• C# Onnx PP-HumanSeg 人像分割

    目录

    效果

    模型信息

    项目

    代码

    下载

    效果

    图片源自网络侵删 

    模型信息

    Inputs
    -------------------------
    name：x
    tensor：Float[1, 3, 192, 192]
    ---------------------------------------------------------------

    Outputs
    -------------------------
    name：tf.identity
    tensor：Float[1, 192, 192, 2]
    ---------------------------------------------------------------

    项目

    VS2022

    .net framework 4.8

    OpenCvSharp 4.8

    Microsoft.ML.OnnxRuntime 1.16.2

    代码

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

    namespace Onnx_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 conf_threshold = 0.9f;

            int inpWidth;
            int inpHeight;

            int outHeight, outWidth;

            Mat image;

            string model_path = "";

            SessionOptions options;
            InferenceSession onnx_session;
            Tensor input_tensor;
            List input_ontainer;

            IDisposableReadOnlyCollection result_infer;
            DisposableNamedOnnxValue[] results_onnxvalue;

            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 System.Drawing.Bitmap(image_path);
                image = new Mat(image_path);
            }

            private void Form1_Load(object sender, EventArgs e)
            {
                // 创建输入容器
                input_ontainer = new List();

                // 创建输出会话
                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
                model_path = "model/model_float32.onnx";

                inpHeight = 192;
                inpWidth = 192;

                outHeight = 192;
                outWidth = 192;

                onnx_session = new InferenceSession(model_path, options);

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

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

            }

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

                image = new Mat(image_path);

                Mat resize_image = new Mat();
                Cv2.Resize(image, resize_image, new OpenCvSharp.Size(inpWidth, inpHeight));

                float[] input_tensor_data = new float[1 * 3 * inpWidth * inpHeight];
                int row = resize_image.Rows;
                int col = resize_image.Cols;
                for (int c = 0; c < 3; c++)
                {
                    for (int i = 0; i < inpHeight; i++)
                    {
                        for (int j = 0; j < inpWidth; j++)
                        {
                            byte pix = ((byte*)(resize_image.Ptr(i).ToPointer()))[j * 3 + c];
                            input_tensor_data[c * row * col + i * col + j] = (float)((pix / 255.0-0.5)/0.5);
                        }
                    }
                }

                input_tensor = new DenseTensor(input_tensor_data, new[] { 1, 3, inpHeight, inpWidth });

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

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

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

                float[] mask = results_onnxvalue[0].AsTensor().ToArray();

                Mat mask_out = new Mat(outHeight, outWidth, MatType.CV_32FC2, mask);

                Cv2.Resize(mask_out, mask_out, new OpenCvSharp.Size(image.Cols, image.Rows));

                Mat result_image = image.Clone();

                for (int h = 0; h < result_image.Rows; h++)
                {
                    for (int w = 0; w < result_image.Cols; w++)
                    {
                        float pix = mask_out.At(h, w);
                        if (pix > conf_threshold)
                        {
                            Vec3b vec3B = result_image.At(h, w);

                            vec3B.Item0 = 0;
                            vec3B.Item1 = 255;
                            vec3B.Item2 = 0;

                            result_image.Set(h, w, vec3B);
                        }
                    }
                }

                if (pictureBox2.Image != null)
                {
                    pictureBox2.Image.Dispose();
                }

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

                mask_out.Dispose();
                image.Dispose();
                resize_image.Dispose();
                result_image.Dispose();
            }

            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 Microsoft.ML.OnnxRuntime.Tensors;
    2. using Microsoft.ML.OnnxRuntime;
    3. using OpenCvSharp;
    4. using System;
    5. using System.Collections.Generic;
    6. using System.Windows.Forms;
    7. using System.Linq;
    8. using System.Drawing;
    9.  
    10. namespace Onnx_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 conf_threshold = 0.9f;
    26.  
    27.         int inpWidth;
    28.         int inpHeight;
    29.  
    30.         int outHeight, outWidth;
    31.  
    32.         Mat image;
    33.  
    34.         string model_path = "";
    35.  
    36.         SessionOptions options;
    37.         InferenceSession onnx_session;
    38.         Tensor<float> input_tensor;
    39.         List<NamedOnnxValue> input_ontainer;
    40.  
    41.         IDisposableReadOnlyCollection<DisposableNamedOnnxValue> result_infer;
    42.         DisposableNamedOnnxValue[] results_onnxvalue;
    43.  
    44.         private void button1_Click(object sender, EventArgs e)
    45.         {
    46.             OpenFileDialog ofd = new OpenFileDialog();
    47.             ofd.Filter = fileFilter;
    48.             if (ofd.ShowDialog() != DialogResult.OK) return;
    49.  
    50.             pictureBox1.Image = null;
    51.             pictureBox2.Image = null;
    52.             textBox1.Text = "";
    53.  
    54.             image_path = ofd.FileName;
    55.             pictureBox1.Image = new System.Drawing.Bitmap(image_path);
    56.             image = new Mat(image_path);
    57.         }
    58.  
    59.         private void Form1_Load(object sender, EventArgs e)
    60.         {
    61.             // 创建输入容器
    62.             input_ontainer = new List<NamedOnnxValue>();
    63.  
    64.             // 创建输出会话
    65.             options = new SessionOptions();
    66.             options.LogSeverityLevel = OrtLoggingLevel.ORT_LOGGING_LEVEL_INFO;
    67.             options.AppendExecutionProvider_CPU(0);// 设置为CPU上运行
    68.  
    69.             // 创建推理模型类，读取本地模型文件
    70.             model_path = "model/model_float32.onnx";
    71.  
    72.             inpHeight = 192;
    73.             inpWidth = 192;
    74.  
    75.             outHeight = 192;
    76.             outWidth = 192;
    77.  
    78.             onnx_session = new InferenceSession(model_path, options);
    79.  
    80.             // 创建输入容器
    81.             input_ontainer = new List<NamedOnnxValue>();
    82.  
    83.             image_path = "test_img/1.jpg";
    84.             pictureBox1.Image = new Bitmap(image_path);
    85.  
    86.         }
    87.  
    88.         private unsafe void button2_Click(object sender, EventArgs e)
    89.         {
    90.             if (image_path == "")
    91.             {
    92.                 return;
    93.             }
    94.             textBox1.Text = "检测中，请稍等……";
    95.             pictureBox2.Image = null;
    96.             System.Windows.Forms.Application.DoEvents();
    97.  
    98.             image = new Mat(image_path);
    99.  
    100.             Mat resize_image = new Mat();
    101.             Cv2.Resize(image, resize_image, new OpenCvSharp.Size(inpWidth, inpHeight));
    102.  
    103.             float[] input_tensor_data = new float[1 * 3 * inpWidth * inpHeight];
    104.             int row = resize_image.Rows;
    105.             int col = resize_image.Cols;
    106.             for (int c = 0; c < 3; c++)
    107.             {
    108.                 for (int i = 0; i < inpHeight; i++)
    109.                 {
    110.                     for (int j = 0; j < inpWidth; j++)
    111.                     {
    112.                         byte pix = ((byte*)(resize_image.Ptr(i).ToPointer()))[j * 3 + c];
    113.                         input_tensor_data[c * row * col + i * col + j] = (float)((pix / 255.0-0.5)/0.5);
    114.                     }
    115.                 }
    116.             }
    117.  
    118.             input_tensor = new DenseTensor<float>(input_tensor_data, new[] { 1, 3, inpHeight, inpWidth });
    119.  
    120.             //将 input_tensor 放入一个输入参数的容器，并指定名称
    121.             input_ontainer.Add(NamedOnnxValue.CreateFromTensor("x", input_tensor));
    122.  
    123.             dt1 = DateTime.Now;
    124.             //运行 Inference 并获取结果
    125.             result_infer = onnx_session.Run(input_ontainer);
    126.             dt2 = DateTime.Now;
    127.  
    128.             //将输出结果转为DisposableNamedOnnxValue数组
    129.             results_onnxvalue = result_infer.ToArray();
    130.  
    131.             float[] mask = results_onnxvalue[0].AsTensor<float>().ToArray();
    132.  
    133.             Mat mask_out = new Mat(outHeight, outWidth, MatType.CV_32FC2, mask);
    134.  
    135.             Cv2.Resize(mask_out, mask_out, new OpenCvSharp.Size(image.Cols, image.Rows));
    136.  
    137.             Mat result_image = image.Clone();
    138.  
    139.             for (int h = 0; h < result_image.Rows; h++)
    140.             {
    141.                 for (int w = 0; w < result_image.Cols; w++)
    142.                 {
    143.                     float pix = mask_out.At<float>(h, w);
    144.                     if (pix > conf_threshold)
    145.                     {
    146.                         Vec3b vec3B = result_image.At<Vec3b>(h, w);
    147.  
    148.                         vec3B.Item0 = 0;
    149.                         vec3B.Item1 = 255;
    150.                         vec3B.Item2 = 0;
    151.  
    152.                         result_image.Set<Vec3b>(h, w, vec3B);
    153.                     }
    154.                 }
    155.             }
    156.  
    157.             if (pictureBox2.Image != null)
    158.             {
    159.                 pictureBox2.Image.Dispose();
    160.             }
    161.  
    162.             pictureBox2.Image = new System.Drawing.Bitmap(result_image.ToMemoryStream());
    163.             textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";
    164.  
    165.             mask_out.Dispose();
    166.             image.Dispose();
    167.             resize_image.Dispose();
    168.             result_image.Dispose();
    169.         }
    170.  
    171.         private void pictureBox2_DoubleClick(object sender, EventArgs e)
    172.         {
    173.             Common.ShowNormalImg(pictureBox2.Image);
    174.         }
    175.  
    176.         private void pictureBox1_DoubleClick(object sender, EventArgs e)
    177.         {
    178.             Common.ShowNormalImg(pictureBox1.Image);
    179.         }
    180.     }
    181. }

    下载

    源码下载

  • 相关阅读:
    LeetCode34.在排序数组中查找元素的第一个和最后一个位置
    【AI】数学基础——最优化
    Excel - 插入空白行
    【软考】12.3 质量管理/风险管理
    【深度学习实验】线性模型（三）：使用Pytorch实现简单线性模型：搭建、构造损失函数、计算损失值
    HarmonyOS系统中内核实现NFC无线通信的方法
    46.Java正则表达式
    设计模式（19）命令模式
    【JavaSpring】Aop切入点表达式
    Python 常用基础模块（四）：sys模块
  • 原文地址：https://blog.csdn.net/lw112190/article/details/134519517