C# Onnx Chinese CLIP 通过一句话从图库中搜出来符合要求的图片

效果

生成图片特征

查找踢足球的人

测试图片

模型信息

image_model.onnx

text_model.onnx

项目

代码

Form1.cs

Clip.cs

下载

C# Onnx Chinese CLIP 通过一句话从图库中搜出来符合要求的图片

效果

生成图片特征

查找踢足球的人

测试图片

模型信息

image_model.onnx

Inputs
-------------------------
name：image
tensor：Float[1, 3, 224, 224]
---------------------------------------------------------------

Outputs
-------------------------
name：unnorm_image_features
tensor：Float[1, 512]
---------------------------------------------------------------

text_model.onnx

Inputs
-------------------------
name：text
tensor：Int64[1, 52]
---------------------------------------------------------------

Outputs
-------------------------
name：unnorm_text_features
tensor：Float[1, 512]
---------------------------------------------------------------

项目

代码

Form1.cs

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();
}

Clip mynet = new Clip("model/image_model.onnx", "model/text_model.onnx", "model/myvocab.txt");

float[] imagedir_features;
string image_dir = "test_img";
StringBuilder sb = new StringBuilder();

private void button2_Click(object sender, EventArgs e)
{
//特征向量可以存二进制文件或者向量数据库
imagedir_features = mynet.generate_imagedir_features(image_dir);
txtInfo.Text = "生成完成！";
txtInfo.Text += "有" + mynet.imgnum + "张图片,特征向量长度=" + imagedir_features.Length;
}

private void button3_Click(object sender, EventArgs e)
{
if (imagedir_features == null)
{
MessageBox.Show("请先生成图片特征！");
return;
}

sb.Clear();
txtInfo.Text = "";
lblInfo.Text = "";
pictureBox1.Image = null;

string input_text = txt_input_text.Text;
if (string.IsNullOrEmpty(input_text))
{
return;
}
List<Dictionary<string, float>> top5imglist = mynet.input_text_search_image(input_text, imagedir_features, mynet.imglist);

sb.AppendLine("top5:");
foreach (var item in top5imglist)
{
sb.AppendLine(Path.GetFileName(item.Keys.First()) + " 相似度:" + item[item.Keys.First()].ToString("F2"));
}

txtInfo.Text = sb.ToString();
lblInfo.Text = Path.GetFileName(top5imglist[0].Keys.First());
pictureBox1.Image = new Bitmap(top5imglist[0].Keys.First());

}

private void Form1_Load(object sender, EventArgs e)
{

}
}
}


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();
        }

        Clip mynet = new Clip("model/image_model.onnx", "model/text_model.onnx", "model/myvocab.txt");

        float[] imagedir_features;
        string image_dir = "test_img";
        StringBuilder sb = new StringBuilder();

        private void button2_Click(object sender, EventArgs e)
        {
            //特征向量 可以存二进制文件或者向量数据库
            imagedir_features = mynet.generate_imagedir_features(image_dir);
            txtInfo.Text = "生成完成！";
            txtInfo.Text += "有" + mynet.imgnum + "张图片,特征向量长度=" + imagedir_features.Length;
        }

        private void button3_Click(object sender, EventArgs e)
        {
            if (imagedir_features == null)
            {
                MessageBox.Show("请先生成图片特征！");
                return;
            }

            sb.Clear();
            txtInfo.Text = "";
            lblInfo.Text = "";
            pictureBox1.Image = null;

            string input_text = txt_input_text.Text;
            if (string.IsNullOrEmpty(input_text))
            {
                return;
            }
            List<Dictionary<string, float>> top5imglist = mynet.input_text_search_image(input_text, imagedir_features, mynet.imglist);

            sb.AppendLine("top5:");
            foreach (var item in top5imglist)
            {
                sb.AppendLine(Path.GetFileName(item.Keys.First()) + "  相似度:" + item[item.Keys.First()].ToString("F2"));
            }

            txtInfo.Text = sb.ToString();
            lblInfo.Text = Path.GetFileName(top5imglist[0].Keys.First());
            pictureBox1.Image = new Bitmap(top5imglist[0].Keys.First());

        }

        private void Form1_Load(object sender, EventArgs e)
        {

        }
    }
}

Clip.cs

public class Clip
{
int inpWidth = 224;
int inpHeight = 224;
float[] mean = new float[] { 0.48145466f, 0.4578275f, 0.40821073f };
float[] std = new float[] { 0.26862954f, 0.26130258f, 0.27577711f };

int context_length = 52;
int len_text_feature = 512;

Net net;
float[] image_features_input;

SessionOptions options;
InferenceSession onnx_session;
Tensor<long> input_tensor;
List<NamedOnnxValue> input_container;
IDisposableReadOnlyCollection<DisposableNamedOnnxValue> result_infer;
DisposableNamedOnnxValue[] results_onnxvalue;
Tensor<float> result_tensors;

TokenizerBase tokenizer;

int[] text_tokens_input;
float[,] text_features_input;

public int imgnum = 0;
public List<string> imglist = new List<string>();

public Clip(string image_modelpath, string text_modelpath, string vocab_path)
{
net = CvDnn.ReadNetFromOnnx(image_modelpath);

// 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(text_modelpath, options);//model_path 为onnx模型文件的路径
// 创建输入容器
input_container = new List<NamedOnnxValue>();

load_tokenizer(vocab_path);

}

void load_tokenizer(string vocab_path)
{

tokenizer = new TokenizerClipChinese();
tokenizer.load_tokenize(vocab_path);
text_tokens_input = new int[1024 * context_length];
}

Mat normalize_(Mat src)
{
Cv2.CvtColor(src, src, ColorConversionCodes.BGR2RGB);

Mat[] bgr = src.Split();
for (int i = 0; i < bgr.Length; ++i)
{
bgr[i].ConvertTo(bgr[i], MatType.CV_32FC1, 1.0 / (255.0 * std[i]), (0.0 - mean[i]) / std[i]);
}

Cv2.Merge(bgr, src);

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

return src;
}

unsafe void generate_image_feature(Mat srcimg)
{
Mat temp_image = new Mat();
Cv2.Resize(srcimg, temp_image, new Size(inpWidth, inpHeight), 0, 0, InterpolationFlags.Cubic);
Mat normalized_mat = normalize_(temp_image);
Mat blob = CvDnn.BlobFromImage(normalized_mat);
net.SetInput(blob);
//模型推理，读取推理结果
Mat[] outs = new Mat[1] { new Mat() };
string[] outBlobNames = net.GetUnconnectedOutLayersNames().ToArray();
net.Forward(outs, outBlobNames);
float* ptr_feat = (float*)outs[0].Data;
int len_image_feature = outs[0].Size(1); //忽略第0维batchsize=1, len_image_feature是定值512,跟len_text_feature相等的, 也可以写死在类成员变量里
image_features_input = new float[len_image_feature];
float norm = 0.0f;
for (int i = 0; i < len_image_feature; i++)
{
norm += ptr_feat[i] * ptr_feat[i];
}
norm = (float)Math.Sqrt(norm);
for (int i = 0; i < len_image_feature; i++)
{
image_features_input[i] = ptr_feat[i] / norm;
}
}

unsafe void generate_text_feature(List<string> texts)
{
List<List<int>> text_token = new List<List<int>>(texts.Count);
for (int i = 0; i < texts.Count; i++)
{
text_token.Add(new List<int>());
}

for (int i = 0; i < texts.Count; i++)
{
tokenizer.encode_text(texts[i], text_token[i]);
}

if (text_token.Count * context_length > text_tokens_input.Length)
{
text_tokens_input = new int[text_token.Count * context_length];
}

foreach (int i in text_tokens_input) { text_tokens_input[i] = 0; }

for (int i = 0; i < text_token.Count; i++)
{
if (text_token[i].Count > context_length)
{
Console.WriteLine("text_features index " + i + " ,bigger than " + context_length + "\n");
continue;
}
for (int j = 0; j < text_token[i].Count; j++)
{
text_tokens_input[i * context_length + j] = text_token[i][j];
}

}

int[] text_token_shape = new int[] { 1, context_length };

text_features_input = new float[text_token.Count, len_text_feature];

long[] text_tokens_input_64 = new long[texts.Count * context_length];
for (int i = 0; i < text_tokens_input_64.Length; i++)
{
text_tokens_input_64[i] = text_tokens_input[i];
}

for (int i = 0; i < text_token.Count; i++)
{
input_tensor = new DenseTensor<long>(text_tokens_input_64, new[] { 1, 52 });
input_container.Clear();
input_container.Add(NamedOnnxValue.CreateFromTensor("text", 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<float>();

float[] text_feature_ptr = results_onnxvalue[0].AsTensor<float>().ToArray();

float norm = 0.0f;
for (int j = 0; j < len_text_feature; j++)
{
norm += text_feature_ptr[j] * text_feature_ptr[j];
}
norm = (float)Math.Sqrt(norm);
for (int j = 0; j < len_text_feature; j++)
{
text_features_input[i, j] = text_feature_ptr[j] / norm;
}

}
}

void softmax(float[] input)
{
int length = input.Length;
float[] exp_x = new float[length];
float maxVal = input.Max();
float sum = 0;
for (int i = 0; i < length; i++)
{
float expval = (float)Math.Exp(input[i] - maxVal);
exp_x[i] = expval;
sum += expval;
}
for (int i = 0; i < length; i++)
{
input[i] = exp_x[i] / sum;
}
}

int[] argsort_ascend(float[] array)
{
int array_len = array.Length;
int[] array_index = new int[array_len];
for (int i = 0; i < array_len; ++i)
{
array_index[i] = i;
}

var temp = array_index.ToList();

temp.Sort((pos1, pos2) =>
{

if (array[pos1] < array[pos2])
{
return -1;
}
else if (array[pos1] == array[pos2])
{
return 0;
}
else
{
return 0;
}

});

return temp.ToArray();
}

public List<Dictionary<string, float>> input_text_search_image(string text, float[] image_features, List<string> imglist)
{

int imgnum = imglist.Count;
List<string> texts = new List<string> { text };

generate_text_feature(texts);

float[] logits_per_image = new float[imgnum];

for (int i = 0; i < imgnum; i++)
{
float sum = 0;
for (int j = 0; j < len_text_feature; j++)
{
sum += image_features[i * len_text_feature + j] * text_features_input[0, j]; //图片特征向量跟文本特征向量做内积
}
logits_per_image[i] = 100 * sum;
}

softmax(logits_per_image);

int[] index = argsort_ascend(logits_per_image);

List<Dictionary<string, float>> top5imglist = new List<Dictionary<string, float>>(5);

for (int i = 0; i < 5; i++)
{
int ind = index[imgnum - 1 - i];
Dictionary<string, float> result = new Dictionary<string, float>();
result.Add(imglist[ind], logits_per_image[ind]);
top5imglist.Add(result);
}
return top5imglist;
}

public float[] generate_imagedir_features(string image_dir)
{

imglist = Common.listdir(image_dir);
imgnum = imglist.Count;
Console.WriteLine("遍历到" + imgnum + "张图片");

float[] imagedir_features = new float[0];

for (int i = 0; i < imgnum; i++)
{
string imgpath = imglist[i];

Mat srcimg = Cv2.ImRead(imgpath);

generate_image_feature(srcimg);

imagedir_features = imagedir_features.Concat(image_features_input).ToArray();

srcimg.Dispose();
}

return imagedir_features;

}

public class Clip
    {
        int inpWidth = 224;
        int inpHeight = 224;
        float[] mean = new float[] { 0.48145466f, 0.4578275f, 0.40821073f };
        float[] std = new float[] { 0.26862954f, 0.26130258f, 0.27577711f };

        int context_length = 52;
        int len_text_feature = 512;

        Net net;
        float[] image_features_input;

        SessionOptions options;
        InferenceSession onnx_session;
        Tensor<long> input_tensor;
        List<NamedOnnxValue> input_container;
        IDisposableReadOnlyCollection<DisposableNamedOnnxValue> result_infer;
        DisposableNamedOnnxValue[] results_onnxvalue;
        Tensor<float> result_tensors;

        TokenizerBase tokenizer;

        int[] text_tokens_input;
        float[,] text_features_input;

        public int imgnum = 0;
        public List<string> imglist = new List<string>();

        public Clip(string image_modelpath, string text_modelpath, string vocab_path)
        {
            net = CvDnn.ReadNetFromOnnx(image_modelpath);

            // 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(text_modelpath, options);//model_path 为onnx模型文件的路径
            // 创建输入容器
            input_container = new List<NamedOnnxValue>();

            load_tokenizer(vocab_path);

        }

        void load_tokenizer(string vocab_path)
        {

            tokenizer = new TokenizerClipChinese();
            tokenizer.load_tokenize(vocab_path);
            text_tokens_input = new int[1024 * context_length];
        }

        Mat normalize_(Mat src)
        {
            Cv2.CvtColor(src, src, ColorConversionCodes.BGR2RGB);

            Mat[] bgr = src.Split();
            for (int i = 0; i < bgr.Length; ++i)
            {
                bgr[i].ConvertTo(bgr[i], MatType.CV_32FC1, 1.0 / (255.0 * std[i]), (0.0 - mean[i]) / std[i]);
            }

            Cv2.Merge(bgr, src);

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

            return src;
        }

        unsafe void generate_image_feature(Mat srcimg)
        {
            Mat temp_image = new Mat();
            Cv2.Resize(srcimg, temp_image, new Size(inpWidth, inpHeight), 0, 0, InterpolationFlags.Cubic);
            Mat normalized_mat = normalize_(temp_image);
            Mat blob = CvDnn.BlobFromImage(normalized_mat);
            net.SetInput(blob);
            //模型推理，读取推理结果
            Mat[] outs = new Mat[1] { new Mat() };
            string[] outBlobNames = net.GetUnconnectedOutLayersNames().ToArray();
            net.Forward(outs, outBlobNames);
            float* ptr_feat = (float*)outs[0].Data;
            int len_image_feature = outs[0].Size(1);  //忽略第0维batchsize=1, len_image_feature是定值512,跟len_text_feature相等的, 也可以写死在类成员变量里
            image_features_input = new float[len_image_feature];
            float norm = 0.0f;
            for (int i = 0; i < len_image_feature; i++)
            {
                norm += ptr_feat[i] * ptr_feat[i];
            }
            norm = (float)Math.Sqrt(norm);
            for (int i = 0; i < len_image_feature; i++)
            {
                image_features_input[i] = ptr_feat[i] / norm;
            }
        }

        unsafe void generate_text_feature(List<string> texts)
        {
            List<List<int>> text_token = new List<List<int>>(texts.Count);
            for (int i = 0; i < texts.Count; i++)
            {
                text_token.Add(new List<int>());
            }

            for (int i = 0; i < texts.Count; i++)
            {
                tokenizer.encode_text(texts[i], text_token[i]);
            }

            if (text_token.Count * context_length > text_tokens_input.Length)
            {
                text_tokens_input = new int[text_token.Count * context_length];
            }

            foreach (int i in text_tokens_input) { text_tokens_input[i] = 0; }

            for (int i = 0; i < text_token.Count; i++)
            {
                if (text_token[i].Count > context_length)
                {
                    Console.WriteLine("text_features index " + i + " ,bigger than " + context_length + "\n");
                    continue;
                }
                for (int j = 0; j < text_token[i].Count; j++)
                {
                    text_tokens_input[i * context_length + j] = text_token[i][j];
                }

            }

            int[] text_token_shape = new int[] { 1, context_length };

            text_features_input = new float[text_token.Count, len_text_feature];

            long[] text_tokens_input_64 = new long[texts.Count * context_length];
            for (int i = 0; i < text_tokens_input_64.Length; i++)
            {
                text_tokens_input_64[i] = text_tokens_input[i];
            }

            for (int i = 0; i < text_token.Count; i++)
            {
                input_tensor = new DenseTensor<long>(text_tokens_input_64, new[] { 1, 52 });
                input_container.Clear();
                input_container.Add(NamedOnnxValue.CreateFromTensor("text", 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<float>();

                float[] text_feature_ptr = results_onnxvalue[0].AsTensor<float>().ToArray();

                float norm = 0.0f;
                for (int j = 0; j < len_text_feature; j++)
                {
                    norm += text_feature_ptr[j] * text_feature_ptr[j];
                }
                norm = (float)Math.Sqrt(norm);
                for (int j = 0; j < len_text_feature; j++)
                {
                    text_features_input[i, j] = text_feature_ptr[j] / norm;
                }

            }
        }

        void softmax(float[] input)
        {
            int length = input.Length;
            float[] exp_x = new float[length];
            float maxVal = input.Max();
            float sum = 0;
            for (int i = 0; i < length; i++)
            {
                float expval = (float)Math.Exp(input[i] - maxVal);
                exp_x[i] = expval;
                sum += expval;
            }
            for (int i = 0; i < length; i++)
            {
                input[i] = exp_x[i] / sum;
            }
        }

        int[] argsort_ascend(float[] array)
        {
            int array_len = array.Length;
            int[] array_index = new int[array_len];
            for (int i = 0; i < array_len; ++i)
            {
                array_index[i] = i;
            }

            var temp = array_index.ToList();

            temp.Sort((pos1, pos2) =>
             {

                 if (array[pos1] < array[pos2])
                 {
                     return -1;
                 }
                 else if (array[pos1] == array[pos2])
                 {
                     return 0;
                 }
                 else
                 {
                     return 0;
                 }

             });

            return temp.ToArray();
        }

        public List<Dictionary<string, float>> input_text_search_image(string text, float[] image_features, List<string> imglist)
        {

            int imgnum = imglist.Count;
            List<string> texts = new List<string> { text };

            generate_text_feature(texts);

            float[] logits_per_image = new float[imgnum];

            for (int i = 0; i < imgnum; i++)
            {
                float sum = 0;
                for (int j = 0; j < len_text_feature; j++)
                {
                    sum += image_features[i * len_text_feature + j] * text_features_input[0, j]; //图片特征向量跟文本特征向量做内积
                }
                logits_per_image[i] = 100 * sum;
            }

            softmax(logits_per_image);

            int[] index = argsort_ascend(logits_per_image);

            List<Dictionary<string, float>> top5imglist = new List<Dictionary<string, float>>(5);

            for (int i = 0; i < 5; i++)
            {
                int ind = index[imgnum - 1 - i];
                Dictionary<string, float> result = new Dictionary<string, float>();
                result.Add(imglist[ind], logits_per_image[ind]);
                top5imglist.Add(result);
            }
            return top5imglist;
        }

        public float[] generate_imagedir_features(string image_dir)
        {

            imglist = Common.listdir(image_dir);
            imgnum = imglist.Count;
            Console.WriteLine("遍历到" + imgnum + "张图片");

            float[] imagedir_features = new float[0];

            for (int i = 0; i < imgnum; i++)
            {
                string imgpath = imglist[i];

                Mat srcimg = Cv2.ImRead(imgpath);

                generate_image_feature(srcimg);

                imagedir_features = imagedir_features.Concat(image_features_input).ToArray();

                srcimg.Dispose();
            }

            return imagedir_features;

        }

    }