Mapper

app.infrastructure.detection.model.torch.mapper

View source code

Mapper for converting TorchVision model output to DetectionPayload.

See Also

• DetectionResult — normalized detection record produced by the mapper
• TorchDetectionModel — runs the mapped model output

Layer: Infrastructure. Context: Implements concrete processing and I/O behind application-facing contracts.

TorchDetectionMapper

Maps raw TorchVision detection results to DetectionPayload format.

Layer: Infrastructure. Context: Implements concrete processing or I/O behind application-facing contracts.

map(raw_results: dict, labels: list[str], chosen_labels: list[str] | None = None) -> list[DetectionResult] staticmethod

Map TorchVision raw inference output to DetectionResult list.

PARAMETER	DESCRIPTION
raw_results	Raw model output (dict with "boxes", "scores", "labels" keys). TYPE: dict
labels	Label names extracted from model weights metadata. TYPE: list[str]
chosen_labels	Optional filter to include only these labels. TYPE: list[str] | None DEFAULT: None

RETURNS	DESCRIPTION
list[DetectionResult]	List of DetectionResult instances filtered by confidence and label.