当前位置：首页 > news >正文

(三)C#使用yolo

news 2025/7/9 7:04:05

github地址

https://github.com/NickSwardh/YoloDotNet

1.安装yoloDotNet

下面是根据官网例子，写的测试代码

        private async void btnVisionTest_Click(object sender, RoutedEventArgs e){string sourceImg =  await VisionHelper.GetInstance().GetLocalImage();string onnxFile = @"D:\easyboot\Onnx\best.onnx";// Instantiate a new Yolo objectusing var yolo = new Yolo(new YoloOptions{OnnxModel = onnxFile,          // Your Yolo model in onnx formatModelType = ModelType.ObjectDetection,      // Set your model typeCuda = false,                               // Use CPU or CUDA for GPU accelerated inference. Default = trueGpuId = 0,                                  // Select Gpu by id. Default = 0PrimeGpu = false,                           // Pre-allocate GPU before first inference. Default = false// ImageResize = ImageResize.Proportional   // Proportional = Default, Stretched = Squares the image// SamplingOptions =  new SKSamplingOptions(SKFilterMode.Linear, SKMipmapMode.None) // View benchmark-test examples: https://github.com/NickSwardh/YoloDotNet/blob/development/test/YoloDotNet.Benchmarks/ImageExtensionTests/ResizeImageTests.cs});// Load imageusing var image = SKImage.FromEncodedData(sourceImg);// Run inference and get the resultsvar results = yolo.RunObjectDetection(image, confidence: 0.25, iou: 0.7);//results.ForEach(a => a.BoundingBox){//    Console.WriteLine(ar//}// Tip:// Use the extension method FilterLabels([]) on any result if you only want specific labels.// Example: Select only the labels you're interested in and exclude the rest.// var results = yolo.RunObjectDetection(image).FilterLabels(["person", "car", "cat"]);// Draw resultsusing var resultImage = image.Draw(results);// Save to fileresultImage.Save(@"D:\new_image.jpg", SKEncodedImageFormat.Jpeg, 80);

D盘生成的图片