IntptrMax.YoloSharp 1.1.4

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.

<details> <summary>Prediction Checkpoints</summary>

</details>

<details> <summary>Segmention Checkpoints</summary>

</details>

How to use

You can download the code or add it from nuget.

dotnet add package IntptrMax.YoloSharp

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);

Use yolov5n pre-trained model to detect.

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);

Use yolov8n-seg pre-trained model to detect.