C# onnxruntime 部署LYT-Net轻量级低光图像增强

目录

说明

效果

模型信息

项目

代码

---

 

说明

LYT-Net: Lightweight YUV Transformer-based Network for Low-Light Image Enhancement

参考：

https://github.com/albrateanu/LYT-Net

https://github.com/hpc203/Low-Light-Image-Enhancement-onnxrun

效果

模型信息

Model Properties
-------------------------
---------------------------------------------------------------

Inputs
-------------------------
name：input_1
tensor：Float[-1, 240, 320, 3]
---------------------------------------------------------------

Outputs
-------------------------
name：output_1
tensor：Float[-1, 240, 320, 3]
---------------------------------------------------------------

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;
 
        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);
 
            Mat dstimg = new Mat();
 
            Cv2.Resize(image, dstimg, new OpenCvSharp.Size(inpWidth, inpHeight));
 
            dstimg.ConvertTo(dstimg, MatType.CV_32FC3, 1 / 127.5, -1.0);
 
            float* pdata = (float*)dstimg.Data;
            float[] input_tensor_data = new float[1 * 3 * inpWidth * inpHeight];
            for (int i = 0; i < 1 * 3 * inpWidth * inpHeight; i++)
            {
                input_tensor_data[i] = pdata[i];
            }
 
            //输入Tensor
            input_tensor = new DenseTensor<float>(input_tensor_data, new[] { 1, inpHeight, inpWidth, 3 });
 
            //将 input_tensor 放入一个输入参数的容器，并指定名称
            input_container.Add(NamedOnnxValue.CreateFromTensor("input_1", 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();
 
            // 读取第一个节点输出并转为Tensor数据
            result_tensors = results_onnxvalue[0].AsTensor<float>();
 
            var result_array = result_tensors.ToArray();
 
            for (int i = 0; i < result_array.Length; i++)
            {
                result_array[i] = (result_array[i] + 1.0f) * 127.5f;
            }
 
            Mat result_image = new Mat(inpHeight, inpWidth, MatType.CV_32FC3, result_array);
 
            result_image.ConvertTo(result_image, MatType.CV_8UC3);
 
            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/lyt_net_lolv2_real_320x240.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_1.JPG";
            pictureBox1.Image = new Bitmap(image_path);
            image = new Mat(image_path);
 
            inpHeight = 240;
            inpWidth = 320;
 
        }
 
        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|Images (*.emf)|*.emf|Images (*.exif)|*.exif|Images (*.gif)|*.gif|Images (*.ico)|*.ico|Images (*.tiff)|*.tiff|Images (*.wmf)|*.wmf";
            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;
                        }
                    case 4:
                        {
                            output.Save(sdf.FileName, ImageFormat.Emf);
                            break;
                        }
                    case 5:
                        {
                            output.Save(sdf.FileName, ImageFormat.Exif);
                            break;
                        }
                    case 6:
                        {
                            output.Save(sdf.FileName, ImageFormat.Gif);
                            break;
                        }
                    case 7:
                        {
                            output.Save(sdf.FileName, ImageFormat.Icon);
                            break;
                        }
 
                    case 8:
                        {
                            output.Save(sdf.FileName, ImageFormat.Tiff);
                            break;
                        }
                    case 9:
                        {
                            output.Save(sdf.FileName, ImageFormat.Wmf);
                            break;
                        }
                }
                MessageBox.Show("保存成功，位置：" + sdf.FileName);
            }
        }
    }
}

引入地址