C# Onnx Yolov8-OBB 旋转目标检测 行驶证副页条码+编号 检测，后续裁剪出图片并摆正显示

C# Onnx Yolov8-OBB 旋转目标检测 行驶证副页条码+编号 检测，后续裁剪出图片并摆正显示

目录

效果

模型信息

项目

代码 

下载

效果

模型信息

Model Properties
-------------------------
date：2024-06-25T10:59:15.206586
description：Ultralytics YOLOv8n-obb model trained on C:\Work\yolov8\config\dl-obb.yaml
author：Ultralytics
version：8.1.29
task：obb
license：AGPL-3.0 License (https://ultralytics.com/license)
docs：https://docs.ultralytics.com
stride：32
batch：1
imgsz：[1024, 1024]
names：{0: 'code'}
---------------------------------------------------------------

Inputs
-------------------------
name：images
tensor：Float[1, 3, 1024, 1024]
---------------------------------------------------------------

Outputs
-------------------------
name：output0
tensor：Float[1, 6, 21504]
---------------------------------------------------------------

项目

代码 

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

namespace Onnx_Yolov8_Demo
{
    public partial class Form1 : Form
    {
        public Form1()
        {
            InitializeComponent();
        }

        string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";
        string image_path = "";
        string classer_path;
        DateTime dt1 = DateTime.Now;
        DateTime dt2 = DateTime.Now;
        string model_path;
        Mat image;
        Mat result_image;
        public string[] class_lables;
        SessionOptions options;
        InferenceSession onnx_session;
        Tensor input_tensor;
        List input_container;
        IDisposableReadOnlyCollection result_infer;
        DisposableNamedOnnxValue[] results_onnxvalue;

        Tensor result_tensors;

        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;
        }

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

            button2.Enabled = false;

            pictureBox2.Image = null;
            pictureBox3.Image = null;
            textBox1.Text = "";
            Application.DoEvents();

            //图片缩放
            image = new Mat(image_path);
            int max_image_length = image.Cols > image.Rows ? image.Cols : image.Rows;
            Mat max_image = Mat.Zeros(new OpenCvSharp.Size(max_image_length, max_image_length), MatType.CV_8UC3);
            Rect roi = new Rect(0, 0, image.Cols, image.Rows);
            image.CopyTo(new Mat(max_image, roi));

            float[] result_array;
            float factor = (float)(max_image_length / 1024.0);

            // 将图片转为RGB通道
            Mat image_rgb = new Mat();
            Cv2.CvtColor(max_image, image_rgb, ColorConversionCodes.BGR2RGB);
            Mat resize_image = new Mat();
            Cv2.Resize(image_rgb, resize_image, new OpenCvSharp.Size(1024, 1024));

           // Cv2.ImShow("resize_image",resize_image);

            // 输入Tensor
            for (int y = 0; y < resize_image.Height; y++)
            {
                for (int x = 0; x < resize_image.Width; x++)
                {
                    input_tensor[0, 0, y, x] = resize_image.At(y, x)[0] / 255f;
                    input_tensor[0, 1, y, x] = resize_image.At(y, x)[1] / 255f;
                    input_tensor[0, 2, y, x] = resize_image.At(y, x)[2] / 255f;
                }
            }

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

            // 读取第一个节点输出并转为Tensor数据
            result_tensors = results_onnxvalue[0].AsTensor();

            result_array = result_tensors.ToArray();

            Mat result_data = new Mat(6, 21504, MatType.CV_32F, result_array);
            result_data = result_data.T();
            string s = result_data.Dump();
            List position_boxes = new List();
            List class_ids = new List();
            List confidences = new List();
            List rotations = new List();
            // Preprocessing output results
            for (int i = 0; i < result_data.Rows; i++)
            {
                Mat classes_scores = new Mat(result_data, new Rect(4, i, 1, 1));
                string s2 = classes_scores.Dump();
                OpenCvSharp.Point max_classId_point, min_classId_point;
                double max_score, min_score;
                // Obtain the maximum value and its position in a set of data
                Cv2.MinMaxLoc(classes_scores, out min_score, out max_score,
                    out min_classId_point, out max_classId_point);
                // Confidence level between 0 ~ 1
                // Obtain identification box information
                if (max_score > 0.5)
                {
                    float cx = result_data.At(i, 0);
                    float cy = result_data.At(i, 1);
                    float ow = result_data.At(i, 2);
                    float oh = result_data.At(i, 3);
                    double x = (cx - 0.5 * ow) * factor;
                    double y = (cy - 0.5 * oh) * factor;
                    double width = ow * factor;
                    double height = oh * factor;
                    Rect2d box = new Rect2d();
                    box.X = x;
                    box.Y = y;
                    box.Width = width;
                    box.Height = height;
                    position_boxes.Add(box);
                    class_ids.Add(max_classId_point.X);
                    confidences.Add((float)max_score);
                    rotations.Add(result_data.At(i, 5));
                }
            }

            // NMS 
            int[] indexes = new int[position_boxes.Count];
            CvDnn.NMSBoxes(position_boxes, confidences, 0.5f, 0.5f, out indexes);
            List rotated_rects = new List();
            for (int i = 0; i < indexes.Length; i++)
            {
                int index = indexes[i];
                float w = (float)position_boxes[index].Width;
                float h = (float)position_boxes[index].Height;
                float x = (float)position_boxes[index].X + w / 2;
                float y = (float)position_boxes[index].Y + h / 2;
                float r = rotations[index];
                float w_ = w > h ? w : h;
                float h_ = w > h ? h : w;
                r = (float)((w > h ? r : (float)(r + Math.PI / 2)) % Math.PI);
                RotatedRect rotate = new RotatedRect(new Point2f(x, y), new Size2f(w_, h_), (float)(r * 180.0 / Math.PI));

                if (rotate.Angle>90)
                {
                    rotate.Angle =  rotate.Angle-180;
                }
                rotated_rects.Add(rotate);
            }

            result_image = image.Clone();

            for (int i = 0; i < indexes.Length; i++)
            {
                int index = indexes[i];

                if (confidences[index]<0.7)
                {
                    continue;
                }

                Point2f[] points = rotated_rects[i].Points();

                //裁剪出需要的图片
                Mat codeMat = GetRotateCropImage(image, rotated_rects[i]);
                pictureBox3.Image = new Bitmap(codeMat.ToMemoryStream());

                for (int j = 0; j < 4; j++)
                {
                    Cv2.Line(result_image, (OpenCvSharp.Point)points[j], (OpenCvSharp.Point)points[(j + 1) % 4], new Scalar(0, 255, 0), 2, LineTypes.Link8);
                }

                Cv2.PutText(result_image, class_lables[class_ids[index]] + "-" + confidences[index].ToString("0.00"),
                    (OpenCvSharp.Point)points[0], HersheyFonts.HersheySimplex, 0.8, new Scalar(0, 0, 255), 2);

                pictureBox2.Image = new Bitmap(result_image.ToMemoryStream());

            }

            


            textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";

            button2.Enabled = true;
        }

        private Mat GetRotateCropImage(Mat src, RotatedRect rect)
        {
            bool wider = rect.Size.Width > rect.Size.Height;
            float angle = rect.Angle;
            OpenCvSharp.Size srcSize = src.Size();
            Rect boundingRect = rect.BoundingRect();

            int expTop = Math.Max(0, 0 - boundingRect.Top);
            int expBottom = Math.Max(0, boundingRect.Bottom - srcSize.Height);
            int expLeft = Math.Max(0, 0 - boundingRect.Left);
            int expRight = Math.Max(0, boundingRect.Right - srcSize.Width);

            Rect rectToExp = boundingRect + new OpenCvSharp.Point(expTop, expLeft);
            Rect roiRect = Rect.FromLTRB(
                boundingRect.Left + expLeft,
                boundingRect.Top + expTop,
                boundingRect.Right - expRight,
                boundingRect.Bottom - expBottom);
            Mat boundingMat = src[roiRect];


            Mat expanded = boundingMat.CopyMakeBorder(expTop, expBottom, expLeft, expRight, BorderTypes.Replicate);
            Point2f[] rp = rect.Points()
                .Select(v => new Point2f(v.X - rectToExp.X, v.Y - rectToExp.Y))
                .ToArray();


            Point2f[] srcPoints = new[] { rp[0], rp[3], rp[2], rp[1] };

            if (wider == true && angle >= 0 && angle < 45)
            {
                srcPoints = new[] { rp[1], rp[2], rp[3], rp[0] };
            }

            var ptsDst0 = new Point2f(0, 0);
            var ptsDst1 = new Point2f(rect.Size.Width, 0);
            var ptsDst2 = new Point2f(rect.Size.Width, rect.Size.Height);
            var ptsDst3 = new Point2f(0, rect.Size.Height);

            Mat matrix = Cv2.GetPerspectiveTransform(srcPoints, new[] { ptsDst0, ptsDst1, ptsDst2, ptsDst3 });

            Mat dest = expanded.WarpPerspective(matrix, new OpenCvSharp.Size(rect.Size.Width, rect.Size.Height), InterpolationFlags.Nearest, BorderTypes.Replicate);

            if (rect.Angle<0)
            {
                Cv2.Flip(dest, dest, FlipMode.X);
            }

            boundingMat.Dispose();
            expanded.Dispose();
            matrix.Dispose();

            return dest;
        }

        private void Form1_Load(object sender, EventArgs e)
        {
            model_path = "model/best.onnx";
            classer_path = "model/lable.txt";

            // 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

            // 输入Tensor
            input_tensor = new DenseTensor(new[] { 1, 3, 1024, 1024 });
            // 创建输入容器
            input_container = new List();

            List str = new List();
            StreamReader sr = new StreamReader(classer_path);
            string line;
            while ((line = sr.ReadLine()) != null)
            {
                str.Add(line);
            }
            class_lables = str.ToArray();

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

        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 (pictureBox3.Image == null)
            {
                return;
            }
            Bitmap output = new Bitmap(pictureBox3.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 OpenCvSharp.Dnn;
  5. using System;
  6. using System.Collections.Generic;
  7. using System.Drawing;
  8. using System.Drawing.Imaging;
  9. using System.IO;
  10. using System.Linq;
  11. using System.Windows.Forms;
  12.  
  13. namespace Onnx_Yolov8_Demo
  14. {
  15.     public partial class Form1 : Form
  16.     {
  17.         public Form1()
  18.         {
  19.             InitializeComponent();
  20.         }
  21.  
  22.         string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";
  23.         string image_path = "";
  24.         string classer_path;
  25.         DateTime dt1 = DateTime.Now;
  26.         DateTime dt2 = DateTime.Now;
  27.         string model_path;
  28.         Mat image;
  29.         Mat result_image;
  30.         public string[] class_lables;
  31.         SessionOptions options;
  32.         InferenceSession onnx_session;
  33.         Tensor<float> input_tensor;
  34.         List<NamedOnnxValue> input_container;
  35.         IDisposableReadOnlyCollection<DisposableNamedOnnxValue> result_infer;
  36.         DisposableNamedOnnxValue[] results_onnxvalue;
  37.  
  38.         Tensor<float> result_tensors;
  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.         private void button2_Click(object sender, EventArgs e)
  54.         {
  55.             if (image_path == "")
  56.             {
  57.                 return;
  58.             }
  59.  
  60.             button2.Enabled = false;
  61.  
  62.             pictureBox2.Image = null;
  63.             pictureBox3.Image = null;
  64.             textBox1.Text = "";
  65.             Application.DoEvents();
  66.  
  67.             //图片缩放
  68.             image = new Mat(image_path);
  69.             int max_image_length = image.Cols > image.Rows ? image.Cols : image.Rows;
  70.             Mat max_image = Mat.Zeros(new OpenCvSharp.Size(max_image_length, max_image_length), MatType.CV_8UC3);
  71.             Rect roi = new Rect(0, 0, image.Cols, image.Rows);
  72.             image.CopyTo(new Mat(max_image, roi));
  73.  
  74.             float[] result_array;
  75.             float factor = (float)(max_image_length / 1024.0);
  76.  
  77.             // 将图片转为RGB通道
  78.             Mat image_rgb = new Mat();
  79.             Cv2.CvtColor(max_image, image_rgb, ColorConversionCodes.BGR2RGB);
  80.             Mat resize_image = new Mat();
  81.             Cv2.Resize(image_rgb, resize_image, new OpenCvSharp.Size(1024, 1024));
  82.  
  83.            // Cv2.ImShow("resize_image",resize_image);
  84.  
  85.             // 输入Tensor
  86.             for (int y = 0; y < resize_image.Height; y++)
  87.             {
  88.                 for (int x = 0; x < resize_image.Width; x++)
  89.                 {
  90.                     input_tensor[0, 0, y, x] = resize_image.At<Vec3b>(y, x)[0] / 255f;
  91.                     input_tensor[0, 1, y, x] = resize_image.At<Vec3b>(y, x)[1] / 255f;
  92.                     input_tensor[0, 2, y, x] = resize_image.At<Vec3b>(y, x)[2] / 255f;
  93.                 }
  94.             }
  95.  
  96.             //将 input_tensor 放入一个输入参数的容器，并指定名称
  97.             input_container.Add(NamedOnnxValue.CreateFromTensor("images", input_tensor));
  98.  
  99.             dt1 = DateTime.Now;
  100.             //运行 Inference 并获取结果
  101.             result_infer = onnx_session.Run(input_container);
  102.             dt2 = DateTime.Now;
  103.  
  104.             // 将输出结果转为DisposableNamedOnnxValue数组
  105.             results_onnxvalue = result_infer.ToArray();
  106.  
  107.             // 读取第一个节点输出并转为Tensor数据
  108.             result_tensors = results_onnxvalue[0].AsTensor<float>();
  109.  
  110.             result_array = result_tensors.ToArray();
  111.  
  112.             Mat result_data = new Mat(6, 21504, MatType.CV_32F, result_array);
  113.             result_data = result_data.T();
  114.             string s = result_data.Dump();
  115.             List<Rect2d> position_boxes = new List<Rect2d>();
  116.             List<int> class_ids = new List<int>();
  117.             List<float> confidences = new List<float>();
  118.             List<float> rotations = new List<float>();
  119.             // Preprocessing output results
  120.             for (int i = 0; i < result_data.Rows; i++)
  121.             {
  122.                 Mat classes_scores = new Mat(result_data, new Rect(4, i, 1, 1));
  123.                 string s2 = classes_scores.Dump();
  124.                 OpenCvSharp.Point max_classId_point, min_classId_point;
  125.                 double max_score, min_score;
  126.                 // Obtain the maximum value and its position in a set of data
  127.                 Cv2.MinMaxLoc(classes_scores, out min_score, out max_score,
  128.                     out min_classId_point, out max_classId_point);
  129.                 // Confidence level between 0 ~ 1
  130.                 // Obtain identification box information
  131.                 if (max_score > 0.5)
  132.                 {
  133.                     float cx = result_data.At<float>(i, 0);
  134.                     float cy = result_data.At<float>(i, 1);
  135.                     float ow = result_data.At<float>(i, 2);
  136.                     float oh = result_data.At<float>(i, 3);
  137.                     double x = (cx - 0.5 * ow) * factor;
  138.                     double y = (cy - 0.5 * oh) * factor;
  139.                     double width = ow * factor;
  140.                     double height = oh * factor;
  141.                     Rect2d box = new Rect2d();
  142.                     box.X = x;
  143.                     box.Y = y;
  144.                     box.Width = width;
  145.                     box.Height = height;
  146.                     position_boxes.Add(box);
  147.                     class_ids.Add(max_classId_point.X);
  148.                     confidences.Add((float)max_score);
  149.                     rotations.Add(result_data.At<float>(i, 5));
  150.                 }
  151.             }
  152.  
  153.  
  154.  
  155.             // NMS 
  156.             int[] indexes = new int[position_boxes.Count];
  157.             CvDnn.NMSBoxes(position_boxes, confidences, 0.5f, 0.5f, out indexes);
  158.             List<RotatedRect> rotated_rects = new List<RotatedRect>();
  159.             for (int i = 0; i < indexes.Length; i++)
  160.             {
  161.                 int index = indexes[i];
  162.                 float w = (float)position_boxes[index].Width;
  163.                 float h = (float)position_boxes[index].Height;
  164.                 float x = (float)position_boxes[index].X + w / 2;
  165.                 float y = (float)position_boxes[index].Y + h / 2;
  166.                 float r = rotations[index];
  167.                 float w_ = w > h ? w : h;
  168.                 float h_ = w > h ? h : w;
  169.                 r = (float)((w > h ? r : (float)(r + Math.PI / 2)) % Math.PI);
  170.                 RotatedRect rotate = new RotatedRect(new Point2f(x, y), new Size2f(w_, h_), (float)(r * 180.0 / Math.PI));
  171.  
  172.                 if (rotate.Angle>90)
  173.                 {
  174.                     rotate.Angle =  rotate.Angle-180;
  175.                 }
  176.                 rotated_rects.Add(rotate);
  177.             }
  178.  
  179.             result_image = image.Clone();
  180.  
  181.             for (int i = 0; i < indexes.Length; i++)
  182.             {
  183.                 int index = indexes[i];
  184.  
  185.                 if (confidences[index]<0.7)
  186.                 {
  187.                     continue;
  188.                 }
  189.  
  190.                 Point2f[] points = rotated_rects[i].Points();
  191.  
  192.                 //裁剪出需要的图片
  193.                 Mat codeMat = GetRotateCropImage(image, rotated_rects[i]);
  194.                 pictureBox3.Image = new Bitmap(codeMat.ToMemoryStream());
  195.  
  196.                 for (int j = 0; j < 4; j++)
  197.                 {
  198.                     Cv2.Line(result_image, (OpenCvSharp.Point)points[j], (OpenCvSharp.Point)points[(j + 1) % 4], new Scalar(0, 255, 0), 2, LineTypes.Link8);
  199.                 }
  200.  
  201.                 Cv2.PutText(result_image, class_lables[class_ids[index]] + "-" + confidences[index].ToString("0.00"),
  202.                     (OpenCvSharp.Point)points[0], HersheyFonts.HersheySimplex, 0.8, new Scalar(0, 0, 255), 2);
  203.  
  204.                 pictureBox2.Image = new Bitmap(result_image.ToMemoryStream());
  205.  
  206.             }
  207.  
  208.           
  209.             textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";
  210.  
  211.             button2.Enabled = true;
  212.         }
  213.  
  214.         private Mat GetRotateCropImage(Mat src, RotatedRect rect)
  215.         {
  216.             bool wider = rect.Size.Width > rect.Size.Height;
  217.             float angle = rect.Angle;
  218.             OpenCvSharp.Size srcSize = src.Size();
  219.             Rect boundingRect = rect.BoundingRect();
  220.  
  221.             int expTop = Math.Max(0, 0 - boundingRect.Top);
  222.             int expBottom = Math.Max(0, boundingRect.Bottom - srcSize.Height);
  223.             int expLeft = Math.Max(0, 0 - boundingRect.Left);
  224.             int expRight = Math.Max(0, boundingRect.Right - srcSize.Width);
  225.  
  226.             Rect rectToExp = boundingRect + new OpenCvSharp.Point(expTop, expLeft);
  227.             Rect roiRect = Rect.FromLTRB(
  228.                 boundingRect.Left + expLeft,
  229.                 boundingRect.Top + expTop,
  230.                 boundingRect.Right - expRight,
  231.                 boundingRect.Bottom - expBottom);
  232.             Mat boundingMat = src[roiRect];
  233.  
  234.  
  235.             Mat expanded = boundingMat.CopyMakeBorder(expTop, expBottom, expLeft, expRight, BorderTypes.Replicate);
  236.             Point2f[] rp = rect.Points()
  237.                 .Select(v => new Point2f(v.X - rectToExp.X, v.Y - rectToExp.Y))
  238.                 .ToArray();
  239.  
  240.  
  241.             Point2f[] srcPoints = new[] { rp[0], rp[3], rp[2], rp[1] };
  242.  
  243.             if (wider == true && angle >= 0 && angle < 45)
  244.             {
  245.                 srcPoints = new[] { rp[1], rp[2], rp[3], rp[0] };
  246.             }
  247.  
  248.             var ptsDst0 = new Point2f(0, 0);
  249.             var ptsDst1 = new Point2f(rect.Size.Width, 0);
  250.             var ptsDst2 = new Point2f(rect.Size.Width, rect.Size.Height);
  251.             var ptsDst3 = new Point2f(0, rect.Size.Height);
  252.  
  253.             Mat matrix = Cv2.GetPerspectiveTransform(srcPoints, new[] { ptsDst0, ptsDst1, ptsDst2, ptsDst3 });
  254.  
  255.             Mat dest = expanded.WarpPerspective(matrix, new OpenCvSharp.Size(rect.Size.Width, rect.Size.Height), InterpolationFlags.Nearest, BorderTypes.Replicate);
  256.  
  257.             if (rect.Angle<0)
  258.             {
  259.                 Cv2.Flip(dest, dest, FlipMode.X);
  260.             }
  261.  
  262.             boundingMat.Dispose();
  263.             expanded.Dispose();
  264.             matrix.Dispose();
  265.  
  266.             return dest;
  267.         }
  268.  
  269.         private void Form1_Load(object sender, EventArgs e)
  270.         {
  271.             model_path = "model/best.onnx";
  272.             classer_path = "model/lable.txt";
  273.  
  274.             // 创建输出会话，用于输出模型读取信息
  275.             options = new SessionOptions();
  276.             options.LogSeverityLevel = OrtLoggingLevel.ORT_LOGGING_LEVEL_INFO;
  277.             options.AppendExecutionProvider_CPU(0);// 设置为CPU上运行
  278.  
  279.             // 创建推理模型类，读取本地模型文件
  280.             onnx_session = new InferenceSession(model_path, options);//model_path 为onnx模型文件的路径
  281.  
  282.             // 输入Tensor
  283.             input_tensor = new DenseTensor<float>(new[] { 1, 3, 1024, 1024 });
  284.             // 创建输入容器
  285.             input_container = new List<NamedOnnxValue>();
  286.  
  287.             List<string> str = new List<string>();
  288.             StreamReader sr = new StreamReader(classer_path);
  289.             string line;
  290.             while ((line = sr.ReadLine()) != null)
  291.             {
  292.                 str.Add(line);
  293.             }
  294.             class_lables = str.ToArray();
  295.  
  296.             image_path = "test_img/1.jpg";
  297.             pictureBox1.Image = new Bitmap(image_path);
  298.             image = new Mat(image_path);
  299.         }
  300.  
  301.         private void pictureBox1_DoubleClick(object sender, EventArgs e)
  302.         {
  303.             Common.ShowNormalImg(pictureBox1.Image);
  304.         }
  305.  
  306.         private void pictureBox2_DoubleClick(object sender, EventArgs e)
  307.         {
  308.             Common.ShowNormalImg(pictureBox2.Image);
  309.         }
  310.  
  311.         SaveFileDialog sdf = new SaveFileDialog();
  312.         private void button3_Click(object sender, EventArgs e)
  313.         {
  314.             if (pictureBox3.Image == null)
  315.             {
  316.                 return;
  317.             }
  318.             Bitmap output = new Bitmap(pictureBox3.Image);
  319.             sdf.Title = "保存";
  320.             sdf.Filter = "Images (*.jpg)|*.jpg|Images (*.png)|*.png|Images (*.bmp)|*.bmp";
  321.             if (sdf.ShowDialog() == DialogResult.OK)
  322.             {
  323.                 switch (sdf.FilterIndex)
  324.                 {
  325.                     case 1:
  326.                         {
  327.                             output.Save(sdf.FileName, ImageFormat.Jpeg);
  328.                             break;
  329.                         }
  330.                     case 2:
  331.                         {
  332.                             output.Save(sdf.FileName, ImageFormat.Png);
  333.                             break;
  334.                         }
  335.                     case 3:
  336.                         {
  337.                             output.Save(sdf.FileName, ImageFormat.Bmp);
  338.                             break;
  339.                         }
  340.                 }
  341.                 MessageBox.Show("保存成功，位置：" + sdf.FileName);
  342.             }
  343.         }
  344.     }
  345. }

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/139958157"。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！