C# OpenCvSharp DNN Image Retouching

天天代码码天天2024-02-22 0:08

目录

介绍

模型

项目

效果

代码

下载

C# OpenCvSharp DNN Image Retouching

介绍

github地址：https://github.com/hejingwenhejingwen/CSRNet

(ECCV 2020) Conditional Sequential Modulation for Efficient Global Image Retouching

模型

Model Properties

Inputs

name：input

tensor：Float[1, 3, 360, 640]

Outputs

name：output

tensor：Float[1, 3, 360, 640]

项目

效果

代码

using OpenCvSharp;

using OpenCvSharp.Dnn;

using System;

using System.Collections.Generic;

using System.Drawing;

using System.IO;

using System.Linq;

using System.Linq.Expressions;

using System.Numerics;

using System.Reflection;

using System.Windows.Forms;

namespace OpenCvSharp_DNN_Demo

{

public partial class frmMain : Form

{

public frmMain()

{

InitializeComponent();

}

string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";

string image_path = "";

DateTime dt1 = DateTime.Now;

DateTime dt2 = DateTime.Now;

string modelpath;

int inpHeight;

int inpWidth;

Net opencv_net;

Mat BN_image;

Mat image;

Mat result_image;

private void button1_Click(object sender, EventArgs e)

{

OpenFileDialog ofd = new OpenFileDialog();

ofd.Filter = fileFilter;

if (ofd.ShowDialog() != DialogResult.OK) return;

pictureBox1.Image = null;

pictureBox2.Image = null;

textBox1.Text = "";

image_path = ofd.FileName;

pictureBox1.Image = new Bitmap(image_path);

image = new Mat(image_path);

}

private void Form1_Load(object sender, EventArgs e)

{

modelpath = "model/csrnet_360x640.onnx";

inpHeight = 360;

inpWidth = 640;

opencv_net = CvDnn.ReadNetFromOnnx(modelpath);

image_path = "test_img/0014.jpg";

pictureBox1.Image = new Bitmap(image_path);

}

private unsafe void button2_Click(object sender, EventArgs e)

{

if (image_path == "")

{

return;

}

textBox1.Text = "检测中，请稍等......";

pictureBox2.Image = null;

Application.DoEvents();

image = new Mat(image_path);

int srch = image.Rows;

int srcw = image.Cols;

BN_image = CvDnn.BlobFromImage(image, 1 / 255.0, new OpenCvSharp.Size(inpWidth, inpHeight), new Scalar(0, 0, 0), true, false);

//配置图片输入数据

opencv_net.SetInput(BN_image);

//模型推理，读取推理结果

Mat[] outs = new Mat[1] { new Mat() };

string[] outBlobNames = opencv_net.GetUnconnectedOutLayersNames().ToArray();

dt1 = DateTime.Now;

opencv_net.Forward(outs, outBlobNames);

dt2 = DateTime.Now;

float* pdata = (float*)outs[0].Data;

int out_h = outs[0].Size(2);

int out_w = outs[0].Size(3);

int channel_step = out_h * out_w;

float[] data = new float[channel_step * 3];

for (int i = 0; i < data.Length; i++)

{

data[i] = pdata[i] * 255;

if (data[i] < 0)

{

data[i] = 0;

}

else if (data[i] > 255)

{

data[i] = 255;

}

}

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(data, temp_r, out_h * out_w);

Array.Copy(data, out_h * out_w, temp_g, 0, out_h * out_w);

Array.Copy(data, out_h * out_w * 2, temp_b, 0, out_h * out_w);

Mat rmat = new Mat(out_h, out_w, MatType.CV_32F, temp_r);

Mat gmat = new Mat(out_h, out_w, MatType.CV_32F, temp_g);

Mat bmat = new Mat(out_h, out_w, MatType.CV_32F, temp_b);

result_image = new Mat();

Cv2.Merge(new Mat[] { bmat, gmat, rmat }, result_image);

Cv2.Resize(result_image, result_image, new OpenCvSharp.Size(srcw, srch));

pictureBox2.Image = new Bitmap(result_image.ToMemoryStream());

textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";

}

private void pictureBox2_DoubleClick(object sender, EventArgs e)

{

Common.ShowNormalImg(pictureBox2.Image);

}

private void pictureBox1_DoubleClick(object sender, EventArgs e)

{

Common.ShowNormalImg(pictureBox1.Image);

}

}

}

复制代码 
using OpenCvSharp;
using OpenCvSharp.Dnn;
using System;
using System.Collections.Generic;
using System.Drawing;
using System.IO;
using System.Linq;
using System.Linq.Expressions;
using System.Numerics;
using System.Reflection;
using System.Windows.Forms;

namespace OpenCvSharp_DNN_Demo
{
    public partial class frmMain : Form
    {
        public frmMain()
        {
            InitializeComponent();
        }

        string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";
        string image_path = "";

        DateTime dt1 = DateTime.Now;
        DateTime dt2 = DateTime.Now;

        string modelpath;

        int inpHeight;
        int inpWidth;

        Net opencv_net;
        Mat BN_image;

        Mat image;
        Mat result_image;

        private void button1_Click(object sender, EventArgs e)
        {
            OpenFileDialog ofd = new OpenFileDialog();
            ofd.Filter = fileFilter;
            if (ofd.ShowDialog() != DialogResult.OK) return;

            pictureBox1.Image = null;
            pictureBox2.Image = null;
            textBox1.Text = "";

            image_path = ofd.FileName;
            pictureBox1.Image = new Bitmap(image_path);
            image = new Mat(image_path);
        }

        private void Form1_Load(object sender, EventArgs e)
        {
            modelpath = "model/csrnet_360x640.onnx";

            inpHeight = 360;
            inpWidth = 640;

            opencv_net = CvDnn.ReadNetFromOnnx(modelpath);

            image_path = "test_img/0014.jpg";
            pictureBox1.Image = new Bitmap(image_path);

        }

        private unsafe void button2_Click(object sender, EventArgs e)
        {
            if (image_path == "")
            {
                return;
            }
            textBox1.Text = "检测中，请稍等......";
            pictureBox2.Image = null;
            Application.DoEvents();

            image = new Mat(image_path);

            int srch = image.Rows;
            int srcw = image.Cols;


            BN_image = CvDnn.BlobFromImage(image, 1 / 255.0, new OpenCvSharp.Size(inpWidth, inpHeight), new Scalar(0, 0, 0), true, false);

            //配置图片输入数据
            opencv_net.SetInput(BN_image);

            //模型推理，读取推理结果
            Mat[] outs = new Mat[1] { new Mat() };
            string[] outBlobNames = opencv_net.GetUnconnectedOutLayersNames().ToArray();

            dt1 = DateTime.Now;

            opencv_net.Forward(outs, outBlobNames);

            dt2 = DateTime.Now;

            float* pdata = (float*)outs[0].Data;
            int out_h = outs[0].Size(2);
            int out_w = outs[0].Size(3);
            int channel_step = out_h * out_w;
            float[] data = new float[channel_step * 3];
            for (int i = 0; i < data.Length; i++)
            {
                data[i] = pdata[i] * 255;

                if (data[i] < 0)
                {
                    data[i] = 0;
                }
                else if (data[i] > 255)
                {
                    data[i] = 255;
                }
            }

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

            Mat rmat = new Mat(out_h, out_w, MatType.CV_32F, temp_r);
            Mat gmat = new Mat(out_h, out_w, MatType.CV_32F, temp_g);
            Mat bmat = new Mat(out_h, out_w, MatType.CV_32F, temp_b);

            result_image = new Mat();
            Cv2.Merge(new Mat[] { bmat, gmat, rmat }, result_image);

            Cv2.Resize(result_image, result_image, new OpenCvSharp.Size(srcw, srch));

            pictureBox2.Image = new Bitmap(result_image.ToMemoryStream());
            textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";
        }

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

        private void pictureBox1_DoubleClick(object sender, EventArgs e)
        {
            Common.ShowNormalImg(pictureBox1.Image);
        }
    }
}

下载

源码下载

相关推荐
爱意随风起风止意难平1 分钟前
如何用AI赋能学习
人工智能·学习·aigc
Listennnn2 分钟前
Ollama vs. vLLM
人工智能
A达峰绮3 分钟前
AI时代的行业重构：机遇、挑战与生存法则
大数据·人工智能·经验分享·ai·推荐算法
阔跃生物13 分钟前
什么是单细胞测序？
深度学习·阔跃生物·阔跃云
昨日之日200617 分钟前
LatentSync V8版 - 音频驱动视频生成数字人说话视频 更新V1.6版模型 支持50系显卡 支持批量 一键整合包下载
人工智能·音视频
shengjk132 分钟前
最全的 MCP协议的 Stdio 机制代码实战
人工智能
爱学习的茄子1 小时前
【前端实战】三分钟掌握原生JS电影搜索应用，从此告别框架依赖
前端·javascript·深度学习
302AI1 小时前
302.AI | DeepAnyLLM 推理增强框架：为任意大模型注入深度推理能力
人工智能·deepseek
Jamence1 小时前
多模态大语言模型arxiv论文略读（119）
论文阅读·人工智能·语言模型·自然语言处理·论文笔记
广州山泉婚姻1 小时前
智慧零工平台后端开发进阶：Spring Boot 3结合MyBatis-Flex的技术实践与优化【无标题】
人工智能·爬虫·spring
热门推荐
01Coze扣子平台完整体验和实践（附国内和国际版对比）02【图像处理与机器视觉】XJTU期末考点03KGG转MP3工具|非KGM文件|解密音频04从零安装 LLaMA-Factory 微调 Qwen 大模型成功及所有的坑05海康Visionmaster-常见问题排查方法-启动阶段06YOLOv8入门 | 重要性能衡量指标、训练结果评价及分析及影响mAP的因素【发论文关注的指标】07扣子（coze）实战|我用扣子搭建了一个自动分析小红薯笔记内容的AI应用|详细步骤拆解08DeepSeek各版本说明与优缺点分析09【SpeedAI科研小助手】2分钟极速解决知网维普重复率、AIGC率过高，一键全文降！文件格式不变，公式都保留的！10坚果投影仪J10如何用苹果Siri开关机并和米家联动