C# OnnxRuntime 部署 DAViD 软前景分割

说明

官网地址：github.com/microsoft/D...

模型下载

效果

模型信息

Model Properties
-------------------------
metadata：{}
---------------------------------------------------------------

Inputs
-------------------------
name：input
tensor：Float[-1, 3, 512, 512]
---------------------------------------------------------------

Outputs
-------------------------
name：output
tensor：Float[-1, 1, 512, 512]
---------------------------------------------------------------

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();
        }

        // ----- 字段定义 -----
        string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.png";
        string image_path = "";
        string startupPath;
        DateTime dt1 = DateTime.Now;
        DateTime dt2 = DateTime.Now;
        string model_path;
        Mat image;                       // 原始图像（BGR）
        Mat result_image_with_alpha;     // 最终带有透明背景的图像
        SessionOptions options;
        InferenceSession onnx_session;
        Tensor<float> input_tensor;
        List<NamedOnnxValue> input_container;
        IDisposableReadOnlyCollection<DisposableNamedOnnxValue> result_infer;
        int inpHeight, inpWidth;

        // DAViD 模型二值化阈值（默认0，不二值化，输出软掩膜）
        private float binarizationThreshold = 0f;

        // ----- 按钮：选择图片 -----
        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;
        }

        // ----- 按钮：执行推理 -----
        private void button2_Click(object sender, EventArgs e)
        {
            if (string.IsNullOrEmpty(image_path))
            {
                MessageBox.Show("请先选择图片！");
                return;
            }

            binarizationThreshold = 0.0f;

            button2.Enabled = false;
            pictureBox2.Image = null;
            textBox1.Text = "";
            Application.DoEvents();

            // 读取原始图像（BGR）
            image = new Mat(image_path);
            int originalWidth = image.Cols;
            int originalHeight = image.Rows;

            // ------------------ 预处理 ------------------
            // 1. 直接缩放 BGR 图像至模型输入尺寸 (512x512)
            Mat resized = new Mat();
            Cv2.Resize(image, resized, new OpenCvSharp.Size(inpWidth, inpHeight));

            // 2. 转换为浮点型并归一化到 [0, 1]
            resized.ConvertTo(resized, MatType.CV_32FC3, 1.0 / 255.0);

            // 3. 分离 BGR 通道（Split 顺序为 B, G, R）
            Mat[] channels = Cv2.Split(resized);
            int channelSize = inpHeight * inpWidth;
            float[] inputData = new float[3 * channelSize];

            for (int c = 0; c < 3; c++)
            {
                float[] channelData = new float[channelSize];
                System.Runtime.InteropServices.Marshal.Copy(channels[c].Data, channelData, 0, channelSize);
                // 直接复制已归一化的像素值，无需额外处理
                Array.Copy(channelData, 0, inputData, c * channelSize, channelSize);
            }

            // 4. 创建输入张量 (N, C, H, W)
            input_tensor = new DenseTensor<float>(inputData, new[] { 1, 3, inpHeight, inpWidth });
            input_container.Clear();
            input_container.Add(NamedOnnxValue.CreateFromTensor("input", input_tensor));

            // ------------------ 推理 ------------------
            dt1 = DateTime.Now;
            result_infer = onnx_session.Run(input_container);
            dt2 = DateTime.Now;

            // 获取输出（模型输出名称为 "output"，形状 [1, 1, 512, 512]）
            var output = result_infer.First(x => x.Name == "output").AsTensor<float>();
            int[] outShape = output.Dimensions.ToArray();
            int outH = outShape[2];
            int outW = outShape[3];
            float[] predFloat = output.ToArray();   // 已经是 float

            // 创建单通道 Mat (CV_32FC1)，值域 [0,1]
            Mat softMask = new Mat(outH, outW, MatType.CV_32FC1, predFloat);

            // ------------------ 后处理 ------------------
            // 1. 双线性插值至原始尺寸
            Mat maskResized = new Mat();
            Cv2.Resize(softMask, maskResized, new OpenCvSharp.Size(originalWidth, originalHeight), interpolation: InterpolationFlags.Linear);


            // 2. 限制值域在 [0,1]（防止数值误差）

            //maskResized.SetTo(0, maskResized.LessThan(0));
            //maskResized.SetTo(1, maskResized.GreaterThanOrEqual(1));
            
            //Cv2.Threshold(maskResized, maskResized, 1.0, 1.0, ThresholdTypes.Trunc);
            //Cv2.Threshold(maskResized, maskResized, 0.0, 0.0, ThresholdTypes.Tozero);

            Mat finalAlpha;
            if (binarizationThreshold > 0)
            {
                // 二值化：大于阈值设为1，其余为0
                Mat binaryMask = new Mat(maskResized.Size(), MatType.CV_32FC1, 0.0f);
                Cv2.Threshold(maskResized, binaryMask, binarizationThreshold, 1.0, ThresholdTypes.Binary);
                finalAlpha = binaryMask;
            }
            else
            {
                finalAlpha = maskResized;
            }

            // 转换为 8 位单通道 (0~255) 用于 alpha 合成
            Mat alphaMask = new Mat();
            finalAlpha.ConvertTo(alphaMask, MatType.CV_8UC1, 255.0);

            // ------------------ 合成透明背景图像 ------------------
            Mat rgba = new Mat();
            Cv2.CvtColor(image, rgba, ColorConversionCodes.BGR2BGRA);
            Mat[] bgraChannels = Cv2.Split(rgba);
            bgraChannels[3] = alphaMask;
            Cv2.Merge(bgraChannels, rgba);

            result_image_with_alpha = rgba.Clone();

            // 显示结果（注意：PictureBox 默认不支持透明，但保存 PNG 时有效）
            pictureBox2.Image = new Bitmap(rgba.ToMemoryStream());
            textBox1.Text = $"推理耗时: {(dt2 - dt1).TotalMilliseconds:F2} ms";
            button2.Enabled = true;
        }

        // ----- 窗体加载：初始化模型 -----
        private void Form1_Load(object sender, EventArgs e)
        {
            startupPath = Application.StartupPath;
            // 请根据实际模型路径修改，模型输入尺寸应为 512x512
            model_path = System.IO.Path.Combine(startupPath, "model", "foreground-segmentation-model-vitb16_384.onnx");
            if (!System.IO.File.Exists(model_path))
            {
                MessageBox.Show($"模型文件不存在: {model_path}");
                return;
            }

            options = new SessionOptions();
            options.LogSeverityLevel = OrtLoggingLevel.ORT_LOGGING_LEVEL_INFO;
            options.AppendExecutionProvider_CPU(0);
            // 若需 CUDA 支持，请取消注释并安装对应运行库
            // options.AppendExecutionProvider_CUDA(0);

            onnx_session = new InferenceSession(model_path, options);
            input_container = new List<NamedOnnxValue>();

            // 模型固定输入尺寸 (DAViD 为 512x512)
            inpHeight = 512;
            inpWidth = 512;

            // 可选默认测试图片
            string testImg = System.IO.Path.Combine(startupPath, "test_img", "1.jpg");
            if (System.IO.File.Exists(testImg))
            {
                image_path = testImg;
                pictureBox1.Image = new Bitmap(image_path);
                image = new Mat(image_path);
            }
        }

        // ----- 双击图片放大显示 -----
        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 (result_image_with_alpha == null || result_image_with_alpha.Empty())
            {
                MessageBox.Show("请先进行推理！");
                return;
            }

            sdf.Title = "保存透明背景图片";
            sdf.Filter = "PNG图片 (*.png)|*.png|JPEG图片 (*.jpg)|*.jpg|BMP图片 (*.bmp)|*.bmp";
            sdf.FilterIndex = 1;
            if (sdf.ShowDialog() == DialogResult.OK)
            {
                string ext = System.IO.Path.GetExtension(sdf.FileName).ToLower();
                ImageFormat format = ImageFormat.Png;
                if (ext == ".jpg" || ext == ".jpeg")
                    format = ImageFormat.Jpeg;
                elseif (ext == ".bmp")
                    format = ImageFormat.Bmp;

                using (var stream = result_image_with_alpha.ToMemoryStream())
                using (var bitmap = new Bitmap(stream))
                {
                    bitmap.Save(sdf.FileName, format);
                }
                MessageBox.Show($"保存成功: {sdf.FileName}");
            }
        }
    }
}