C#教程

关注公众号 jb51net

关闭
首页 > 软件编程 > C#教程 > C# Onnx图像二类分割

C# Onnx实现DIS高精度图像二类分割

作者:天天代码码天天

这篇文章主要为大家详细介绍了C# Onnx实现DIS高精度图像二类分割的相关知识,文中的示例代码讲解详细,感兴趣的小伙伴可以跟随小编一起学习一下

介绍

github地址:https://github.com/xuebinqin/DIS

This is the repo for our new project Highly Accurate Dichotomous Image Segmentation

对应的paper是ECCV2022的一篇文章《Highly Accurate Dichotomous Image Segmentation》, 跟BASNet和U2-Net都是出自同一个作者写的。 

效果

模型信息

Inputs
-------------------------
name:input
tensor:Float[1, 3, 480, 640]
---------------------------------------------------------------

Outputs
-------------------------
name:output
tensor:Float[1, 1, 480, 640]
---------------------------------------------------------------

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;
using static System.Net.Mime.MediaTypeNames;
 
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;
 
        int inpWidth;
        int inpHeight;
 
        int outHeight, outWidth;
 
        Mat image;
 
        string model_path = "";
 
        SessionOptions options;
        InferenceSession onnx_session;
        Tensor<float> input_tensor;
        Tensor<float> mask_tensor;
        List<NamedOnnxValue> input_ontainer;
 
        IDisposableReadOnlyCollection<DisposableNamedOnnxValue> 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<NamedOnnxValue>();
 
            // 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/isnet_general_use_480x640.onnx";
 
            inpHeight = 480;
            inpWidth = 640;
 
            outHeight = 480;
            outWidth = 640;
 
            onnx_session = new InferenceSession(model_path, options);
 
            // 创建输入容器
            input_ontainer = new List<NamedOnnxValue>();
 
            image_path = "test_img/bike.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];
 
            for (int c = 0; c < 3; c++)
            {
                for (int i = 0; i < inpHeight; i++)
                {
                    for (int j = 0; j < inpWidth; j++)
                    {
                        float pix = ((byte*)(resize_image.Ptr(i).ToPointer()))[j * 3 + 2 - c];
                        input_tensor_data[c * inpHeight * inpWidth + i * inpWidth + j] = (float)(pix / 255.0 - 0.5);
                    }
                }
            }
 
            input_tensor = new DenseTensor<float>(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("input", 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[] pred = results_onnxvalue[0].AsTensor<float>().ToArray();
 
            Mat mask = new Mat(outHeight, outWidth, MatType.CV_32FC1, pred);
            double min_value, max_value;
            Cv2.MinMaxLoc(mask, out min_value, out max_value);
 
            mask = (mask - min_value) / (max_value - min_value);
 
            mask *= 255;
            mask.ConvertTo(mask, MatType.CV_8UC1);
 
            Cv2.Resize(mask, mask, new OpenCvSharp.Size(image.Cols, image.Rows));
 
            Mat result_image = mask.Clone();
 
            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.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);
        }
    }
}

到此这篇关于C# Onnx实现DIS高精度图像二类分割的文章就介绍到这了,更多相关C# Onnx图像二类分割内容请搜索脚本之家以前的文章或继续浏览下面的相关文章希望大家以后多多支持脚本之家!

您可能感兴趣的文章:
阅读全文