devbox
IT小白
这个屌丝很懒，什么也没留下！
关注作者
热门标签
热门文章
当前位置:   article > 正文

C# SwinV2 Stable Diffusion 提示词反推 Onnx Demo_stable diffusion c#

作者：IT小白 | 2024-03-26 21:12:49

赞

踩

stable diffusion c#

目录

介绍

效果

CPU

GPU

模型信息

项目

代码

下载 

C# SwinV2 Stable Diffusion 提示词反推 Onnx Demo

介绍

模型出处github地址：https://github.com/SmilingWolf/SW-CV-ModelZoo

模型下载地址：https://huggingface.co/SmilingWolf/wd-v1-4-swinv2-tagger-v2

效果

CPU

GPU

模型信息

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

Inputs
-------------------------
name：input_1:0
tensor：Float[1, 448, 448, 3]
---------------------------------------------------------------

Outputs
-------------------------
name：predictions_sigmoid
tensor：Float[1, 9083]
---------------------------------------------------------------

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.IO;
using System.Linq;
using System.Text;
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 = "";
        DateTime dt1 = DateTime.Now;
        DateTime dt2 = DateTime.Now;
        string model_path;
        Mat 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;

        StringBuilder sb = new StringBuilder();

        public string[] class_names;

        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);
        }

        private void button2_Click(object sender, EventArgs e)
        {
            if (image_path == "")
            {
                return;
            }

            button2.Enabled = false;
            textBox1.Text = "";
            sb.Clear();
            Application.DoEvents();

            //图片缩放
            image = new Mat(image_path);
            int max_image_length = image.Cols > image.Rows ? image.Cols : image.Rows;
            Mat max_image = Mat.Zeros(new OpenCvSharp.Size(max_image_length, max_image_length), MatType.CV_8UC3);
            Rect roi = new Rect(0, 0, image.Cols, image.Rows);
            image.CopyTo(new Mat(max_image, roi));

            float[] result_array;

            // 将图片转为RGB通道
            Mat image_rgb = new Mat();
            Cv2.CvtColor(max_image, image_rgb, ColorConversionCodes.BGR2RGB);
            Mat resize_image = new Mat();
            Cv2.Resize(max_image, resize_image, new OpenCvSharp.Size(448, 448));

            // 输入Tensor
            for (int y = 0; y < resize_image.Height; y++)
            {
                for (int x = 0; x < resize_image.Width; x++)
                {
                    input_tensor[0, y, x, 0] = resize_image.At<Vec3b>(y, x)[0];
                    input_tensor[0, y, x, 1] = resize_image.At<Vec3b>(y, x)[1];
                    input_tensor[0, y, x, 2] = resize_image.At<Vec3b>(y, x)[2];
                }
            }

            //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_1:0", 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>();

            result_array = result_tensors.ToArray();

            List<ScoreIndex> ltResult = new List<ScoreIndex>();
            ScoreIndex temp;
            for (int i = 0; i < result_array.Length; i++)
            {
                temp = new ScoreIndex(i, result_array[i]);
                ltResult.Add(temp);
            }

            //根据分数倒序排序，取前14个
            var SortedByScore = ltResult.OrderByDescending(p => p.Score).ToList().Take(14);

            foreach (var item in SortedByScore)
            {
                sb.Append(class_names[item.Index] + ",");
            }
            sb.Length--; // 将长度减1来移除最后一个字符

            sb.AppendLine("");
            sb.AppendLine("------------------");
            
            // 只取分数最高的
            // float max = result_array.Max();
            // int maxIndex = Array.IndexOf(result_array, max);
            // sb.AppendLine(class_names[maxIndex]+" "+ max.ToString("P2"));
           
            sb.AppendLine("推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms");
            textBox1.Text = sb.ToString();
            button2.Enabled = true;
        }

        private void Form1_Load(object sender, EventArgs e)
        {
            model_path = "model/model.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

            // 输入Tensor
            input_tensor = new DenseTensor<float>(new[] { 1, 448, 448, 3 });
            // 创建输入容器
            input_container = new List<NamedOnnxValue>();

            image_path = "test_img/test.jpg";
            pictureBox1.Image = new Bitmap(image_path);
            image = new Mat(image_path);

            List<string> str = new List<string>();
            StreamReader sr = new StreamReader("model/lable.txt");
            string line;
            while ((line = sr.ReadLine()) != null)
            {
                str.Add(line);
            }
            class_names = str.ToArray();
        }

    }
}

  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.IO;
  8. using System.Linq;
  9. using System.Text;
  10. using System.Windows.Forms;
  11.  
  12. namespace Onnx_Demo
  13. {
  14.     public partial class Form1 : Form
  15.     {
  16.         public Form1()
  17.         {
  18.             InitializeComponent();
  19.         }
  20.  
  21.         string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";
  22.         string image_path = "";
  23.         DateTime dt1 = DateTime.Now;
  24.         DateTime dt2 = DateTime.Now;
  25.         string model_path;
  26.         Mat image;
  27.  
  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.  
  35.         Tensor<float> result_tensors;
  36.  
  37.         StringBuilder sb = new StringBuilder();
  38.  
  39.         public string[] class_names;
  40.  
  41.         private void button1_Click(object sender, EventArgs e)
  42.         {
  43.             OpenFileDialog ofd = new OpenFileDialog();
  44.             ofd.Filter = fileFilter;
  45.             if (ofd.ShowDialog() != DialogResult.OK) return;
  46.             pictureBox1.Image = null;
  47.             image_path = ofd.FileName;
  48.             pictureBox1.Image = new Bitmap(image_path);
  49.             textBox1.Text = "";
  50.             image = new Mat(image_path);
  51.         }
  52.  
  53.         private void button2_Click(object sender, EventArgs e)
  54.         {
  55.             if (image_path == "")
  56.             {
  57.                 return;
  58.             }
  59.  
  60.             button2.Enabled = false;
  61.             textBox1.Text = "";
  62.             sb.Clear();
  63.             Application.DoEvents();
  64.  
  65.             //图片缩放
  66.             image = new Mat(image_path);
  67.             int max_image_length = image.Cols > image.Rows ? image.Cols : image.Rows;
  68.             Mat max_image = Mat.Zeros(new OpenCvSharp.Size(max_image_length, max_image_length), MatType.CV_8UC3);
  69.             Rect roi = new Rect(0, 0, image.Cols, image.Rows);
  70.             image.CopyTo(new Mat(max_image, roi));
  71.  
  72.             float[] result_array;
  73.  
  74.             // 将图片转为RGB通道
  75.             Mat image_rgb = new Mat();
  76.             Cv2.CvtColor(max_image, image_rgb, ColorConversionCodes.BGR2RGB);
  77.             Mat resize_image = new Mat();
  78.             Cv2.Resize(max_image, resize_image, new OpenCvSharp.Size(448, 448));
  79.  
  80.             // 输入Tensor
  81.             for (int y = 0; y < resize_image.Height; y++)
  82.             {
  83.                 for (int x = 0; x < resize_image.Width; x++)
  84.                 {
  85.                     input_tensor[0, y, x, 0] = resize_image.At<Vec3b>(y, x)[0];
  86.                     input_tensor[0, y, x, 1] = resize_image.At<Vec3b>(y, x)[1];
  87.                     input_tensor[0, y, x, 2] = resize_image.At<Vec3b>(y, x)[2];
  88.                 }
  89.             }
  90.  
  91.             //将 input_tensor 放入一个输入参数的容器，并指定名称
  92.             input_container.Add(NamedOnnxValue.CreateFromTensor("input_1:0", input_tensor));
  93.  
  94.             dt1 = DateTime.Now;
  95.             //运行 Inference 并获取结果
  96.             result_infer = onnx_session.Run(input_container);
  97.             dt2 = DateTime.Now;
  98.  
  99.             // 将输出结果转为DisposableNamedOnnxValue数组
  100.             results_onnxvalue = result_infer.ToArray();
  101.  
  102.             // 读取第一个节点输出并转为Tensor数据
  103.             result_tensors = results_onnxvalue[0].AsTensor<float>();
  104.  
  105.             result_array = result_tensors.ToArray();
  106.  
  107.             List<ScoreIndex> ltResult = new List<ScoreIndex>();
  108.             ScoreIndex temp;
  109.             for (int i = 0; i < result_array.Length; i++)
  110.             {
  111.                 temp = new ScoreIndex(i, result_array[i]);
  112.                 ltResult.Add(temp);
  113.             }
  114.  
  115.             //根据分数倒序排序，取前14个
  116.             var SortedByScore = ltResult.OrderByDescending(p => p.Score).ToList().Take(14);
  117.  
  118.             foreach (var item in SortedByScore)
  119.             {
  120.                 sb.Append(class_names[item.Index] + ",");
  121.             }
  122.             sb.Length--; // 将长度减1来移除最后一个字符
  123.  
  124.             sb.AppendLine("");
  125.             sb.AppendLine("------------------");
  126.             
  127.             // 只取分数最高的
  128.             // float max = result_array.Max();
  129.             // int maxIndex = Array.IndexOf(result_array, max);
  130.             // sb.AppendLine(class_names[maxIndex]+" "+ max.ToString("P2"));
  131.            
  132.             sb.AppendLine("推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms");
  133.             textBox1.Text = sb.ToString();
  134.             button2.Enabled = true;
  135.         }
  136.  
  137.         private void Form1_Load(object sender, EventArgs e)
  138.         {
  139.             model_path = "model/model.onnx";
  140.  
  141.             // 创建输出会话，用于输出模型读取信息
  142.             options = new SessionOptions();
  143.             options.LogSeverityLevel = OrtLoggingLevel.ORT_LOGGING_LEVEL_INFO;
  144.             options.AppendExecutionProvider_CPU(0);// 设置为CPU上运行
  145.  
  146.             // 创建推理模型类，读取本地模型文件
  147.             onnx_session = new InferenceSession(model_path, options);//model_path 为onnx模型文件的路径
  148.  
  149.             // 输入Tensor
  150.             input_tensor = new DenseTensor<float>(new[] { 1, 448, 448, 3 });
  151.             // 创建输入容器
  152.             input_container = new List<NamedOnnxValue>();
  153.  
  154.             image_path = "test_img/test.jpg";
  155.             pictureBox1.Image = new Bitmap(image_path);
  156.             image = new Mat(image_path);
  157.  
  158.             List<string> str = new List<string>();
  159.             StreamReader sr = new StreamReader("model/lable.txt");
  160.             string line;
  161.             while ((line = sr.ReadLine()) != null)
  162.             {
  163.                 str.Add(line);
  164.             }
  165.             class_names = str.ToArray();
  166.         }
  167.  
  168.     }
  169. }

下载 

源码下载

声明：本文内容由网友自发贡献，不代表【wpsshop博客】立场，版权归原作者所有，本站不承担相应法律责任。如您发现有侵权的内容，请联系我们。转载请注明出处：https://www.wpsshop.cn/w/IT小白/article/detail/319731
推荐阅读