IntptrMax.YoloSharp 1.1.1

YoloSharp

Train Yolo model in C# with TorchSharp. </br> With the help of this project you won't have to transform .pt model to onnx, and can train your own model in C#.

Feature

• Written in C# only.
• Train and predict your own model.
• Support Yolov5, Yolov5u, Yolov8 and Yolov11 now.
• Support Predict and Segment now.
• Support n/s/m/l/x size.
• Support LetterBox and Mosaic4 method for preprocessing images.
• Support NMS with GPU.
• Support Load PreTrained models from ultralytics/yolov5/yolov8 and yolo11 (converted).

Models

You can download yolov5/yolov8 pre-trained models here.

How to use

You can download the code or add it from nuget.

dotnet add package IntptrMax.YoloSharp --version 1.1.0

In your code you can use it as below.

Predict

You can use it with the code below:

Bitmap inputBitmap = new Bitmap(predictImagePath);

// Create predictor
Predictor predictor = new Predictor(sortCount, yoloType: yoloType, deviceType: deviceType, yoloSize: yoloSize, dtype: dtype);

// Train model
predictor.LoadModel(preTraindModelPath);
predictor.Train(trainDataPath, valDataPath, outputPath: outputPath, batchSize: batchSize, epochs: epochs);

// Predict image
predictor.LoadModel(Path.Combine(outputPath, "best.bin"));

var results = predictor.ImagePredict(inputBitmap, predictThreshold, iouThreshold);

Segment

You can use it with the code below:

// Create segmenter
Segmenter segmenter = new Segmenter(sortCount, yoloType: yoloType, deviceType: deviceType, yoloSize: yoloSize, dtype: dtype);

// Train model
segmenter.LoadModel(preTraindModelPath);
segmenter.Train(trainDataPath, valDataPath, outputPath: outputPath, batchSize: batchSize, epochs: epochs, useMosaic: false);

// Segment image
segmenter.LoadModel("output/best.bin");
Bitmap testBitmap = new Bitmap(predictImagePath);
var (predictResult, bitmap) = segmenter.ImagePredict(testBitmap, predictThreshold, iouThreshold);