C# OnnxRuntime Diffusion-Low-Light 低光照图像增强

目录

说明

效果

模型信息

项目

代码

下载

说明

官网地址：https://github.com/JianghaiSCU/Diffusion-Low-Light

代码实现参考：https://github.com/hpc203/Diffusion-Low-Light-onnxrun

效果

模型信息

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

Inputs
-------------------------
name：input
tensor：Float[1, 3, 192, 320]
---------------------------------------------------------------

Outputs
-------------------------
name：output
tensor：Float[1, 3, 192, 320]
---------------------------------------------------------------

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 input_tensor;
        List input_container;
        IDisposableReadOnlyCollection result_infer;
        DisposableNamedOnnxValue[] results_onnxvalue;
        Tensor 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;
        }

        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);
            int cols = image.Cols;
            int rows = image.Rows;

            Mat dstimg = new Mat();
            Cv2.CvtColor(image, dstimg, ColorConversionCodes.BGR2RGB);
            Cv2.Resize(dstimg, dstimg, new OpenCvSharp.Size(inpWidth, inpHeight));
            dstimg.ConvertTo(dstimg, MatType.CV_32FC3, 1 / 255.0f);

            //输入Tensor
            input_tensor = new DenseTensor(Common.ExtractMat(dstimg), 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_container.Add(NamedOnnxValue.CreateFromTensor("input", 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();

            int[] out_shape = result_tensors.Dimensions.ToArray();
            int out_h = out_shape[2];
            int out_w = out_shape[3];
            float[] pred = result_tensors.ToArray();

            float[] temp_r = new float[out_h * out_w];
            float[] temp_g = new float[out_h * out_w];
            float[] temp_b = new float[out_h * out_w];

            Array.Copy(pred, temp_b, out_h * out_w);
            Array.Copy(pred, out_h * out_w, temp_g, 0, out_h * out_w);
            Array.Copy(pred, out_h * out_w * 2, temp_r, 0, out_h * out_w);

            int channel_step = out_h * out_w;
            Mat bmat = new Mat(out_h, out_w, MatType.CV_32FC1, temp_b);
            Mat gmat = new Mat(out_h, out_w, MatType.CV_32FC1, temp_g);
            Mat rmat = new Mat(out_h, out_w, MatType.CV_32FC1, temp_r);

            bmat *= 255.0f;
            gmat *= 255.0f;
            rmat *= 255.0f;

            Mat[] channel_mats = new Mat[] { rmat, gmat, bmat };
            dstimg = new Mat();
            Cv2.Merge(channel_mats.ToArray(), dstimg);
            dstimg.ConvertTo(dstimg, MatType.CV_8UC3);

            Cv2.Resize(dstimg, dstimg, new OpenCvSharp.Size(cols, rows));

            pictureBox2.Image = new Bitmap(dstimg.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/diffusion_low_light_1x3x192x320.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);

            // 创建输入容器
            input_container = new List();

            image_path = "test_img/1.png";
            pictureBox1.Image = new Bitmap(image_path);
            image = new Mat(image_path);

            inpHeight = 192;
            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);
            }
        }
    }
}
 

  1. using Microsoft.ML.OnnxRuntime;
  2. using Microsoft.ML.OnnxRuntime.Tensors;
  3. using OpenCvSharp;
  4. using System;
  5. using System.Collections.Generic;
  6. using System.Drawing;
  7. using System.Drawing.Imaging;
  8. using System.Linq;
  9. using System.Windows.Forms;
  10.  
  11. namespace Onnx_Demo
  12. {
  13.     public partial class Form1 : Form
  14.     {
  15.         public Form1()
  16.         {
  17.             InitializeComponent();
  18.         }
  19.  
  20.         string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";
  21.         string image_path = "";
  22.         string startupPath;
  23.         DateTime dt1 = DateTime.Now;
  24.         DateTime dt2 = DateTime.Now;
  25.         string model_path;
  26.         Mat image;
  27.         Mat result_image;
  28.         SessionOptions options;
  29.         InferenceSession onnx_session;
  30.         Tensor<float> input_tensor;
  31.         List<NamedOnnxValue> input_container;
  32.         IDisposableReadOnlyCollection<DisposableNamedOnnxValue> result_infer;
  33.         DisposableNamedOnnxValue[] results_onnxvalue;
  34.         Tensor<float> result_tensors;
  35.         int inpHeight, inpWidth;
  36.  
  37.         private void button1_Click(object sender, EventArgs e)
  38.         {
  39.             OpenFileDialog ofd = new OpenFileDialog();
  40.             ofd.Filter = fileFilter;
  41.             if (ofd.ShowDialog() != DialogResult.OK) return;
  42.             pictureBox1.Image = null;
  43.             image_path = ofd.FileName;
  44.             pictureBox1.Image = new Bitmap(image_path);
  45.             textBox1.Text = "";
  46.             image = new Mat(image_path);
  47.             pictureBox2.Image = null;
  48.         }
  49.  
  50.         private void button2_Click(object sender, EventArgs e)
  51.         {
  52.             if (image_path == "")
  53.             {
  54.                 return;
  55.             }
  56.  
  57.             button2.Enabled = false;
  58.             pictureBox2.Image = null;
  59.             textBox1.Text = "";
  60.             Application.DoEvents();
  61.  
  62.             //读图片
  63.             image = new Mat(image_path);
  64.             int cols = image.Cols;
  65.             int rows = image.Rows;
  66.  
  67.             Mat dstimg = new Mat();
  68.             Cv2.CvtColor(image, dstimg, ColorConversionCodes.BGR2RGB);
  69.             Cv2.Resize(dstimg, dstimg, new OpenCvSharp.Size(inpWidth, inpHeight));
  70.             dstimg.ConvertTo(dstimg, MatType.CV_32FC3, 1 / 255.0f);
  71.  
  72.             //输入Tensor
  73.             input_tensor = new DenseTensor<float>(Common.ExtractMat(dstimg), new[] { 1, 3, inpHeight, inpWidth });
  74.  
  75.             //将 input_tensor 放入一个输入参数的容器，并指定名称
  76.             input_container.Add(NamedOnnxValue.CreateFromTensor("input", input_tensor));
  77.  
  78.             dt1 = DateTime.Now;
  79.             //运行 Inference 并获取结果
  80.             result_infer = onnx_session.Run(input_container);
  81.             dt2 = DateTime.Now;
  82.  
  83.             // 将输出结果转为DisposableNamedOnnxValue数组
  84.             results_onnxvalue = result_infer.ToArray();
  85.  
  86.             // 读取第一个节点输出并转为Tensor数据
  87.             result_tensors = results_onnxvalue[0].AsTensor<float>();
  88.  
  89.             int[] out_shape = result_tensors.Dimensions.ToArray();
  90.             int out_h = out_shape[2];
  91.             int out_w = out_shape[3];
  92.             float[] pred = result_tensors.ToArray();
  93.  
  94.             float[] temp_r = new float[out_h * out_w];
  95.             float[] temp_g = new float[out_h * out_w];
  96.             float[] temp_b = new float[out_h * out_w];
  97.  
  98.             Array.Copy(pred, temp_b, out_h * out_w);
  99.             Array.Copy(pred, out_h * out_w, temp_g, 0, out_h * out_w);
  100.             Array.Copy(pred, out_h * out_w * 2, temp_r, 0, out_h * out_w);
  101.  
  102.             int channel_step = out_h * out_w;
  103.             Mat bmat = new Mat(out_h, out_w, MatType.CV_32FC1, temp_b);
  104.             Mat gmat = new Mat(out_h, out_w, MatType.CV_32FC1, temp_g);
  105.             Mat rmat = new Mat(out_h, out_w, MatType.CV_32FC1, temp_r);
  106.  
  107.             bmat *= 255.0f;
  108.             gmat *= 255.0f;
  109.             rmat *= 255.0f;
  110.  
  111.             Mat[] channel_mats = new Mat[] { rmat, gmat, bmat };
  112.             dstimg = new Mat();
  113.             Cv2.Merge(channel_mats.ToArray(), dstimg);
  114.             dstimg.ConvertTo(dstimg, MatType.CV_8UC3);
  115.  
  116.             Cv2.Resize(dstimg, dstimg, new OpenCvSharp.Size(cols, rows));
  117.  
  118.             pictureBox2.Image = new Bitmap(dstimg.ToMemoryStream());
  119.             textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";
  120.  
  121.             button2.Enabled = true;
  122.  
  123.         }
  124.  
  125.         private void Form1_Load(object sender, EventArgs e)
  126.         {
  127.             startupPath = System.Windows.Forms.Application.StartupPath;
  128.             model_path = "model/diffusion_low_light_1x3x192x320.onnx";
  129.  
  130.             // 创建输出会话，用于输出模型读取信息
  131.             options = new SessionOptions();
  132.             options.LogSeverityLevel = OrtLoggingLevel.ORT_LOGGING_LEVEL_INFO;
  133.             options.AppendExecutionProvider_CPU(0);// 设置为CPU上运行
  134.  
  135.             // 创建推理模型类，读取本地模型文件
  136.             onnx_session = new InferenceSession(model_path, options);
  137.  
  138.             // 创建输入容器
  139.             input_container = new List<NamedOnnxValue>();
  140.  
  141.             image_path = "test_img/1.png";
  142.             pictureBox1.Image = new Bitmap(image_path);
  143.             image = new Mat(image_path);
  144.  
  145.             inpHeight = 192;
  146.             inpWidth = 320;
  147.  
  148.         }
  149.  
  150.         private void pictureBox1_DoubleClick(object sender, EventArgs e)
  151.         {
  152.             Common.ShowNormalImg(pictureBox1.Image);
  153.         }
  154.  
  155.         private void pictureBox2_DoubleClick(object sender, EventArgs e)
  156.         {
  157.             Common.ShowNormalImg(pictureBox2.Image);
  158.         }
  159.  
  160.         SaveFileDialog sdf = new SaveFileDialog();
  161.         private void button3_Click(object sender, EventArgs e)
  162.         {
  163.             if (pictureBox2.Image == null)
  164.             {
  165.                 return;
  166.             }
  167.             Bitmap output = new Bitmap(pictureBox2.Image);
  168.             sdf.Title = "保存";
  169.             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";
  170.             if (sdf.ShowDialog() == DialogResult.OK)
  171.             {
  172.                 switch (sdf.FilterIndex)
  173.                 {
  174.                     case 1:
  175.                         {
  176.                             output.Save(sdf.FileName, ImageFormat.Jpeg);
  177.                             break;
  178.                         }
  179.                     case 2:
  180.                         {
  181.                             output.Save(sdf.FileName, ImageFormat.Png);
  182.                             break;
  183.                         }
  184.                     case 3:
  185.                         {
  186.                             output.Save(sdf.FileName, ImageFormat.Bmp);
  187.                             break;
  188.                         }
  189.                     case 4:
  190.                         {
  191.                             output.Save(sdf.FileName, ImageFormat.Emf);
  192.                             break;
  193.                         }
  194.                     case 5:
  195.                         {
  196.                             output.Save(sdf.FileName, ImageFormat.Exif);
  197.                             break;
  198.                         }
  199.                     case 6:
  200.                         {
  201.                             output.Save(sdf.FileName, ImageFormat.Gif);
  202.                             break;
  203.                         }
  204.                     case 7:
  205.                         {
  206.                             output.Save(sdf.FileName, ImageFormat.Icon);
  207.                             break;
  208.                         }
  209.  
  210.                     case 8:
  211.                         {
  212.                             output.Save(sdf.FileName, ImageFormat.Tiff);
  213.                             break;
  214.                         }
  215.                     case 9:
  216.                         {
  217.                             output.Save(sdf.FileName, ImageFormat.Wmf);
  218.                             break;
  219.                         }
  220.                 }
  221.                 MessageBox.Show("保存成功，位置：" + sdf.FileName);
  222.             }
  223.         }
  224.     }
  225. }

下载

源码下载

天天代码码天天
微信公众号
.NET 人工智能实践
注：本文转载自blog.csdn.net的天天代码码天天的文章"https://lw112190.blog.csdn.net/article/details/141305745"。版权归原作者所有，此博客不拥有其著作权，亦不承担相应法律责任。如有侵权，请联系我们删除。
复制链接
相关推荐
发表评论

评论记录：

未查询到任何数据！