2025年7月13日 星期日 5:53am

C# OpenCvSharp DNN 部署yoloX

目录

效果

模型信息

项目

代码

下载

C# OpenCvSharp DNN 部署yoloX

效果

模型信息

Inputs
-------------------------
name：images
tensor：Float[1, 3, 640, 640]
---------------------------------------------------------------

Outputs
-------------------------
name：output
tensor：Float[1, 8400, 85]
---------------------------------------------------------------

项目

代码

using OpenCvSharp;
using OpenCvSharp.Dnn;
using System;
using System.Collections.Generic;
using System.Drawing;
using System.IO;
using System.Linq;
using System.Windows.Forms;

namespace OpenCvSharp_DNN_Demo
{
    public partial class frmMain : Form
    {
        public frmMain()
        {
            InitializeComponent();
        }

        string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";
        string image_path = "";

        DateTime dt1 = DateTime.Now;
        DateTime dt2 = DateTime.Now;

        float prob_threshold;
        float nms_threshold;

        float[] stride = new float[3] { 8.0f, 16.0f, 32.0f };

        int[] input_shape = new int[] { 640, 640 };   // height, width

        float[] mean = new float[3] { 0.485f, 0.456f, 0.406f };
        float[] std = new float[3] { 0.229f, 0.224f, 0.225f };
        float scale = 1.0f;

        string modelpath;

        int inpHeight;
        int inpWidth;

        List class_names;
        int num_class;

        Net opencv_net;
        Mat BN_image;

        Mat image;
        Mat result_image;

        public Mat Normalize(Mat src)
        {
            Cv2.CvtColor(src, src, ColorConversionCodes.BGR2RGB);
            Mat[] bgr = src.Split();
            for (int i = 0; i < bgr.Length; ++i)
            {
                bgr[i].ConvertTo(bgr[i], MatType.CV_32FC1, 1.0 / (255.0 * std[i]), (0.0 - mean[i]) / std[i]);
            }
            Cv2.Merge(bgr, src);
            foreach (Mat channel in bgr)
            {
                channel.Dispose();
            }
            return src;
        }

        private void button1_Click(object sender, EventArgs e)
        {
            OpenFileDialog ofd = new OpenFileDialog();
            ofd.Filter = fileFilter;
            if (ofd.ShowDialog() != DialogResult.OK) return;

            pictureBox1.Image = null;
            pictureBox2.Image = null;
            textBox1.Text = "";

            image_path = ofd.FileName;
            pictureBox1.Image = new Bitmap(image_path);
            image = new Mat(image_path);
        }

        private void Form1_Load(object sender, EventArgs e)
        {
            prob_threshold = 0.6f;
            nms_threshold = 0.6f;

            modelpath = "model/yolox_s.onnx";

            inpHeight = 640;
            inpWidth = 640;

            opencv_net = CvDnn.ReadNetFromOnnx(modelpath);

            class_names = new List();
            StreamReader sr = new StreamReader("model/coco.names");
            string line;
            while ((line = sr.ReadLine()) != null)
            {
                class_names.Add(line);
            }
            num_class = class_names.Count();

            image_path = "test_img/dog.jpg";
            pictureBox1.Image = new Bitmap(image_path);

        }

        Mat ResizeImage(Mat srcimg)
        {

            float r = (float)Math.Min(input_shape[1] / (srcimg.Cols * 1.0), input_shape[0] / (srcimg.Rows * 1.0));
            scale = r;
            int unpad_w = (int)(r * srcimg.Cols);
            int unpad_h = (int)(r * srcimg.Rows);
            Mat re = new Mat(unpad_h, unpad_w, MatType.CV_8UC3);
            Cv2.Resize(srcimg, re, new OpenCvSharp.Size(unpad_w, unpad_h));
            Mat outMat = new Mat(input_shape[1], input_shape[0], MatType.CV_8UC3, new Scalar(114, 114, 114));
            re.CopyTo(new Mat(outMat, new Rect(0, 0, re.Cols, re.Rows)));
            return outMat;
        }


        private unsafe void button2_Click(object sender, EventArgs e)
        {
            if (image_path == "")
            {
                return;
            }
            textBox1.Text = "检测中，请稍等……";
            pictureBox2.Image = null;
            Application.DoEvents();

            image = new Mat(image_path);

            Mat dstimg = ResizeImage(image);

            dstimg = Normalize(dstimg);

            BN_image = CvDnn.BlobFromImage(dstimg);

            //配置图片输入数据
            opencv_net.SetInput(BN_image);

            //模型推理，读取推理结果
            Mat[] outs = new Mat[] { new Mat() };
            string[] outBlobNames = opencv_net.GetUnconnectedOutLayersNames().ToArray();

            dt1 = DateTime.Now;

            opencv_net.Forward(outs, outBlobNames);

            dt2 = DateTime.Now;

            int num_proposal = outs[0].Size(1);
            outs[0] = outs[0].Reshape(0, num_proposal);

            float* pdata = (float*)outs[0].Data;

            int row_ind = 0;
            int nout = num_class + 5;

            List boxes = new List();
            List confidences = new List();
            List classIds = new List();

            for (int n = 0; n < 3; n++)
            {
                int num_grid_x = (int)(inpWidth / stride[n]);
                int num_grid_y = (int)(inpHeight / stride[n]);

                for (int i = 0; i < num_grid_y; i++)
                {
                    for (int j = 0; j < num_grid_x; j++)
                    {
                        float box_score = pdata[4];
                        Mat scores = outs[0].Row(row_ind).ColRange(5, outs[0].Cols);

                        double minVal, max_class_socre;
                        OpenCvSharp.Point minLoc, classIdPoint;
                        // Get the value and location of the maximum score
                        Cv2.MinMaxLoc(scores, out minVal, out max_class_socre, out minLoc, out classIdPoint);

                        int class_idx = classIdPoint.X;

                        float cls_score = pdata[5 + class_idx];
                        float box_prob = box_score * cls_score;
                        if (box_prob > prob_threshold)
                        {
                            float x_center = (pdata[0] + j) * stride[n];
                            float y_center = (pdata[1] + i) * stride[n];
                            float w = (float)(Math.Exp(pdata[2]) * stride[n]);
                            float h = (float)(Math.Exp(pdata[3]) * stride[n]);
                            float x0 = x_center - w * 0.5f;
                            float y0 = y_center - h * 0.5f;

                            classIds.Add(class_idx);
                            confidences.Add(box_prob);
                            boxes.Add(new Rect((int)x0, (int)y0, (int)w, (int)h));
                        }

                        pdata += nout;
                        row_ind++;
                    }
                }
            }

            int[] indices;
            CvDnn.NMSBoxes(boxes, confidences, prob_threshold, nms_threshold, out indices);

            result_image = image.Clone();

            for (int ii = 0; ii < indices.Length; ++ii)
            {
                int idx = indices[ii];
                Rect box = boxes[idx];

                // adjust offset to original unpadded
                float x0 = box.X / scale; ;
                float y0 = box.Y / scale; ;
                float x1 = (box.X + box.Width) / scale;
                float y1 = (box.Y + box.Height) / scale;

                // clip
                x0 = Math.Max(Math.Min(x0, (float)(image.Cols - 1)), 0.0f);
                y0 = Math.Max(Math.Min(y0, (float)(image.Rows - 1)), 0.0f);
                x1 = Math.Max(Math.Min(x1, (float)(image.Cols - 1)), 0.0f);
                y1 = Math.Max(Math.Min(y1, (float)(image.Rows - 1)), 0.0f);

                Cv2.Rectangle(result_image, new OpenCvSharp.Point(x0, y0), new OpenCvSharp.Point(x1, y1), new Scalar(0, 255, 0), 2);
                string label = class_names[classIds[idx]] + ":" + confidences[idx].ToString("0.00");
                Cv2.PutText(result_image, label, new OpenCvSharp.Point(x0, y0 - 5), HersheyFonts.HersheySimplex, 1, new Scalar(0, 0, 255), 2);
            }

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

        }

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

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

  1. using OpenCvSharp;
  2. using OpenCvSharp.Dnn;
  3. using System;
  4. using System.Collections.Generic;
  5. using System.Drawing;
  6. using System.IO;
  7. using System.Linq;
  8. using System.Windows.Forms;
  9.  
  10. namespace OpenCvSharp_DNN_Demo
  11. {
  12.     public partial class frmMain : Form
  13.     {
  14.         public frmMain()
  15.         {
  16.             InitializeComponent();
  17.         }
  18.  
  19.         string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";
  20.         string image_path = "";
  21.  
  22.         DateTime dt1 = DateTime.Now;
  23.         DateTime dt2 = DateTime.Now;
  24.  
  25.         float prob_threshold;
  26.         float nms_threshold;
  27.  
  28.         float[] stride = new float[3] { 8.0f, 16.0f, 32.0f };
  29.  
  30.         int[] input_shape = new int[] { 640, 640 };   // height, width
  31.  
  32.         float[] mean = new float[3] { 0.485f, 0.456f, 0.406f };
  33.         float[] std = new float[3] { 0.229f, 0.224f, 0.225f };
  34.         float scale = 1.0f;
  35.  
  36.         string modelpath;
  37.  
  38.         int inpHeight;
  39.         int inpWidth;
  40.  
  41.         List<string> class_names;
  42.         int num_class;
  43.  
  44.         Net opencv_net;
  45.         Mat BN_image;
  46.  
  47.         Mat image;
  48.         Mat result_image;
  49.  
  50.         public Mat Normalize(Mat src)
  51.         {
  52.             Cv2.CvtColor(src, src, ColorConversionCodes.BGR2RGB);
  53.             Mat[] bgr = src.Split();
  54.             for (int i = 0; i < bgr.Length; ++i)
  55.             {
  56.                 bgr[i].ConvertTo(bgr[i], MatType.CV_32FC1, 1.0 / (255.0 * std[i]), (0.0 - mean[i]) / std[i]);
  57.             }
  58.             Cv2.Merge(bgr, src);
  59.             foreach (Mat channel in bgr)
  60.             {
  61.                 channel.Dispose();
  62.             }
  63.             return src;
  64.         }
  65.  
  66.         private void button1_Click(object sender, EventArgs e)
  67.         {
  68.             OpenFileDialog ofd = new OpenFileDialog();
  69.             ofd.Filter = fileFilter;
  70.             if (ofd.ShowDialog() != DialogResult.OK) return;
  71.  
  72.             pictureBox1.Image = null;
  73.             pictureBox2.Image = null;
  74.             textBox1.Text = "";
  75.  
  76.             image_path = ofd.FileName;
  77.             pictureBox1.Image = new Bitmap(image_path);
  78.             image = new Mat(image_path);
  79.         }
  80.  
  81.         private void Form1_Load(object sender, EventArgs e)
  82.         {
  83.             prob_threshold = 0.6f;
  84.             nms_threshold = 0.6f;
  85.  
  86.             modelpath = "model/yolox_s.onnx";
  87.  
  88.             inpHeight = 640;
  89.             inpWidth = 640;
  90.  
  91.             opencv_net = CvDnn.ReadNetFromOnnx(modelpath);
  92.  
  93.             class_names = new List<string>();
  94.             StreamReader sr = new StreamReader("model/coco.names");
  95.             string line;
  96.             while ((line = sr.ReadLine()) != null)
  97.             {
  98.                 class_names.Add(line);
  99.             }
  100.             num_class = class_names.Count();
  101.  
  102.             image_path = "test_img/dog.jpg";
  103.             pictureBox1.Image = new Bitmap(image_path);
  104.  
  105.         }
  106.  
  107.         Mat ResizeImage(Mat srcimg)
  108.         {
  109.  
  110.             float r = (float)Math.Min(input_shape[1] / (srcimg.Cols * 1.0), input_shape[0] / (srcimg.Rows * 1.0));
  111.             scale = r;
  112.             int unpad_w = (int)(r * srcimg.Cols);
  113.             int unpad_h = (int)(r * srcimg.Rows);
  114.             Mat re = new Mat(unpad_h, unpad_w, MatType.CV_8UC3);
  115.             Cv2.Resize(srcimg, re, new OpenCvSharp.Size(unpad_w, unpad_h));
  116.             Mat outMat = new Mat(input_shape[1], input_shape[0], MatType.CV_8UC3, new Scalar(114, 114, 114));
  117.             re.CopyTo(new Mat(outMat, new Rect(0, 0, re.Cols, re.Rows)));
  118.             return outMat;
  119.         }
  120.  
  121.  
  122.         private unsafe void button2_Click(object sender, EventArgs e)
  123.         {
  124.             if (image_path == "")
  125.             {
  126.                 return;
  127.             }
  128.             textBox1.Text = "检测中，请稍等……";
  129.             pictureBox2.Image = null;
  130.             Application.DoEvents();
  131.  
  132.             image = new Mat(image_path);
  133.  
  134.             Mat dstimg = ResizeImage(image);
  135.  
  136.             dstimg = Normalize(dstimg);
  137.  
  138.             BN_image = CvDnn.BlobFromImage(dstimg);
  139.  
  140.             //配置图片输入数据
  141.             opencv_net.SetInput(BN_image);
  142.  
  143.             //模型推理，读取推理结果
  144.             Mat[] outs = new Mat[] { new Mat() };
  145.             string[] outBlobNames = opencv_net.GetUnconnectedOutLayersNames().ToArray();
  146.  
  147.             dt1 = DateTime.Now;
  148.  
  149.             opencv_net.Forward(outs, outBlobNames);
  150.  
  151.             dt2 = DateTime.Now;
  152.  
  153.             int num_proposal = outs[0].Size(1);
  154.             outs[0] = outs[0].Reshape(0, num_proposal);
  155.  
  156.             float* pdata = (float*)outs[0].Data;
  157.  
  158.             int row_ind = 0;
  159.             int nout = num_class + 5;
  160.  
  161.             List<Rect> boxes = new List<Rect>();
  162.             List<float> confidences = new List<float>();
  163.             List<int> classIds = new List<int>();
  164.  
  165.             for (int n = 0; n < 3; n++)
  166.             {
  167.                 int num_grid_x = (int)(inpWidth / stride[n]);
  168.                 int num_grid_y = (int)(inpHeight / stride[n]);
  169.  
  170.                 for (int i = 0; i < num_grid_y; i++)
  171.                 {
  172.                     for (int j = 0; j < num_grid_x; j++)
  173.                     {
  174.                         float box_score = pdata[4];
  175.                         Mat scores = outs[0].Row(row_ind).ColRange(5, outs[0].Cols);
  176.  
  177.                         double minVal, max_class_socre;
  178.                         OpenCvSharp.Point minLoc, classIdPoint;
  179.                         // Get the value and location of the maximum score
  180.                         Cv2.MinMaxLoc(scores, out minVal, out max_class_socre, out minLoc, out classIdPoint);
  181.  
  182.                         int class_idx = classIdPoint.X;
  183.  
  184.                         float cls_score = pdata[5 + class_idx];
  185.                         float box_prob = box_score * cls_score;
  186.                         if (box_prob > prob_threshold)
  187.                         {
  188.                             float x_center = (pdata[0] + j) * stride[n];
  189.                             float y_center = (pdata[1] + i) * stride[n];
  190.                             float w = (float)(Math.Exp(pdata[2]) * stride[n]);
  191.                             float h = (float)(Math.Exp(pdata[3]) * stride[n]);
  192.                             float x0 = x_center - w * 0.5f;
  193.                             float y0 = y_center - h * 0.5f;
  194.  
  195.                             classIds.Add(class_idx);
  196.                             confidences.Add(box_prob);
  197.                             boxes.Add(new Rect((int)x0, (int)y0, (int)w, (int)h));
  198.                         }
  199.  
  200.                         pdata += nout;
  201.                         row_ind++;
  202.                     }
  203.                 }
  204.             }
  205.  
  206.             int[] indices;
  207.             CvDnn.NMSBoxes(boxes, confidences, prob_threshold, nms_threshold, out indices);
  208.  
  209.             result_image = image.Clone();
  210.  
  211.             for (int ii = 0; ii < indices.Length; ++ii)
  212.             {
  213.                 int idx = indices[ii];
  214.                 Rect box = boxes[idx];
  215.  
  216.                 // adjust offset to original unpadded
  217.                 float x0 = box.X / scale; ;
  218.                 float y0 = box.Y / scale; ;
  219.                 float x1 = (box.X + box.Width) / scale;
  220.                 float y1 = (box.Y + box.Height) / scale;
  221.  
  222.                 // clip
  223.                 x0 = Math.Max(Math.Min(x0, (float)(image.Cols - 1)), 0.0f);
  224.                 y0 = Math.Max(Math.Min(y0, (float)(image.Rows - 1)), 0.0f);
  225.                 x1 = Math.Max(Math.Min(x1, (float)(image.Cols - 1)), 0.0f);
  226.                 y1 = Math.Max(Math.Min(y1, (float)(image.Rows - 1)), 0.0f);
  227.  
  228.                 Cv2.Rectangle(result_image, new OpenCvSharp.Point(x0, y0), new OpenCvSharp.Point(x1, y1), new Scalar(0, 255, 0), 2);
  229.                 string label = class_names[classIds[idx]] + ":" + confidences[idx].ToString("0.00");
  230.                 Cv2.PutText(result_image, label, new OpenCvSharp.Point(x0, y0 - 5), HersheyFonts.HersheySimplex, 1, new Scalar(0, 0, 255), 2);
  231.             }
  232.  
  233.             pictureBox2.Image = new Bitmap(result_image.ToMemoryStream());
  234.             textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";
  235.  
  236.         }
  237.  
  238.         private void pictureBox2_DoubleClick(object sender, EventArgs e)
  239.         {
  240.             Common.ShowNormalImg(pictureBox2.Image);
  241.         }
  242.  
  243.         private void pictureBox1_DoubleClick(object sender, EventArgs e)
  244.         {
  245.             Common.ShowNormalImg(pictureBox1.Image);
  246.         }
  247.     }
  248. }

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/135460960"。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！