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

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

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

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

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

 
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;
        }
 
        服务器托管网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> top5imglist = mynet.input_text_search_image(input_text, imagedir_features, mynet.imglist);
            sb.AppendLine("top5:");
            fore服务器托管网ach (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)
        {
 
        }
    }
}

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 input_tensor;
        List input_container;
        IDisposableReadOnlyCollection result_infer;
        DisposableNamedOnnxValue[] results_onnxvalue;
        Tensor result_tensors;
 
        TokenizerBase tokenizer;
 
        int[] text_tokens_input;
        float[,] text_features_input;
 
        public int imgnum = 0;
        public List imglist = new List();
 
        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();
 
            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  texts)
        {
            List> text_token = new List>(texts.Count);
            for (int i = 0; i ());
            }
 
            for (int i = 0; i  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  context_length)
                {
                    Console.WriteLine("text_features index " + i + " ,bigger than " + context_length + "n");
                    continue;
                }
                for (int j = 0; j (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[] text_feature_ptr = results_onnxvalue[0].AsTensor().ToArray();
 
                float norm = 0.0f;
                for (int j = 0; j 
             {
 
                 if (array[pos1] > input_text_search_image(string text, float[] image_features, List imglist)
        {
 
            int imgnum = imglist.Count;
            List texts = new List { text };
 
            generate_text_feature(texts);
 
            float[] logits_per_image = new float[imgnum];
 
            for (int i = 0; i > top5imglist = new List>(5);
 
            for (int i = 0; i  result = new Dictionary();
                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