Object Detection Metrics

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1166 stars · 230 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A Python toolkit implementing the most popular metrics (AP, mAP, precision-recall curves) used to evaluate object detection algorithms, with a newer version adding COCO metrics, multiple file formats, and a UI. It aims to provide consistent, trustworthy benchmarking across datasets and detection implementations.

Use cases

• calculate mAP for my object detection model
• compare object detection results against Pascal VOC metrics
• plot precision-recall curves for bounding box predictions
• evaluate detection accuracy on a custom dataset
• compute COCO metrics for my detector
• benchmark different object detection implementations fairly

When to choose

• you need standard object detection metrics like AP/mAP without implementing them yourself
• you want consistent evaluation across different datasets or file formats
• you need a GUI to guide the evaluation process
• you are benchmarking detection models for research

When to avoid

• you need metrics for segmentation or classification rather than bounding-box detection
• you want metrics integrated directly into a training framework like MMDetection or Detectron2
• you need real-time streaming evaluation in production

Facets

library · maturity stable

machine-learning computer-vision data-science benchmarking computer-vision machine-learning deep-learning data-science python cross-platform object-detection average-precision mean-average-precision precision-recall bounding-boxes pascal-voc coco-metrics evaluation-metrics

Member repositories

For agents

markdown · JSON · MCP: product_card(name="rafaelpadilla/review_object_detection_metrics")