C# SwinV2 Stable Diffusion 提示词反推 Onnx Demo

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();

}

}

}

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();
        }

    }
}

下载

源码下载

相关推荐
禁默3 分钟前
第六届机器人、智能控制与人工智能国际学术会议(RICAI 2024)
人工智能·机器人·智能控制
Robot25111 分钟前
浅谈,华为切入具身智能赛道
人工智能
只怕自己不够好16 分钟前
OpenCV 图像运算全解析:加法、位运算(与、异或)在图像处理中的奇妙应用
图像处理·人工智能·opencv
余生H1 小时前
transformer.js(三):底层架构及性能优化指南
javascript·深度学习·架构·transformer
果冻人工智能1 小时前
2025 年将颠覆商业的 8 大 AI 应用场景
人工智能·ai员工
代码不行的搬运工1 小时前
神经网络12-Time-Series Transformer (TST)模型
人工智能·神经网络·transformer
石小石Orz1 小时前
Three.js + AI:AI 算法生成 3D 萤火虫飞舞效果~
javascript·人工智能·算法
罗小罗同学2 小时前
医工交叉入门书籍分享:Transformer模型在机器学习领域的应用|个人观点·24-11-22
深度学习·机器学习·transformer
孤独且没人爱的纸鹤2 小时前
【深度学习】:从人工神经网络的基础原理到循环神经网络的先进技术,跨越智能算法的关键发展阶段及其未来趋势,探索技术进步与应用挑战
人工智能·python·深度学习·机器学习·ai
阿_旭2 小时前
TensorFlow构建CNN卷积神经网络模型的基本步骤:数据处理、模型构建、模型训练
人工智能·深度学习·cnn·tensorflow