YoloSharp

YoloSharp allows you to define a training and inference pipeline using a Config object and a YoloTask instance.

1. Configure: Define your DeviceType (e.g., CUDA), YoloType (e.g., Yolov8), TaskType (e.g., Obb, Detection, Segmentation, Pose), and dataset paths in a Config object.
2. Initialize Task: Create a YoloTask passing the configuration.
3. Load Model (Optional): Use yoloTask.LoadModel() to load pretrained weights.
4. Train: Call yoloTask.Train() to start the training process.
5. Predict: Use yoloTask.ImagePredict(Mat image) to perform inference on an OpenCV Mat object.

string preTrainedModelPath = @"..\..\..\Assets\PreTrainedModels\yolov8n-obb.bin";
string predictImagePath = @"..\..\..\Assets\TestImage\trucks.jpg";
string dataRootPath = @"..\..\..\Assets\datasets\dotav1";

string trainDataPath = "train.txt";
string valDataPath = "val.txt";

Mat predictImage = Cv2.ImRead(predictImagePath);

// Create a Yolo config
Config config = new Config
{
    DeviceType = DeviceType.CUDA,
    ScalarType = ScalarType.BFloat16,
    RootPath = dataRootPath,
    TrainDataPath = trainDataPath,
    ValDataPath = valDataPath,
    YoloType = YoloType.Yolov8,
    YoloSize = YoloSize.n,
    TaskType = TaskType.Obb,
    ImageProcessType = ImageProcessType.Mosiac,
    ImageSize = 640,
    BatchSize = 16,
    NumberClass = 15,
    PredictThreshold = 0.3f,
    IouThreshold = 0.7f,
    Workers = 4,
    Epochs = 100,
    LearningRate = 1e-4f,
    Patience = 50,
    KeyPoint_Num = 21,
    KeyPoint_Dim = 3,
};

// Create a yolo task.
YoloTask yoloTask = new YoloTask(config);

// Load pre-trained model.
yoloTask.LoadModel(preTrainedModelPath, skipNcNotEqualLayers: true);

// Train model
yoloTask.Train();

// Predict image
List<YoloResult> predictResult = yoloTask.ImagePredict(predictImage);