【TensorRT】TensorRT C# API 项目更新 (1)：支持动态Bath输入模型推理（下篇）

4. 接口应用

关于该项目的调用方式在上一篇文章中已经进行了详细介绍，具体使用可以参考《最新发布！TensorRT C# API ：基于C#与TensorRT部署深度学习模型》，下面结合Yolov8-cls模型详细介绍一下更新的接口使用方法。

4.1 创建并配置C#项目

首先创建一个简单的C#项目，然后添加项目配置。

首先是添加TensorRT C# API 项目引用，如下图所示，添加上文中C#项目生成的dll文件即可。

接下来添加OpenCvSharp，此处通过NuGet Package安装即可，此处主要安装以下两个程序包即可：

|---------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------|
| | |

配置好项目后，项目的配置文件如下所示：

xml 复制代码

<Project Sdk="Microsoft.NET.Sdk">

  <PropertyGroup>
    <OutputType>Exe</OutputType>
    <TargetFramework>net6.0</TargetFramework>
    <RootNamespace>TensorRT_CSharp_API_demo</RootNamespace>
    <ImplicitUsings>enable</ImplicitUsings>
    <Nullable>enable</Nullable>
  </PropertyGroup>

  <ItemGroup>
    <PackageReference Include="OpenCvSharp4.Extensions" Version="4.9.0.20240103" />
    <PackageReference Include="OpenCvSharp4.Windows" Version="4.9.0.20240103" />
  </ItemGroup>

  <ItemGroup>
    <Reference Include="TensorRtSharp">
      <HintPath>E:\GitSpace\TensorRT-CSharp-API\src\TensorRtSharp\bin\Release\net6.0\TensorRtSharp.dll</HintPath>
    </Reference>
  </ItemGroup>

</Project>

4.2 添加推理代码

此处演示一个简单的图像分类项目，以Yolov8-cls项目为例：

(1) 转换engine模型

动态输入的模型在进行格式转换时，需要指定模型推理形状至此的范围，minShapes表示模型推理支持的最小形状，optShapes表示模型推理支持的最佳形状，maxShapes表示模型推理支持的最大形状，模型转换需要消耗较多时间，最终转换成功后会在模型同级目录下生成相同名字的.engine文件。

csharp 复制代码

Dims minShapes = new Dims(1, 3, 224, 224);
Dims optShapes = new Dims(10, 3, 224, 224);
Dims maxShapes = new Dims(20, 3, 224, 224);
Nvinfer.OnnxToEngine(onnxPath, 20, "images", minShapes, optShapes, maxShapes);

(2) 定义模型预测方法

下面代码是定义的Yolov8-cls模型的预测方法，该方法支持动态Bath输入模型推理，可以根据用户输入图片数量，自动设置输入Bath，然后进行推理。

下面代码与上一篇文章中的代码差异主要是增加了predictor.SetBindingDimensions("images", new Dims(batchNum, 3, 224, 224));这一句代码。同时在初始化时，设置最大支持20Bath，这与上文模型转换时设置的一致。

csharp 复制代码

public class Yolov8Cls
{
    public Dims InputDims;
    public int BatchNum;
    private Nvinfer predictor;
    public Yolov8Cls(string enginePath)
    {
        predictor = new Nvinfer(enginePath, 20);
        InputDims = predictor.GetBindingDimensions("images");
    }
    public void Predict(List<Mat> images)
    {
        BatchNum = images.Count;
        for (int begImgNo = 0; begImgNo < images.Count; begImgNo += BatchNum)
        {
            DateTime start = DateTime.Now;
            int endImgNo = Math.Min(images.Count, begImgNo + BatchNum);
            int batchNum = endImgNo - begImgNo;
            List<Mat> normImgBatch = new List<Mat>();
            int imageLen = 3 * 224 * 224;
            float[] inputData = new float[BatchNum * imageLen];
            for (int ino = begImgNo; ino < endImgNo; ino++)
            {
                Mat input_mat = CvDnn.BlobFromImage(images[ino], 1.0 / 255.0, new OpenCvSharp.Size(224, 224), 0, true, false);
                float[] data = new float[imageLen];
                Marshal.Copy(input_mat.Ptr(0), data, 0, imageLen);
                Array.Copy(data, 0, inputData, ino * imageLen, imageLen);
            }
            predictor.SetBindingDimensions("images", new Dims(batchNum, 3, 224, 224));
            predictor.LoadInferenceData("images", inputData);
            DateTime end = DateTime.Now;
            Console.WriteLine("[ INFO ] Input image data processing time: " + (end - start).TotalMilliseconds + " ms.");
            predictor.infer();
            start = DateTime.Now;
            predictor.infer();
            end = DateTime.Now;
            Console.WriteLine("[ INFO ] Model inference time: " + (end - start).TotalMilliseconds + " ms.");
            start = DateTime.Now;

            float[] outputData = predictor.GetInferenceResult("output0");
            for (int i = 0; i < batchNum; ++i)
            {
                Console.WriteLine(string.Format("[ INFO ] Classification Top {0} result : ", 2));
                float[] data = new float[1000];
                Array.Copy(outputData, i * 1000, data, 0, 1000);
                List<int> sortResult = Argsort(new List<float>(data));
                for (int j = 0; j < 2; ++j)
                {
                    string msg = "";
                    msg += ("index: " + sortResult[j] + "\t");
                    msg += ("score: " + data[sortResult[j]] + "\t");
                    Console.WriteLine("[ INFO ] " + msg);
                }
            }
            end = DateTime.Now;
            Console.WriteLine("[ INFO ] Inference result processing time: " + (end - start).TotalMilliseconds + " ms.\n");
        }
    }
    public static List<int> Argsort(List<float> array)
    {
        int arrayLen = array.Count;
        List<float[]> newArray = new List<float[]> { };
        for (int i = 0; i < arrayLen; i++)
        {
            newArray.Add(new float[] { array[i], i });
        }
        newArray.Sort((a, b) => b[0].CompareTo(a[0]));
        List<int> arrayIndex = new List<int>();
        foreach (float[] item in newArray)
        {
            arrayIndex.Add((int)item[1]);
        }
        return arrayIndex;
    }
}

(3) 预测方法调用

下面是上述定义的预测方法，为了测试不同Bath性能，此处读取了多张图片，并分别预测不同张数图片，如下所示：

csharp 复制代码

Yolov8Cls yolov8Cls = new Yolov8Cls("E:\\Model\\yolov8\\yolov8s-cls_b.engine");
Mat image1 = Cv2.ImRead("E:\\ModelData\\image\\demo_4.jpg");
Mat image2 = Cv2.ImRead("E:\\ModelData\\image\\demo_5.jpg");
Mat image3 = Cv2.ImRead("E:\\ModelData\\image\\demo_6.jpg");
Mat image4 = Cv2.ImRead("E:\\ModelData\\image\\demo_7.jpg");
Mat image5 = Cv2.ImRead("E:\\ModelData\\image\\demo_8.jpg");

yolov8Cls.Predict(new List<Mat> { image1, image2 });

yolov8Cls.Predict(new List<Mat> { image1, image2, image3 });

yolov8Cls.Predict(new List<Mat> { image1, image2, image3, image4 });

yolov8Cls.Predict(new List<Mat> { image1, image2, image3, image4, image5 });

4.3 项目演示

配置好项目并编写好代码后，运行该项目，项目输出如下所示：

shell 复制代码

[ INFO ] Input image data processing time: 5.5277 ms.
[ INFO ] Model inference time: 1.3685 ms.
[ INFO ] Classification Top 2 result :
[ INFO ] index: 386     score: 0.8754883
[ INFO ] index: 385     score: 0.08013916
[ INFO ] Classification Top 2 result :
[ INFO ] index: 293     score: 0.89160156
[ INFO ] index: 276     score: 0.05480957
[ INFO ] Inference result processing time: 3.0823 ms.

[ INFO ] Input image data processing time: 2.7356 ms.
[ INFO ] Model inference time: 1.4435 ms.
[ INFO ] Classification Top 2 result :
[ INFO ] index: 386     score: 0.8754883
[ INFO ] index: 385     score: 0.08013916
[ INFO ] Classification Top 2 result :
[ INFO ] index: 293     score: 0.89160156
[ INFO ] index: 276     score: 0.05480957
[ INFO ] Classification Top 2 result :
[ INFO ] index: 14      score: 0.99853516
[ INFO ] index: 88      score: 0.0006980896
[ INFO ] Inference result processing time: 1.5137 ms.

[ INFO ] Input image data processing time: 3.7277 ms.
[ INFO ] Model inference time: 1.5285 ms.
[ INFO ] Classification Top 2 result :
[ INFO ] index: 386     score: 0.8754883
[ INFO ] index: 385     score: 0.08013916
[ INFO ] Classification Top 2 result :
[ INFO ] index: 293     score: 0.89160156
[ INFO ] index: 276     score: 0.05480957
[ INFO ] Classification Top 2 result :
[ INFO ] index: 14      score: 0.99853516
[ INFO ] index: 88      score: 0.0006980896
[ INFO ] Classification Top 2 result :
[ INFO ] index: 294     score: 0.96533203
[ INFO ] index: 269     score: 0.0124435425
[ INFO ] Inference result processing time: 2.7328 ms.

[ INFO ] Input image data processing time: 4.063 ms.
[ INFO ] Model inference time: 1.6947 ms.
[ INFO ] Classification Top 2 result :
[ INFO ] index: 386     score: 0.8754883
[ INFO ] index: 385     score: 0.08013916
[ INFO ] Classification Top 2 result :
[ INFO ] index: 293     score: 0.89160156
[ INFO ] index: 276     score: 0.05480957
[ INFO ] Classification Top 2 result :
[ INFO ] index: 14      score: 0.99853516
[ INFO ] index: 88      score: 0.0006980896
[ INFO ] Classification Top 2 result :
[ INFO ] index: 294     score: 0.96533203
[ INFO ] index: 269     score: 0.0124435425
[ INFO ] Classification Top 2 result :
[ INFO ] index: 127     score: 0.9008789
[ INFO ] index: 128     score: 0.07745361
[ INFO ] Inference result processing time: 3.5664 ms.

通过上面输出可以看出，不同Bath模型推理时间在1.3685~1.6947ms，大大提升了模型的推理速度。

5. 总结

在本项目中，我们扩展了TensorRT C# API 接口，使其支持动态输入模型。并结合分类模型部署流程向大家展示了TensorRT C# API 的使用方式，方便大家快速上手使用。

为了方便各位开发者使用，此处开发了配套的演示项目，主要是基于Yolov8开发的目标检测、目标分割、人体关键点识别、图像分类以及旋转目标识别，并且支持动态输入模型，用户可以同时推理任意张图像。

Yolov8 Det 目标检测项目源码：

https://github.com/guojin-yan/TensorRT-CSharp-API-Samples/blob/master/model_samples/yolov8_custom_dynamic/Yolov8Det.cs
Yolov8 Seg 目标分割项目源码：

https://github.com/guojin-yan/TensorRT-CSharp-API-Samples/blob/master/model_samples/yolov8_custom_dynamic/Yolov8Seg.cs
Yolov8 Pose 人体关键点识别项目源码：

https://github.com/guojin-yan/TensorRT-CSharp-API-Samples/blob/master/model_samples/yolov8_custom_dynamic/Yolov8Pose.cs
Yolov8 Cls 图像分类项目源码：

https://github.com/guojin-yan/TensorRT-CSharp-API-Samples/blob/master/model_samples/yolov8_custom_dynamic/Yolov8Cls.cs
Yolov8 Obb 旋转目标识别项目源码：

https://github.com/guojin-yan/TensorRT-CSharp-API-Samples/blob/master/model_samples/yolov8_custom_dynamic/Yolov8Obb.cs

同时对本项目开发的案例进行了时间测试，以下时间只是程序运行一次的时间，测试环境为：

CPU：i7-165G7
CUDA型号：12.2
Cudnn：8.9.3
TensorRT：8.6.1.6

Model	Batch	数据预处理 (ms)	模型推理 (ms)	结果后处理 (ms)
Yolov8s-Det	1	16.6	4.6	13.1
	4	38.0	12.4	32.4
	8	70.5	23.0	80.1
Yolov8s-Obb	1	28.7	8.9	17.7
	4	81.7	25.9	67.4
	8	148.4	44.6	153.0
Yolov8s-Seg	1	15.4	5.4	67.4
	4	37.3	15.5	220.6
	8	78.7	26.9	433.6
Yolov8s-Pose	1	15.1	5.2	8.7
	4	39.2	13.2	14.3
	8	67.8	23.1	27.7
Yolov8s-Cls	1	9.9	1.3	1.9
	4	14.7	1.5	2.3
	8	22.6	2.0	2.9

最后如果各位开发者在使用中有任何问题，欢迎大家与我联系。