Cartucho/mAP

Health v2 · maintenance only

Adoption not part of the score

2966 stars · 918 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Python library and script that computes mean Average Precision (mAP) for object detection models, adapted from the official PASCAL VOC 2012 Matlab evaluation code. It matches detection results against ground-truth annotations using IoU >= 0.5, builds precision/recall curves, and reports per-class AP plus the overall mAP.

Use cases

• evaluate object detection model accuracy with mAP
• compute pascal voc mean average precision in python
• compare yolo detections against ground truth annotations
• generate precision recall curves for detection results
• measure IoU-based detection performance per class
• benchmark neural net object recognition performance

When to choose

• you need the standard PASCAL VOC mAP metric for object detection evaluation
• you have detection results and ground-truth files and want per-class AP plus overall mAP
• you want a lightweight Python evaluation script compatible with YOLO/Darknet-style outputs

When to avoid

• you need COCO-style metrics such as AP@[.5:.95] or AR
• you want a training framework or model inference library rather than an evaluation tool
• you need real-time evaluation integrated into a training loop with GPU acceleration

Facets

library · maturity maintenance

machine-learning computer-vision data-visualization benchmarking machine-learning computer-vision deep-learning python cross-platform cli mean-average-precision pascal-voc object-detection-metrics iou precision-recall yolo darknet evaluation-metrics detection-evaluation ground-truth algorithms

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Cartucho/mAP")