IDetectionTrainingModel<T>
Interfaces · AiDotNet.Interfaces
A model that implements its detection task’s assignment and classification/box loss.
Known implementations: CascadeRCNN<T>, DETR<T>, DINO<T>, FasterRCNN<T>, RTDETR<T>, YOLOv10<T>, YOLOv11<T>, YOLOv8<T>, YOLOv9<T>
How It Works
This capability is separate from raw-output tensor regression. Implementing it promises a real family-specific detection objective, not a generic MSE fallback or an inferred tensor format.
Methods
| Method | Summary |
|---|---|
void TrainDetections(Tensor<T> input, DetectionTrainingBatch<T> targets) |
Runs one semantic detection training step. |