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<float> input_tensor;
        List<NamedOnnxValue> input_container;
        IDisposableReadOnlyCollection<DisposableNamedOnnxValue> result_infer;
        DisposableNamedOnnxValue[] results_onnxvalue;
        Tensor<float> 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<float>(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<Vec3b>(y, x)[0];
                    input_tensor[0, 1, y, x] = image_rgb.At<Vec3b>(y, x)[1];
                    input_tensor[0, 2, y, x] = image_rgb.At<Vec3b>(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<float>().ToArray();
            float[] pv = results_onnxvalue[1].AsTensor<float>().ToArray();

            float[] temp = new float[51];

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

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

                if (pv[i] >= confThreshold)
                {
                    List<int> human_pts = new List<int>();
                    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<NamedOnnxValue>();

            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);
            }
        }
    }
}

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<float> input_tensor;
        List<NamedOnnxValue> input_container;
        IDisposableReadOnlyCollection<DisposableNamedOnnxValue> result_infer;
        DisposableNamedOnnxValue[] results_onnxvalue;
        Tensor<float> 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<float>(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<Vec3b>(y, x)[0];
                    input_tensor[0, 1, y, x] = image_rgb.At<Vec3b>(y, x)[1];
                    input_tensor[0, 2, y, x] = image_rgb.At<Vec3b>(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<float>().ToArray();
            float[] pv = results_onnxvalue[1].AsTensor<float>().ToArray();

            float[] temp = new float[51];

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

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

                if (pv[i] >= confThreshold)
                {
                    List<int> human_pts = new List<int>();
                    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<NamedOnnxValue>();

            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);
            }
        }
    }
}

下载

源码下载