C# OnnxRuntime MPCount 人群计数

C# OnnxRuntime MPCount 人群计数

目录

说明

效果

模型信息

项目

代码

下载

说明

官网地址：https://github.com/Shimmer93/MPCount

代码实现参考：https://github.com/hpc203/MPCount-onnxrun

效果

C# OnnxRuntime MPCount 人群计数

模型信息

Model Properties
-------------------------
---------------------------------------------------------------

Inputs
-------------------------
name：input
tensor：Float[-1, 3, -1, -1]
---------------------------------------------------------------

Outputs
-------------------------
name：output
tensor：Float[-1, 1, -1, -1]
name：c
tensor：Float[-1, 1, -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;
        SessionOptions options;
        InferenceSession onnx_session;
        List input_container;

        int unit_size = 16;
        int log_para = 1000;

        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;
            textBox1.Text = "";
            Application.DoEvents();

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

            Mat x = new Mat();
            int left = 0;
            int top = 0;
            int right = 0;
            int bottom = 0;
            Common.preprocess(unit_size,image, x, ref left, ref top, ref right, ref bottom);

            int[] input_shape_ = new int[] { 1, 3, x.Rows, x.Cols };
            x.ConvertTo(x, MatType.CV_32FC3, 1 / 127.5, -1.0);

            float[] input_image = Common.ExtractMat(x);
            x.Release();

            Tensor input_tensor = new DenseTensor(input_image, input_shape_);
            List input_container2 = new List
                {
                    NamedOnnxValue.CreateFromTensor("input", input_tensor)
                };
            dt1 = DateTime.Now;
            var result_infer = onnx_session.Run(input_container2).ToArray();
            dt2 = DateTime.Now;

            var ort_outputs = result_infer.ToArray();
            ReadOnlySpan out_shape = ort_outputs[0].AsTensor().Dimensions;
            int outHeight = out_shape[2];
            int outWidth = out_shape[3];
            float[] pred = ort_outputs[0].AsTensor().ToArray();

            Mat result = new Mat(outHeight, outWidth, MatType.CV_32FC1, pred);
            Rect crop_roi = new Rect(left, top, outWidth - right - left, outHeight - top - bottom);

            Mat result_map = Mat.Zeros(new OpenCvSharp.Size(outWidth, outHeight), MatType.CV_32FC1);
            result.CopyTo(new Mat(result_map, crop_roi));

            int people_count = (int)(Cv2.Sum(result_map)[0] / log_para);

            Mat drawimg = Common.draw_result(image, result_map, people_count);

            pictureBox2.Image = new Bitmap(drawimg.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/MPCount_qnrf.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/0.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 (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|Images (*.emf)|*.emf|Images (*.exif)|*.exif|Images (*.gif)|*.gif|Images (*.ico)|*.ico|Images (*.tiff)|*.tiff|Images (*.wmf)|*.wmf";
            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;
                        }
                    case 4:
                        {
                            output.Save(sdf.FileName, ImageFormat.Emf);
                            break;
                        }
                    case 5:
                        {
                            output.Save(sdf.FileName, ImageFormat.Exif);
                            break;
                        }
                    case 6:
                        {
                            output.Save(sdf.FileName, ImageFormat.Gif);
                            break;
                        }
                    case 7:
                        {
                            output.Save(sdf.FileName, ImageFormat.Icon);
                            break;
                        }

                    case 8:
                        {
                            output.Save(sdf.FileName, ImageFormat.Tiff);
                            break;
                        }
                    case 9:
                        {
                            output.Save(sdf.FileName, ImageFormat.Wmf);
                            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.         SessionOptions options;
  28.         InferenceSession onnx_session;
  29.         List<NamedOnnxValue> input_container;
  30.  
  31.         int unit_size = 16;
  32.         int log_para = 1000;
  33.  
  34.         private void button1_Click(object sender, EventArgs e)
  35.         {
  36.             OpenFileDialog ofd = new OpenFileDialog();
  37.             ofd.Filter = fileFilter;
  38.             if (ofd.ShowDialog() != DialogResult.OK) return;
  39.             pictureBox1.Image = null;
  40.             image_path = ofd.FileName;
  41.             pictureBox1.Image = new Bitmap(image_path);
  42.             textBox1.Text = "";
  43.             image = new Mat(image_path);
  44.             pictureBox2.Image = null;
  45.         }
  46.  
  47.         private void button2_Click(object sender, EventArgs e)
  48.         {
  49.             if (image_path == "")
  50.             {
  51.                 return;
  52.             }
  53.  
  54.             button2.Enabled = false;
  55.             pictureBox2.Image = null;
  56.             textBox1.Text = "";
  57.             Application.DoEvents();
  58.  
  59.             //读图片
  60.             image = new Mat(image_path);
  61.  
  62.             Mat x = new Mat();
  63.             int left = 0;
  64.             int top = 0;
  65.             int right = 0;
  66.             int bottom = 0;
  67.             Common.preprocess(unit_size,image, x, ref left, ref top, ref right, ref bottom);
  68.  
  69.             int[] input_shape_ = new int[] { 1, 3, x.Rows, x.Cols };
  70.             x.ConvertTo(x, MatType.CV_32FC3, 1 / 127.5, -1.0);
  71.  
  72.             float[] input_image = Common.ExtractMat(x);
  73.             x.Release();
  74.  
  75.             Tensor<float> input_tensor = new DenseTensor<float>(input_image, input_shape_);
  76.             List<NamedOnnxValue> input_container2 = new List<NamedOnnxValue>
  77.                 {
  78.                     NamedOnnxValue.CreateFromTensor("input", input_tensor)
  79.                 };
  80.             dt1 = DateTime.Now;
  81.             var result_infer = onnx_session.Run(input_container2).ToArray();
  82.             dt2 = DateTime.Now;
  83.  
  84.             var ort_outputs = result_infer.ToArray();
  85.             ReadOnlySpan<int> out_shape = ort_outputs[0].AsTensor<float>().Dimensions;
  86.             int outHeight = out_shape[2];
  87.             int outWidth = out_shape[3];
  88.             float[] pred = ort_outputs[0].AsTensor<float>().ToArray();
  89.  
  90.             Mat result = new Mat(outHeight, outWidth, MatType.CV_32FC1, pred);
  91.             Rect crop_roi = new Rect(left, top, outWidth - right - left, outHeight - top - bottom);
  92.  
  93.             Mat result_map = Mat.Zeros(new OpenCvSharp.Size(outWidth, outHeight), MatType.CV_32FC1);
  94.             result.CopyTo(new Mat(result_map, crop_roi));
  95.  
  96.             int people_count = (int)(Cv2.Sum(result_map)[0] / log_para);
  97.  
  98.             Mat drawimg = Common.draw_result(image, result_map, people_count);
  99.  
  100.             pictureBox2.Image = new Bitmap(drawimg.ToMemoryStream());
  101.             textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";
  102.  
  103.             button2.Enabled = true;
  104.  
  105.         }
  106.  
  107.         private void Form1_Load(object sender, EventArgs e)
  108.         {
  109.             startupPath = System.Windows.Forms.Application.StartupPath;
  110.             model_path = "model/MPCount_qnrf.onnx";
  111.  
  112.             // 创建输出会话，用于输出模型读取信息
  113.             options = new SessionOptions();
  114.             options.LogSeverityLevel = OrtLoggingLevel.ORT_LOGGING_LEVEL_INFO;
  115.             options.AppendExecutionProvider_CPU(0);// 设置为CPU上运行
  116.  
  117.             // 创建推理模型类，读取本地模型文件
  118.             onnx_session = new InferenceSession(model_path, options);//model_path 为onnx模型文件的路径
  119.  
  120.             // 创建输入容器
  121.             input_container = new List<NamedOnnxValue>();
  122.  
  123.             image_path = "test_img/0.jpg";
  124.             pictureBox1.Image = new Bitmap(image_path);
  125.             image = new Mat(image_path);
  126.  
  127.         }
  128.  
  129.         private void pictureBox1_DoubleClick(object sender, EventArgs e)
  130.         {
  131.             Common.ShowNormalImg(pictureBox1.Image);
  132.         }
  133.  
  134.         private void pictureBox2_DoubleClick(object sender, EventArgs e)
  135.         {
  136.             Common.ShowNormalImg(pictureBox2.Image);
  137.         }
  138.  
  139.         SaveFileDialog sdf = new SaveFileDialog();
  140.         private void button3_Click(object sender, EventArgs e)
  141.         {
  142.             if (pictureBox2.Image == null)
  143.             {
  144.                 return;
  145.             }
  146.             Bitmap output = new Bitmap(pictureBox2.Image);
  147.             sdf.Title = "保存";
  148.             sdf.Filter = "Images (*.jpg)|*.jpg|Images (*.png)|*.png|Images (*.bmp)|*.bmp|Images (*.emf)|*.emf|Images (*.exif)|*.exif|Images (*.gif)|*.gif|Images (*.ico)|*.ico|Images (*.tiff)|*.tiff|Images (*.wmf)|*.wmf";
  149.             if (sdf.ShowDialog() == DialogResult.OK)
  150.             {
  151.                 switch (sdf.FilterIndex)
  152.                 {
  153.                     case 1:
  154.                         {
  155.                             output.Save(sdf.FileName, ImageFormat.Jpeg);
  156.                             break;
  157.                         }
  158.                     case 2:
  159.                         {
  160.                             output.Save(sdf.FileName, ImageFormat.Png);
  161.                             break;
  162.                         }
  163.                     case 3:
  164.                         {
  165.                             output.Save(sdf.FileName, ImageFormat.Bmp);
  166.                             break;
  167.                         }
  168.                     case 4:
  169.                         {
  170.                             output.Save(sdf.FileName, ImageFormat.Emf);
  171.                             break;
  172.                         }
  173.                     case 5:
  174.                         {
  175.                             output.Save(sdf.FileName, ImageFormat.Exif);
  176.                             break;
  177.                         }
  178.                     case 6:
  179.                         {
  180.                             output.Save(sdf.FileName, ImageFormat.Gif);
  181.                             break;
  182.                         }
  183.                     case 7:
  184.                         {
  185.                             output.Save(sdf.FileName, ImageFormat.Icon);
  186.                             break;
  187.                         }
  188.  
  189.                     case 8:
  190.                         {
  191.                             output.Save(sdf.FileName, ImageFormat.Tiff);
  192.                             break;
  193.                         }
  194.                     case 9:
  195.                         {
  196.                             output.Save(sdf.FileName, ImageFormat.Wmf);
  197.                             break;
  198.                         }
  199.                 }
  200.                 MessageBox.Show("保存成功，位置：" + sdf.FileName);
  201.             }
  202.         }
  203.     }
  204. }

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/141092803"。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！