C# Onnx E2Pose人体关键点检测

C# Onnx E2Pose人体关键点检测

 

目录

效果

模型信息

项目

代码

下载

效果

模型信息

Inputs
-------------------------
name：inputimg
tensor：Float[1, 3, 512, 512]
---------------------------------------------------------------

Outputs
-------------------------
name：kvxy/concat
tensor：Float[1, 341, 17, 3]
name：pv/concat
tensor：Float[1, 341, 1, 1]
---------------------------------------------------------------

项目

代码

using Microsoft.ML.OnnxRuntime;
using Microsoft.ML.OnnxRuntime.Tensors;
using OpenCvSharp;
using System;
using System.Collections.Generic;
using System.Drawing;
using System.Drawing.Imaging;
using System.Linq;
using System.Windows.Forms;

namespace Onnx_Demo
{
    public partial class Form1 : Form
    {
        public Form1()
        {
            InitializeComponent();
        }

        string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";
        string image_path = "";
        string startupPath;
        DateTime dt1 = DateTime.Now;
        DateTime dt2 = DateTime.Now;
        string model_path;
        Mat image;
        Mat result_image;
        SessionOptions options;
        InferenceSession onnx_session;
        Tensor input_tensor;
        List input_container;
        IDisposableReadOnlyCollection result_infer;
        DisposableNamedOnnxValue[] results_onnxvalue;
        Tensor result_tensors;
        int inpHeight, inpWidth;
        float confThreshold;

        int[] connect_list = { 0, 1, 0, 2, 1, 3, 2, 4, 3, 5, 4, 6, 5, 6, 5, 7, 7, 9, 6, 8, 8, 10, 5, 11, 6, 12, 11, 12, 11, 13, 13, 15, 12, 14, 14, 16 };

        private void button1_Click(object sender, EventArgs e)
        {
            OpenFileDialog ofd = new OpenFileDialog();
            ofd.Filter = fileFilter;
            if (ofd.ShowDialog() != DialogResult.OK) return;
            pictureBox1.Image = null;
            image_path = ofd.FileName;
            pictureBox1.Image = new Bitmap(image_path);
            textBox1.Text = "";
            image = new Mat(image_path);
            pictureBox2.Image = null;
        }

        unsafe private void button2_Click(object sender, EventArgs e)
        {
            if (image_path == "")
            {
                return;
            }

            button2.Enabled = false;
            pictureBox2.Image = null;
            textBox1.Text = "";
            Application.DoEvents();

            //读图片
            image = new Mat(image_path);

            //将图片转为RGB通道
            Mat image_rgb = new Mat();
            Cv2.CvtColor(image, image_rgb, ColorConversionCodes.BGR2RGB);

            Cv2.Resize(image_rgb, image_rgb, new OpenCvSharp.Size(inpHeight, inpWidth));

            //输入Tensor
            input_tensor = new DenseTensor(new[] { 1, 3, inpHeight, inpWidth });
            for (int y = 0; y < image_rgb.Height; y++)
            {
                for (int x = 0; x < image_rgb.Width; x++)
                {
                    input_tensor[0, 0, y, x] = image_rgb.At(y, x)[0];
                    input_tensor[0, 1, y, x] = image_rgb.At(y, x)[1];
                    input_tensor[0, 2, y, x] = image_rgb.At(y, x)[2];
                }
            }

            //将 input_tensor 放入一个输入参数的容器，并指定名称
            input_container.Add(NamedOnnxValue.CreateFromTensor("inputimg", input_tensor));

            dt1 = DateTime.Now;
            //运行 Inference 并获取结果
            result_infer = onnx_session.Run(input_container);
            dt2 = DateTime.Now;

            // 将输出结果转为DisposableNamedOnnxValue数组
            results_onnxvalue = result_infer.ToArray();

            float[] kpt = results_onnxvalue[0].AsTensor().ToArray();
            float[] pv = results_onnxvalue[1].AsTensor().ToArray();

            float[] temp = new float[51];

            int num_proposal = 341;
            int num_pts = 17;
            int len = num_pts * 3;

            List> results = new List>();
            for (int i = 0; i < num_proposal; i++)
            {
                Array.Copy(kpt, i * 51, temp, 0, 51);

                if (pv[i] >= confThreshold)
                {
                    List human_pts = new List();
                    for (int ii = 0; ii < num_pts * 2; ii++)
                    {
                        human_pts.Add(0);
                    }

                    for (int j = 0; j < num_pts; j++)
                    {
                        float score = temp[j * 3] * 2;
                        if (score >= confThreshold)
                        {
                            float x = temp[j * 3 + 1] * image.Cols;
                            float y = temp[j * 3 + 2] * image.Rows;
                            human_pts[j * 2] = (int)x;
                            human_pts[j * 2 + 1] = (int)y;
                        }
                    }
                    results.Add(human_pts);
                }
            }

            result_image = image.Clone();
            int start_x = 0;
            int start_y = 0;
            int end_x = 0;
            int end_y = 0;

            for (int i = 0; i < results.Count; ++i)
            {
                for (int j = 0; j < num_pts; j++)
                {
                    int cx = results[i][j * 2];
                    int cy = results[i][j * 2 + 1];
                    if (cx > 0 && cy > 0)
                    {
                        Cv2.Circle(result_image, new OpenCvSharp.Point(cx, cy), 3, new Scalar(0, 0, 255), -1, LineTypes.AntiAlias);
                    }

                    start_x = results[i][connect_list[j * 2] * 2];
                    start_y = results[i][connect_list[j * 2] * 2 + 1];
                    end_x = results[i][connect_list[j * 2 + 1] * 2];
                    end_y = results[i][connect_list[j * 2 + 1] * 2 + 1];

                    if (start_x > 0 && start_y > 0 && end_x > 0 && end_y > 0)
                    {
                        Cv2.Line(result_image, new OpenCvSharp.Point(start_x, start_y), new OpenCvSharp.Point(end_x, end_y), new Scalar(0, 255, 0), 2, LineTypes.AntiAlias);
                    }
                }

                start_x = results[i][connect_list[num_pts * 2] * 2];
                start_y = results[i][connect_list[num_pts * 2] * 2 + 1];
                end_x = results[i][connect_list[num_pts * 2 + 1] * 2];
                end_y = results[i][connect_list[num_pts * 2 + 1] * 2 + 1];

                if (start_x > 0 && start_y > 0 && end_x > 0 && end_y > 0)
                {
                    Cv2.Line(result_image, new OpenCvSharp.Point(start_x, start_y), new OpenCvSharp.Point(end_x, end_y), new Scalar(0, 255, 0), 2, LineTypes.AntiAlias);
                }
            }

            pictureBox2.Image = new Bitmap(result_image.ToMemoryStream());
            textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";

            button2.Enabled = true;

        }

        private void Form1_Load(object sender, EventArgs e)
        {
            startupPath = System.Windows.Forms.Application.StartupPath;
            model_path = "model/e2epose_resnet50_1x3x512x512.onnx";

            // 创建输出会话，用于输出模型读取信息
            options = new SessionOptions();
            options.LogSeverityLevel = OrtLoggingLevel.ORT_LOGGING_LEVEL_INFO;
            options.AppendExecutionProvider_CPU(0);// 设置为CPU上运行

            // 创建推理模型类，读取本地模型文件
            onnx_session = new InferenceSession(model_path, options);//model_path 为onnx模型文件的路径

            // 创建输入容器
            input_container = new List();

            image_path = "test_img/1.jpg";
            pictureBox1.Image = new Bitmap(image_path);
            image = new Mat(image_path);

            inpWidth = 512;
            inpHeight = 512;

            confThreshold = 0.5f;

        }

        private void pictureBox1_DoubleClick(object sender, EventArgs e)
        {
            Common.ShowNormalImg(pictureBox1.Image);
        }

        private void pictureBox2_DoubleClick(object sender, EventArgs e)
        {
            Common.ShowNormalImg(pictureBox2.Image);
        }

        SaveFileDialog sdf = new SaveFileDialog();
        private void button3_Click(object sender, EventArgs e)
        {
            if (pictureBox2.Image == null)
            {
                return;
            }
            Bitmap output = new Bitmap(pictureBox2.Image);
            sdf.Title = "保存";
            sdf.Filter = "Images (*.jpg)|*.jpg|Images (*.png)|*.png|Images (*.bmp)|*.bmp";
            if (sdf.ShowDialog() == DialogResult.OK)
            {
                switch (sdf.FilterIndex)
                {
                    case 1:
                        {
                            output.Save(sdf.FileName, ImageFormat.Jpeg);
                            break;
                        }
                    case 2:
                        {
                            output.Save(sdf.FileName, ImageFormat.Png);
                            break;
                        }
                    case 3:
                        {
                            output.Save(sdf.FileName, ImageFormat.Bmp);
                            break;
                        }
                }
                MessageBox.Show("保存成功，位置：" + sdf.FileName);
            }
        }
    }
}

  1. using Microsoft.ML.OnnxRuntime;
  2. using Microsoft.ML.OnnxRuntime.Tensors;
  3. using OpenCvSharp;
  4. using System;
  5. using System.Collections.Generic;
  6. using System.Drawing;
  7. using System.Drawing.Imaging;
  8. using System.Linq;
  9. using System.Windows.Forms;
  10.  
  11. namespace Onnx_Demo
  12. {
  13.     public partial class Form1 : Form
  14.     {
  15.         public Form1()
  16.         {
  17.             InitializeComponent();
  18.         }
  19.  
  20.         string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";
  21.         string image_path = "";
  22.         string startupPath;
  23.         DateTime dt1 = DateTime.Now;
  24.         DateTime dt2 = DateTime.Now;
  25.         string model_path;
  26.         Mat image;
  27.         Mat result_image;
  28.         SessionOptions options;
  29.         InferenceSession onnx_session;
  30.         Tensor<float> input_tensor;
  31.         List<NamedOnnxValue> input_container;
  32.         IDisposableReadOnlyCollection<DisposableNamedOnnxValue> result_infer;
  33.         DisposableNamedOnnxValue[] results_onnxvalue;
  34.         Tensor<float> result_tensors;
  35.         int inpHeight, inpWidth;
  36.         float confThreshold;
  37.  
  38.         int[] connect_list = { 0, 1, 0, 2, 1, 3, 2, 4, 3, 5, 4, 6, 5, 6, 5, 7, 7, 9, 6, 8, 8, 10, 5, 11, 6, 12, 11, 12, 11, 13, 13, 15, 12, 14, 14, 16 };
  39.  
  40.         private void button1_Click(object sender, EventArgs e)
  41.         {
  42.             OpenFileDialog ofd = new OpenFileDialog();
  43.             ofd.Filter = fileFilter;
  44.             if (ofd.ShowDialog() != DialogResult.OK) return;
  45.             pictureBox1.Image = null;
  46.             image_path = ofd.FileName;
  47.             pictureBox1.Image = new Bitmap(image_path);
  48.             textBox1.Text = "";
  49.             image = new Mat(image_path);
  50.             pictureBox2.Image = null;
  51.         }
  52.  
  53.         unsafe private void button2_Click(object sender, EventArgs e)
  54.         {
  55.             if (image_path == "")
  56.             {
  57.                 return;
  58.             }
  59.  
  60.             button2.Enabled = false;
  61.             pictureBox2.Image = null;
  62.             textBox1.Text = "";
  63.             Application.DoEvents();
  64.  
  65.             //读图片
  66.             image = new Mat(image_path);
  67.  
  68.             //将图片转为RGB通道
  69.             Mat image_rgb = new Mat();
  70.             Cv2.CvtColor(image, image_rgb, ColorConversionCodes.BGR2RGB);
  71.  
  72.             Cv2.Resize(image_rgb, image_rgb, new OpenCvSharp.Size(inpHeight, inpWidth));
  73.  
  74.             //输入Tensor
  75.             input_tensor = new DenseTensor<float>(new[] { 1, 3, inpHeight, inpWidth });
  76.             for (int y = 0; y < image_rgb.Height; y++)
  77.             {
  78.                 for (int x = 0; x < image_rgb.Width; x++)
  79.                 {
  80.                     input_tensor[0, 0, y, x] = image_rgb.At<Vec3b>(y, x)[0];
  81.                     input_tensor[0, 1, y, x] = image_rgb.At<Vec3b>(y, x)[1];
  82.                     input_tensor[0, 2, y, x] = image_rgb.At<Vec3b>(y, x)[2];
  83.                 }
  84.             }
  85.  
  86.             //将 input_tensor 放入一个输入参数的容器，并指定名称
  87.             input_container.Add(NamedOnnxValue.CreateFromTensor("inputimg", input_tensor));
  88.  
  89.             dt1 = DateTime.Now;
  90.             //运行 Inference 并获取结果
  91.             result_infer = onnx_session.Run(input_container);
  92.             dt2 = DateTime.Now;
  93.  
  94.             // 将输出结果转为DisposableNamedOnnxValue数组
  95.             results_onnxvalue = result_infer.ToArray();
  96.  
  97.             float[] kpt = results_onnxvalue[0].AsTensor<float>().ToArray();
  98.             float[] pv = results_onnxvalue[1].AsTensor<float>().ToArray();
  99.  
  100.             float[] temp = new float[51];
  101.  
  102.             int num_proposal = 341;
  103.             int num_pts = 17;
  104.             int len = num_pts * 3;
  105.  
  106.             List<List<int>> results = new List>();
  107.             for (int i = 0; i < num_proposal; i++)
  108.             {
  109.                 Array.Copy(kpt, i * 51, temp, 0, 51);
  110.  
  111.                 if (pv[i] >= confThreshold)
  112.                 {
  113.                     List<int> human_pts = new List<int>();
  114.                     for (int ii = 0; ii < num_pts * 2; ii++)
  115.                     {
  116.                         human_pts.Add(0);
  117.                     }
  118.  
  119.                     for (int j = 0; j < num_pts; j++)
  120.                     {
  121.                         float score = temp[j * 3] * 2;
  122.                         if (score >= confThreshold)
  123.                         {
  124.                             float x = temp[j * 3 + 1] * image.Cols;
  125.                             float y = temp[j * 3 + 2] * image.Rows;
  126.                             human_pts[j * 2] = (int)x;
  127.                             human_pts[j * 2 + 1] = (int)y;
  128.                         }
  129.                     }
  130.                     results.Add(human_pts);
  131.                 }
  132.             }
  133.  
  134.             result_image = image.Clone();
  135.             int start_x = 0;
  136.             int start_y = 0;
  137.             int end_x = 0;
  138.             int end_y = 0;
  139.  
  140.             for (int i = 0; i < results.Count; ++i)
  141.             {
  142.                 for (int j = 0; j < num_pts; j++)
  143.                 {
  144.                     int cx = results[i][j * 2];
  145.                     int cy = results[i][j * 2 + 1];
  146.                     if (cx > 0 && cy > 0)
  147.                     {
  148.                         Cv2.Circle(result_image, new OpenCvSharp.Point(cx, cy), 3, new Scalar(0, 0, 255), -1, LineTypes.AntiAlias);
  149.                     }
  150.  
  151.                     start_x = results[i][connect_list[j * 2] * 2];
  152.                     start_y = results[i][connect_list[j * 2] * 2 + 1];
  153.                     end_x = results[i][connect_list[j * 2 + 1] * 2];
  154.                     end_y = results[i][connect_list[j * 2 + 1] * 2 + 1];
  155.  
  156.                     if (start_x > 0 && start_y > 0 && end_x > 0 && end_y > 0)
  157.                     {
  158.                         Cv2.Line(result_image, new OpenCvSharp.Point(start_x, start_y), new OpenCvSharp.Point(end_x, end_y), new Scalar(0, 255, 0), 2, LineTypes.AntiAlias);
  159.                     }
  160.                 }
  161.  
  162.                 start_x = results[i][connect_list[num_pts * 2] * 2];
  163.                 start_y = results[i][connect_list[num_pts * 2] * 2 + 1];
  164.                 end_x = results[i][connect_list[num_pts * 2 + 1] * 2];
  165.                 end_y = results[i][connect_list[num_pts * 2 + 1] * 2 + 1];
  166.  
  167.                 if (start_x > 0 && start_y > 0 && end_x > 0 && end_y > 0)
  168.                 {
  169.                     Cv2.Line(result_image, new OpenCvSharp.Point(start_x, start_y), new OpenCvSharp.Point(end_x, end_y), new Scalar(0, 255, 0), 2, LineTypes.AntiAlias);
  170.                 }
  171.             }
  172.  
  173.             pictureBox2.Image = new Bitmap(result_image.ToMemoryStream());
  174.             textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";
  175.  
  176.             button2.Enabled = true;
  177.  
  178.         }
  179.  
  180.         private void Form1_Load(object sender, EventArgs e)
  181.         {
  182.             startupPath = System.Windows.Forms.Application.StartupPath;
  183.             model_path = "model/e2epose_resnet50_1x3x512x512.onnx";
  184.  
  185.             // 创建输出会话，用于输出模型读取信息
  186.             options = new SessionOptions();
  187.             options.LogSeverityLevel = OrtLoggingLevel.ORT_LOGGING_LEVEL_INFO;
  188.             options.AppendExecutionProvider_CPU(0);// 设置为CPU上运行
  189.  
  190.             // 创建推理模型类，读取本地模型文件
  191.             onnx_session = new InferenceSession(model_path, options);//model_path 为onnx模型文件的路径
  192.  
  193.             // 创建输入容器
  194.             input_container = new List<NamedOnnxValue>();
  195.  
  196.             image_path = "test_img/1.jpg";
  197.             pictureBox1.Image = new Bitmap(image_path);
  198.             image = new Mat(image_path);
  199.  
  200.             inpWidth = 512;
  201.             inpHeight = 512;
  202.  
  203.             confThreshold = 0.5f;
  204.  
  205.         }
  206.  
  207.         private void pictureBox1_DoubleClick(object sender, EventArgs e)
  208.         {
  209.             Common.ShowNormalImg(pictureBox1.Image);
  210.         }
  211.  
  212.         private void pictureBox2_DoubleClick(object sender, EventArgs e)
  213.         {
  214.             Common.ShowNormalImg(pictureBox2.Image);
  215.         }
  216.  
  217.         SaveFileDialog sdf = new SaveFileDialog();
  218.         private void button3_Click(object sender, EventArgs e)
  219.         {
  220.             if (pictureBox2.Image == null)
  221.             {
  222.                 return;
  223.             }
  224.             Bitmap output = new Bitmap(pictureBox2.Image);
  225.             sdf.Title = "保存";
  226.             sdf.Filter = "Images (*.jpg)|*.jpg|Images (*.png)|*.png|Images (*.bmp)|*.bmp";
  227.             if (sdf.ShowDialog() == DialogResult.OK)
  228.             {
  229.                 switch (sdf.FilterIndex)
  230.                 {
  231.                     case 1:
  232.                         {
  233.                             output.Save(sdf.FileName, ImageFormat.Jpeg);
  234.                             break;
  235.                         }
  236.                     case 2:
  237.                         {
  238.                             output.Save(sdf.FileName, ImageFormat.Png);
  239.                             break;
  240.                         }
  241.                     case 3:
  242.                         {
  243.                             output.Save(sdf.FileName, ImageFormat.Bmp);
  244.                             break;
  245.                         }
  246.                 }
  247.                 MessageBox.Show("保存成功，位置：" + sdf.FileName);
  248.             }
  249.         }
  250.     }
  251. }

下载

源码下载

天天代码码天天
微信公众号
.NET 人工智能实践
注：本文转载自blog.csdn.net的天天代码码天天的文章"https://lw112190.blog.csdn.net/article/details/139476332"。版权归原作者所有，此博客不拥有其著作权，亦不承担相应法律责任。如有侵权，请联系我们删除。
复制链接
相关推荐
发表评论

评论记录：

未查询到任何数据！