网站首页 > 后端 > 正文

人工智能计算机视觉 opencv 深度学习机器学习神经网络 C# Image Caption

微信小程序怎么做店铺后端 2024-01-19 12 0

介绍

效果

模型

decoder_fc_nsc.onnx

encoder.onnx

项目

代码

下载

C# Image Caption

介绍

地址：https://github.com/ruotianluo/ImageCaptioning.pytorch

I decide to sync up this repo and self-critical.pytorch. (The old master is in old master branch for archive)

效果

模型

decoder_fc_nsc.onnx

Inputs ------------------------- name：fc_feats tensor：Float[1, 2048] ---------------------------------------------------------------

Outputs ------------------------- name：seq tensor：Int64[1, 20] name：logprobs tensor：Float[1, 20, 9488] ---------------------------------------------------------------

encoder.onnx

Inputs ------------------------- name：img tensor：Float[1, 3, 640, 640] ---------------------------------------------------------------

Outputs ------------------------- name：fc tensor：Float[2048] ---------------------------------------------------------------

项目

代码

using Microsoft.ML.OnnxRuntime; using Microsoft.ML.OnnxRuntime.Tensors; using OpenCvSharp; using OpenCvSharp.Dnn; using System; using System.Collections.Generic; using System.Drawing; using System.Drawing.Imaging; using System.IO; using System.Linq; using System.Windows.Forms;

namespace ImageCaption { public partial class Form1 : Form { public Form1() { InitializeComponent(); }

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

Net net;

int feat_len; int D; int inpWidth = 640; int inpHeight = 640; float[] mean = new float[] { 0.485f, 0.456f, 0.406f }; float[] std = new float[] { 0.229f, 0.224f, 0.225f };

Dictionary ix_to_word = new Dictionary();

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

button2.Enabled = false; pictureBox2.Image = null; textBox1.Text = ""; pictureBox2.Image = null; Application.DoEvents();

//图片缩放 image = new Mat(image_path);

Mat temp_image = new Mat(); Cv2.Resize(image, temp_image, new OpenCvSharp.Size(inpWidth, inpHeight)); Normalize(temp_image);

Mat blob = CvDnn.BlobFromImage(temp_image);

//配置图片输入数据 net.SetInput(blob);

Mat result_mat = net.Forward();

float* ptr_feat = (float*)result_mat.Data;

for (int i = 0; i < 2048; i++) { input_tensor[0, i] = ptr_feat[i]; }

//将 input_tensor 放入一个输入参数的容器，并指定名称 input_container.Add(NamedOnnxValue.CreateFromTensor("fc_feats", input_tensor));

//运行 Inference 并获取结果 result_infer = onnx_session.Run(input_container);

// 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();

Int64[] result_array = result_tensors.ToArray();

string words = ""; for (int k = 0; k < D; k++) { if (result_array[k] > 0) { if (words.Length > 0) { words += " "; } words += ix_to_word[result_array[k].ToString()]; } else { break; } }

result_image = image.Clone();

Cv2.PutText(result_image, words , new OpenCvSharp.Point(10, 60) , HersheyFonts.HersheySimplex , 1 , new Scalar(0, 0, 255) , 2 );

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

textBox1.Text = words;

button2.Enabled = true; }

public void Normalize(Mat src) { src.ConvertTo(src, MatType.CV_32FC3, 1.0 / 255);

Mat[] bgr = src.Split(); for (int i = 0; i < bgr.Length; ++i) { bgr[i].ConvertTo(bgr[i], MatType.CV_32FC1, 1 / std[i], (0.0 - mean[i]) / std[i]); }

Cv2.Merge(bgr, src);

foreach (Mat channel in bgr) { channel.Dispose(); } }

private void Form1_Load(object sender, EventArgs e) { startupPath = System.Windows.Forms.Application.StartupPath;

model_path = "model/decoder_fc_nsc.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(new[] { 1, 2048 }); // 创建输入容器 input_container = new List();

feat_len = 2048; D = 20;

//初始化网络类，读取本地模型 net = CvDnn.ReadNetFromOnnx("model/encoder.onnx");

StreamReader sr = new StreamReader("model/vocab.txt"); string line; while ((line = sr.ReadLine()) != null) { ix_to_word.Add(line.Split(':')[0], line.Split(':')[1]); }

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

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); } } } }

using Microsoft.ML.OnnxRuntime;

using Microsoft.ML.OnnxRuntime.Tensors;

using OpenCvSharp;

using OpenCvSharp.Dnn;

using System;

using System.Collections.Generic;

using System.Drawing;

using System.Drawing.Imaging;

using System.IO;

using System.Linq;

using System.Windows.Forms;

namespace ImageCaption

{

public partial class Form1 : Form

{

public Form1()

{

InitializeComponent();

}

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

string image_path = "";

string startupPath;

string classer_path;

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;

Net net;

int feat_len;

int D;

int inpWidth = 640;

int inpHeight = 640;

float[] mean = new float[] { 0.485f, 0.456f, 0.406f };

float[] std = new float[] { 0.229f, 0.224f, 0.225f };

Dictionary ix_to_word = new Dictionary();

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 unsafe void button2_Click(object sender, EventArgs e)

{

if (image_path == "")

{

return;

}

button2.Enabled = false;

pictureBox2.Image = null;

textBox1.Text = "";

pictureBox2.Image = null;

Application.DoEvents();

//图片缩放

image = new Mat(image_path);

Mat temp_image = new Mat();

Cv2.Resize(image, temp_image, new OpenCvSharp.Size(inpWidth, inpHeight));

Normalize(temp_image);

Mat blob = CvDnn.BlobFromImage(temp_image);

//配置图片输入数据

net.SetInput(blob);

Mat result_mat = net.Forward();

float* ptr_feat = (float*)result_mat.Data;

for (int i = 0; i < 2048; i++)

{

input_tensor[0, i] = ptr_feat[i];

}

//将 input_tensor 放入一个输入参数的容器，并指定名称

input_container.Add(NamedOnnxValue.CreateFromTensor("fc_feats", input_tensor));

//运行 Inference 并获取结果

result_infer = onnx_session.Run(input_container);

// 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();

Int64[] result_array = result_tensors.ToArray();

string words = "";

for (int k = 0; k < D; k++)

{

if (result_array[k] > 0)

{

if (words.Length > 0)

{

words += " ";

}

words += ix_to_word[result_array[k].ToString()];

}

else

{

break;

}

result_image = image.Clone();

Cv2.PutText(result_image, words

, new OpenCvSharp.Point(10, 60)

, HersheyFonts.HersheySimplex

, 1

, new Scalar(0, 0, 255)

, 2

);

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

textBox1.Text = words;

button2.Enabled = true;

}

public void Normalize(Mat src)

{

src.ConvertTo(src, MatType.CV_32FC3, 1.0 / 255);

Mat[] bgr = src.Split();

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

{

bgr[i].ConvertTo(bgr[i], MatType.CV_32FC1, 1 / std[i], (0.0 - mean[i]) / std[i]);

}

Cv2.Merge(bgr, src);

foreach (Mat channel in bgr)

{

channel.Dispose();

}

private void Form1_Load(object sender, EventArgs e)

{

startupPath = System.Windows.Forms.Application.StartupPath;

model_path = "model/decoder_fc_nsc.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(new[] { 1, 2048 });

// 创建输入容器

input_container = new List();

feat_len = 2048;

D = 20;

//初始化网络类，读取本地模型

net = CvDnn.ReadNetFromOnnx("model/encoder.onnx");

StreamReader sr = new StreamReader("model/vocab.txt");

string line;

while ((line = sr.ReadLine()) != null)

{

ix_to_word.Add(line.Split(':')[0], line.Split(':')[1]);

}

image_path = "test_img/1.jpg";

pictureBox1.Image = new Bitmap(image_path);

image = new Mat(image_path);

}

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";

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);

}

下载

源码下载

好文链接

评论可见，请评论后查看内容，谢谢！！！

您阅读本篇文章共花了：

c#人工智能计算机视觉 opencv 深度学习机器学习神经网络

本文由用户于 2024-01-19 发布在金钥匙，如有疑问，请联系我们。
本文链接：https://www.51969.com/post/18383667.html

金钥匙

人工智能计算机视觉 opencv 深度学习机器学习神经网络 C# Image Caption

开发语言 visualstudio .net C# ListView 的用法

开发语言 C# WPF窗体设计器显示以及App.xaml文件打不开（VS 2022）

发表评论取消回复

金钥匙

人工智能 计算机视觉 opencv 深度学习 机器学习 神经网络 C# Image Caption

开发语言 visualstudio .net C# ListView 的用法

开发语言 C# WPF窗体设计器显示以及App.xaml文件打不开（VS 2022）

相关文章

发表评论取消回复

人工智能计算机视觉 opencv 深度学习机器学习神经网络 C# Image Caption