C# OpenCvSharp DNN 部署yolov3目标检测

目录

效果

yolov3.cfg

项目

代码

下载

---

C# OpenCvSharp DNN 部署yolov3目标检测

效果

yolov3.cfg

[net]
# Testing
#batch=1
#subdivisions=1
# Training
batch=16
subdivisions=1
width=416
height=416
channels=3
momentum=0.9
decay=0.0005
angle=0
saturation = 1.5
exposure = 1.5
hue=.1

learning_rate=0.001
burn_in=1000
max_batches = 500200
policy=steps
steps=400000,450000
scales=.1,.1

[convolutional]
batch_normalize=1
filters=32
size=3
stride=1
pad=1
activation=leaky

# Downsample

[convolutional]
batch_normalize=1
filters=64
size=3
stride=2
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=32
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=64
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear

# Downsample

[convolutional]
batch_normalize=1
filters=128
size=3
stride=2
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear

[convolutional]
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear

# Downsample

[convolutional]
batch_normalize=1
filters=256
size=3
stride=2
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear

[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear

[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear

[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear


[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear

[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear

[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear

[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear

# Downsample

[convolutional]
batch_normalize=1
filters=512
size=3
stride=2
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear


[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear


[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear


[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear

[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear


[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear


[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear

[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear

# Downsample

[convolutional]
batch_normalize=1
filters=1024
size=3
stride=2
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=1024
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear

[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=1024
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear

[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=1024
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear

[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=1024
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear

######################

[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky

[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky

[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky

[convolutional]
size=1
stride=1
pad=1
filters=255
activation=linear


[yolo]
mask = 6,7,8
anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
classes=80
num=9
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1


[route]
layers = -4

[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky

[upsample]
stride=2

[route]
layers = -1, 61



[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky

[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky

[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky

[convolutional]
size=1
stride=1
pad=1
filters=255
activation=linear


[yolo]
mask = 3,4,5
anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
classes=80
num=9
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1



[route]
layers = -4

[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[upsample]
stride=2

[route]
layers = -1, 36



[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky

[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky

[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky

[convolutional]
size=1
stride=1
pad=1
filters=255
activation=linear


[yolo]
mask = 0,1,2
anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
classes=80
num=9
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1

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 confThreshold;
? ? ? ? float nmsThreshold;

? ? ? ? int inpHeight;
? ? ? ? int inpWidth;

? ? ? ? List<string> class_names;
? ? ? ? int num_class;

? ? ? ? Net opencv_net;
? ? ? ? Mat BN_image;

? ? ? ? Mat image;
? ? ? ? Mat result_image;

? ? ? ? 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)
? ? ? ? {
? ? ? ? ? ? confThreshold = 0.5f;
? ? ? ? ? ? nmsThreshold = 0.4f;

? ? ? ? ? ? inpHeight = 416;
? ? ? ? ? ? inpWidth = 416;

? ? ? ? ? ? opencv_net = CvDnn.ReadNetFromDarknet("model/yolov3.cfg", "model/yolov3.weights");

? ? ? ? ? ? class_names = new List<string>();
? ? ? ? ? ? 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);

? ? ? ? }

? ? ? ? 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);

? ? ? ? ? ? BN_image = CvDnn.BlobFromImage(image, 1 / 255.0, new OpenCvSharp.Size(inpWidth, inpHeight), new Scalar(0, 0, 0), true, false);

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

? ? ? ? ? ? //模型推理，读取推理结果
? ? ? ? ? ? var outNames = opencv_net.GetUnconnectedOutLayersNames();
? ? ? ? ? ? var outs = outNames.Select(_ => new Mat()).ToArray();

? ? ? ? ? ? dt1 = DateTime.Now;

? ? ? ? ? ? opencv_net.Forward(outs, outNames);

? ? ? ? ? ? dt2 = DateTime.Now;

? ? ? ? ? ? List<int> classIds = new List<int>();
? ? ? ? ? ? List<float> confidences = new List<float>();
? ? ? ? ? ? List<Rect> boxes = new List<Rect>();

? ? ? ? ? ? for (int i = 0; i < outs.Length; ++i)
? ? ? ? ? ? {
? ? ? ? ? ? ? ? float* data = (float*)outs[i].Data;
? ? ? ? ? ? ? ? for (int j = 0; j < outs[i].Rows; ++j, data += outs[i].Cols)
? ? ? ? ? ? ? ? {
? ? ? ? ? ? ? ? ? ? Mat scores = outs[i].Row(j).ColRange(5, outs[i].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);

? ? ? ? ? ? ? ? ? ? if (max_class_socre > confThreshold)
? ? ? ? ? ? ? ? ? ? {
? ? ? ? ? ? ? ? ? ? ? ? int centerX = (int)(data[0] * image.Cols);
? ? ? ? ? ? ? ? ? ? ? ? int centerY = (int)(data[1] * image.Rows);
? ? ? ? ? ? ? ? ? ? ? ? int width = (int)(data[2] * image.Cols);
? ? ? ? ? ? ? ? ? ? ? ? int height = (int)(data[3] * image.Rows);
? ? ? ? ? ? ? ? ? ? ? ? int left = centerX - width / 2;
? ? ? ? ? ? ? ? ? ? ? ? int top = centerY - height / 2;

? ? ? ? ? ? ? ? ? ? ? ? classIds.Add(classIdPoint.X);
? ? ? ? ? ? ? ? ? ? ? ? confidences.Add((float)max_class_socre);
? ? ? ? ? ? ? ? ? ? ? ? boxes.Add(new Rect(left, top, width, height));
? ? ? ? ? ? ? ? ? ? }
? ? ? ? ? ? ? ? }
? ? ? ? ? ? }

? ? ? ? ? ? int[] indices;
? ? ? ? ? ? CvDnn.NMSBoxes(boxes, confidences, confThreshold, nmsThreshold, out indices);

? ? ? ? ? ? result_image = image.Clone();

? ? ? ? ? ? for (int i = 0; i < indices.Length; ++i)
? ? ? ? ? ? {
? ? ? ? ? ? ? ? int idx = indices[i];
? ? ? ? ? ? ? ? Rect box = boxes[idx];
? ? ? ? ? ? ? ? Cv2.Rectangle(result_image, new OpenCvSharp.Point(box.X, box.Y), new OpenCvSharp.Point(box.X + box.Width, box.Y + box.Height), new Scalar(0, 0, 255), 2);
? ? ? ? ? ? ? ? string label = class_names[classIds[idx]] + ":" + confidences[idx].ToString("0.00");
? ? ? ? ? ? ? ? Cv2.PutText(result_image, label, new OpenCvSharp.Point(box.X, box.Y - 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);
? ? ? ? }
? ? }
}

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 confThreshold;
        float nmsThreshold;

        int inpHeight;
        int inpWidth;

        List<string> class_names;
        int num_class;

        Net opencv_net;
        Mat BN_image;

        Mat image;
        Mat result_image;

        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)
        {
            confThreshold = 0.5f;
            nmsThreshold = 0.4f;

            inpHeight = 416;
            inpWidth = 416;

            opencv_net = CvDnn.ReadNetFromDarknet("model/yolov3.cfg", "model/yolov3.weights");

            class_names = new List<string>();
            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);

        }

        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);

            BN_image = CvDnn.BlobFromImage(image, 1 / 255.0, new OpenCvSharp.Size(inpWidth, inpHeight), new Scalar(0, 0, 0), true, false);

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

            //模型推理，读取推理结果
            var outNames = opencv_net.GetUnconnectedOutLayersNames();
            var outs = outNames.Select(_ => new Mat()).ToArray();

            dt1 = DateTime.Now;

            opencv_net.Forward(outs, outNames);

            dt2 = DateTime.Now;

            List<int> classIds = new List<int>();
            List<float> confidences = new List<float>();
            List<Rect> boxes = new List<Rect>();

            for (int i = 0; i < outs.Length; ++i)
            {
                float* data = (float*)outs[i].Data;
                for (int j = 0; j < outs[i].Rows; ++j, data += outs[i].Cols)
                {
                    Mat scores = outs[i].Row(j).ColRange(5, outs[i].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);

                    if (max_class_socre > confThreshold)
                    {
                        int centerX = (int)(data[0] * image.Cols);
                        int centerY = (int)(data[1] * image.Rows);
                        int width = (int)(data[2] * image.Cols);
                        int height = (int)(data[3] * image.Rows);
                        int left = centerX - width / 2;
                        int top = centerY - height / 2;

                        classIds.Add(classIdPoint.X);
                        confidences.Add((float)max_class_socre);
                        boxes.Add(new Rect(left, top, width, height));
                    }
                }
            }

            int[] indices;
            CvDnn.NMSBoxes(boxes, confidences, confThreshold, nmsThreshold, out indices);

            result_image = image.Clone();

            for (int i = 0; i < indices.Length; ++i)
            {
                int idx = indices[i];
                Rect box = boxes[idx];
                Cv2.Rectangle(result_image, new OpenCvSharp.Point(box.X, box.Y), new OpenCvSharp.Point(box.X + box.Width, box.Y + box.Height), new Scalar(0, 0, 255), 2);
                string label = class_names[classIds[idx]] + ":" + confidences[idx].ToString("0.00");
                Cv2.PutText(result_image, label, new OpenCvSharp.Point(box.X, box.Y - 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);
        }
    }
}

下载

源码下载