C# OnnxRuntime 部署 DAViD 深度估计

说明

官网地址：github.com/microsoft/DAViD

模型信息

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

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

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

代码

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

namespace Onnx_Demo
{
    public partial class Form1 : Form
    {
        // ----- 深度估计专用字段 -----
        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 depth_color_map;             // 生成的深度彩色图
        SessionOptions options;
        InferenceSession onnx_session;
        Tensor
<float> input_tensor;
        List
<NamedOnnxValue> input_container;
        IDisposableReadOnlyCollection
<DisposableNamedOnnxValue> result_infer;
        int inpHeight = 512, inpWidth = 512;
        bool inverse_depth = false;       // 是否反转深度（近处亮）

        public Form1()
        {
            InitializeComponent();
        }

        // ----- 按钮1：选择图片 -----

csharp
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;
    depth_color_map = null;
}

// ----- 按钮2：执行深度估计推理 -----
private void button2_Click(object sender, EventArgs e)
{
    if (string.IsNullOrEmpty(image_path))
    {
        MessageBox.Show("请先选择图片！");
        return;
    }

    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. 缩放至模型输入尺寸 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，并按 RGB 顺序填充（模型预期 RGB）
    Mat[] channels = Cv2.Split(resized);   // channels[0]=B, [1]=G, [2]=R
    int channelSize = inpHeight * inpWidth;
    float[] inputData = new float[3 * channelSize];

    // 将 B,G,R 重新排列为 R,G,B
    for (int c = 0; c < 3; c++)
    {
        float[] channelData = new float[channelSize];
        System.Runtime.InteropServices.Marshal.Copy(channels[c].Data, channelData, 0, channelSize);
        int targetIndex = (c == 0) ? 2 : (c == 2) ? 0 : 1; // B->2, G->1, R->0
        Array.Copy(channelData, 0, inputData, targetIndex * channelSize, channelSize);
    }

    // 4. 创建输入张量
    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
    var output = result_infer.First(x => x.Name == "output").AsTensor
<float>();
    var dimensions = output.Dimensions.ToArray();
}

csharp
int outH = dimensions.Length >= 2 ? dimensions[dimensions.Length - 2] : inpHeight;
int outW = dimensions.Length >= 1 ? dimensions[dimensions.Length - 1] : inpWidth;
float[] depthFloat = output.ToArray();

// 创建单通道深度 Mat (CV_32FC1)
Mat depthRaw = new Mat(outH, outW, MatType.CV_32FC1);
System.Runtime.InteropServices.Marshal.Copy(depthFloat, 0, depthRaw.Data, depthFloat.Length);

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

// 2. 反转深度（使近处物体更亮）
if (inverse_depth)
{
    Cv2.Subtract(1.0, depthResized, depthResized);
}

// 3. 归一化深度到 [0,1] 用于彩色映射
double minVal, maxVal;
Cv2.MinMaxLoc(depthResized, out minVal, out maxVal);
float range = (float)(maxVal - minVal);
if (range < 1e-6) range = 1e-6f;
Mat depthNorm = new Mat();
depthResized.ConvertTo(depthNorm, MatType.CV_32FC1, 1.0 / range, -minVal / range);
Cv2.Min(depthNorm, 1.0, depthNorm);
Cv2.Max(depthNorm, 0.0, depthNorm);

// 4. 转换为 8-bit 灰度图
Mat depthGray = new Mat();
depthNorm.ConvertTo(depthGray, MatType.CV_8UC1, 255.0);

// 5. 应用热力图（Inferno 风格）
depth_color_map = new Mat();
Cv2.ApplyColorMap(depthGray, depth_color_map, ColormapTypes.Inferno);

// 显示结果
pictureBox2.Image = new Bitmap(depth_color_map.ToMemoryStream());
textBox1.Text = $"推理耗时: {(dt2 - dt1).TotalMilliseconds:F2} ms\n深度范围: [{minVal:F3}, {maxVal:F3}]";
button2.Enabled = true;
}

// ----- 按钮3：保存深度彩色图 -----
private void button3_Click(object sender, EventArgs e)
{
    if (depth_color_map == null || depth_color_map.Empty())
    {
        MessageBox.Show("请先执行深度估计！");
        return;
    }

    SaveFileDialog sdf = new SaveFileDialog();
    sdf.Title = "保存深度彩色图";
    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)
    {
        Cv2.ImWrite(sdf.FileName, depth_color_map);
        MessageBox.Show($"保存成功: {sdf.FileName}");
    }
}

// ----- 窗体加载：初始化 ONNX 模型 -----
private void Form1_Load(object sender, EventArgs e)
{

请注意，上述代码块中的注释和代码已经按照Markdown格式进行了适当的格式化。

startupPath = Application.StartupPath;
// 深度估计模型路径（请根据实际位置修改）
model_path = System.IO.Path.Combine(startupPath, "model", "depth-model-vitb16_384.onnx");
if (!System.IO.File.Exists(model_path))
{
    MessageBox.Show($"模型文件不存在: {model_path}\n请将模型放置于 {startupPath}\\model\\ 目录下");
    return;
}

options = new SessionOptions();
options.LogSeverityLevel = OrtLoggingLevel.ORT_LOGGING_LEVEL_INFO;
options.AppendExecutionProvider_CPU(0);
// 若需 CUDA，可取消注释
// options.AppendExecutionProvider_CUDA(0);

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

// 可选默认测试图片
string testImg = System.IO.Path.Combine(startupPath, "test_img", "0.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（保留原功能）-----
private void pictureBox1_DoubleClick(object sender, EventArgs e)
{
    Common.ShowNormalImg(pictureBox1.Image);
}

private void pictureBox2_DoubleClick(object sender, EventArgs e)
{
    Common.ShowNormalImg(pictureBox2.Image);
}