEditable=💞 OpenVINO wrapper for .NET💞&font=Inter&forks=1&issues=1&logo=https%3A%2F%2Fs2.loli.net%2F2023%2F01%2F26%2FylE1K5JPogMqGSW.png&name=1&owner=1&pattern=Circuit Board&pulls=1&stargazers=1&theme=Light)

<img title="更新日志" src="https://s2.loli.net/2023/01/26/RJ1znO78bygCcKj.png" alt="" width="40">更新日志

  • 🔥 2023.1.23 :发布 OpenVinoSharp 2.0
    • 🗳 OpenVinoSharp 库:

      • 基于OpenVinoSharp 1.0 以及使用中所出现的问题,将一些问题进行了修改;
      • 增加数据处理方式。
    • 🔮 NuGet包:

      • 制作并发布NuGet包,包括OpenVinoSharp.winOpenVinoSharp.win.simplify 两个安装包。
    • 💡 技术文档:

<img title="更新日志" src="https://s2.loli.net/2023/01/26/Zs1VFUT4BGQgfE9.png" alt="" width="40"> 简介

    OpenVINO™是一个用于优化和部署深度学习模型的开源工具包,是英特尔基于自身现有的硬件平台开发的一种可以加快高性能计算机视觉和深度学习视觉应用开发速度工具套件,用于快速开发应用程序和解决方案,以解决各种任务(包括人类视觉模拟、自动语音识别、自然语言处理和推荐系统等)。

  官方发行的OpenVINO™未提供C#编程语言接口,因此在使用时无法实现在C#中利用OpenVINO™进行模型部署。在该项目中,利用动态链接库功能,调用官方依赖库,实现在C#中部署深度学习模型,为方便使用,在该项目中提供了NuGet包方便使用,为了方便大家再此基础上进行开发,该项目提供了详细的技术文档。

<img title="更新日志" src="https://s2.loli.net/2023/01/26/LdbeOYGgwZvHcBQ.png" alt="" width="400">

<img title="NuGet" src="https://s2.loli.net/2023/01/26/ks9BMwXaHqQnKZP.png" alt="" width="40">NuGet包

托管库

Package Description Link
OpenVinoSharp.win OpenVinoSharp core libraries,附带完整的OpenCV 4.5.5、OpenVINO 2022.3依赖库
OpenVinoSharp.win.simplify OpenVinoSharp core libraries,附带完整的OpenCV 4.5.5,需自行安装OpenVINO 2022.3。

<img title="安装" src="https://s2.loli.net/2023/01/26/bm6WsE5cfoVvj7i.png" alt="" width="50"> 安装

OpenVINO安装

OpenVinoSharp NuGet包安装

<img title="API文档" src="https://s2.loli.net/2023/01/26/CNgHGrJ2DyvsaP4.png" alt="" width="50">API文档

命名空间

using OpenVinoSharp;

模型推理API

<table> <tr> <th width="7%" align="center" bgcolor=#FF7A68>序号</th> <th width="35%" colspan="2" align="center" bgcolor=#FF7A68>API</th> <th width="43%" align="center" bgcolor=#FF7A68>参数解释</th>
<th width="15%" align="center" bgcolor=#FF7A68>说明</th> </tr > <tr > <td rowspan="4" align="center">1</td> <td align="center">方法</td> <td>Core()</td> <td>构造函数</td> <td rowspan="4">初始化推理核心,读取本地模型,加载到设备,并创建推理通道</td> </tr> <tr > <td rowspan="3" align="center">参数</td> <td><font color=blue>string</font> model</td> <td>模型路径</td> </tr> <tr > <td><font color=blue>string</font>device</td> <td>设备名称</td> </tr> <tr > <td><font color=blue>string</font>cache_dir</td> <td>缓存路径</td> </tr> <tr > <td rowspan="3" align="center">2</td> <td align="center">方法</td> <td><font color=blue>void</font> set_input_shape()</td> <td>设置输入节点形状</td> <td rowspan="3">根据节点维度设置</td> </tr> <tr > <td rowspan="2" align="center">参数</td> <td><font color=blue>string</font> node_name</td> <td>节点名称</td> </tr> <tr > <td><font color=blue>int[]</font> input_shape</td> <td>形状数组</td> </tr> <tr > <td rowspan="6" align="center">3</td> <td align="center">方法</td> <td><font color=blue>void</font> load_input_data()</td> <td>设置图片/普通输入数据</td> <td rowspan="6">方法重载</td> </tr> <tr > <td rowspan="2" align="center">参数</td> <td><font color=blue>string</font> node_name</td> <td>输入节点名称</td> </tr> <tr > <td><font color=blue>float[]</font> input_data</td> <td>输入数据</td> </tr> <tr > <td rowspan="3" align="center">参数</td> <td><font color=blue>string</font> node_name</td> <td>输入节点名称</td> </tr> <tr > <td><font color=blue>byte[]</font> image_data</td> <td>图片数据</td> </tr> <tr > <td><font color=blue>int</font> type</td> <td>数据处理类型:<br>type = 0: 均值方差归一化、常规缩放<br>type = 1: 普通归一化(1/255)、常规缩放<br>type = 2: 不归一化、常规缩放<br>type = 0: 均值方差归一化、仿射变换<br>type = 1: 普通归一化(1/255)、仿射变换<br>type = 2: 不归一化、仿射变换</td> </tr> <tr > <td rowspan="1" align="center">4</td> <td align="center">方法</td> <td><font color=blue>void</font> infer()</td> <td>模型推理</td> <td rowspan="1"></td> </tr> <tr > <td rowspan="3" align="center">5</td> <td align="center">方法</td> <td><font color=blue>void</font> <font color=green>T</font>[] read_infer_result &lt<font color=green>T</font>&gt()</td> <td>读取推理结果数据</td> <td rowspan="3">支持读取Float32、Int32、Int64格式数据</td> </tr> <tr > <td rowspan="2" align="center">参数</td> <td><font color=blue>string</font> output_name</td> <td>输出节点名</td> </tr> <tr > <td><font color=blue>int</font> data_size</td> <td>输出数据长度</td> </tr> <tr > <td rowspan="1" align="center">6</td> <td align="center">方法</td> <td><font color=blue>void</font> delet()</td> <td>删除内存地址</td> <td rowspan="1"></td> </tr>

Product Compatible and additional computed target framework versions.
.NET net6.0 is compatible.  net6.0-android was computed.  net6.0-ios was computed.  net6.0-maccatalyst was computed.  net6.0-macos was computed.  net6.0-tvos was computed.  net6.0-windows was computed.  net7.0 was computed.  net7.0-android was computed.  net7.0-ios was computed.  net7.0-maccatalyst was computed.  net7.0-macos was computed.  net7.0-tvos was computed.  net7.0-windows was computed.  net8.0 was computed.  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. 
.NET Framework net48 is compatible.  net481 was computed. 
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.
  • .NETFramework 4.8

    • No dependencies.
  • net6.0

    • No dependencies.

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
3.0.120 898 7/30/2023
3.0.118 251 7/30/2023
3.0.117 227 7/27/2023
2.1.2 391 7/23/2023
2.1.1 381 6/21/2023
2.1.0 261 6/21/2023
2.0.10 203 6/21/2023
2.0.9 238 6/21/2023
2.0.8 215 6/21/2023
2.0.7 240 6/21/2023
2.0.6 898 1/27/2023
2.0.5 562 1/27/2023
2.0.4 639 1/26/2023
2.0.3 548 1/25/2023
2.0.2 769 1/25/2023
2.0.1 505 1/25/2023
2.0.0 517 1/25/2023

发布 2.0.4