YOLOV5 使用 ML.NET ONNX 在C#部署

• 前言
• 一、生成dll调用库
• • 1.安装.NET core SDK
  • 2.Nuget安装 ML ONNX Running Time
  • 3.生成Dll库文件
• 二、winform 程序调用dll
• • 1.新建winform 程序
  • 2.安装Nuget 包
  • 3.下载官网的onnx模型文件
  • 4.添加引用
  • 5. 程序修改
  • • 5.1 模型初始化
    • 5.2 模型推断
• 三、实际的效果

.NET Core 3.1 SDK (v3.1.416) - Windows x64

模型文件下载地址

scorer = new YoloScorer("Assets/Weights/yolov5s.onnx");

        private void button1_Click(object sender, EventArgs e)
        {

           
            var image = Image.FromFile(@"Assets/test3.jpg");
            DateTime T_start = DateTime.Now;
            List predictions = scorer.Predict(image);

            var graphics = Graphics.FromImage(image);

            foreach (var prediction in predictions) // iterate predictions to draw results
            {
                double score = Math.Round(prediction.Score, 2);

                graphics.DrawRectangles(new Pen(prediction.Label.Color, 1),
                    new[] { prediction.Rectangle });

                var (x, y) = (prediction.Rectangle.X - 3, prediction.Rectangle.Y - 23);

                graphics.DrawString($"{prediction.Label.Name} ({score})",
                    new Font("Arial", 16, GraphicsUnit.Pixel), new SolidBrush(prediction.Label.Color),
                    new PointF(x, y));
            }

            image.Save("Assets/result.jpg");
            this.pictureBox1.Image = image;
            DateTime T_end = DateTime.Now;
            TimeSpan T_esp = T_end - T_start;
            this.label1.Text = T_esp.TotalMilliseconds.ToString();

        }