class documentation

Metadata for an object detection head.

Instance Variable anchors Optional predefined boxes of different sizes and aspect ratios. The innermost values describe box sizes, the middle values group anchors per output, and the outer values are ordered from smallest to largest output.
Instance Variable classes Names of classes detected by the model.
Instance Variable conf_threshold Confidence threshold above which a detection is considered valid.
Instance Variable iou_threshold Non-maximum suppression IoU threshold for filtering overlapping boxes.
Instance Variable max_det Maximum detections per image.
Instance Variable n_classes Number of classes detected by the model.

Inherited from HeadMetadata:

Class Variable model_config Undocumented
Instance Variable postprocessor_path Optional path to the postprocessor.
anchors: list[list[list[float]]] | None =

Optional predefined boxes of different sizes and aspect ratios. The innermost values describe box sizes, the middle values group anchors per output, and the outer values are ordered from smallest to largest output.

classes: list[str] =

Names of classes detected by the model.

conf_threshold: float =

Confidence threshold above which a detection is considered valid.

iou_threshold: float =

Non-maximum suppression IoU threshold for filtering overlapping boxes.

max_det: int =

Maximum detections per image.

n_classes: int =

Number of classes detected by the model.