# Cartucho/mAP

mean Average Precision - This code evaluates the performance of your neural net for object recognition.

Repository: https://github.com/Cartucho/mAP
Canonical: https://ross.abutalabs.com/products/cartucho-map
Language: Python
License: Apache-2.0
License Family: permissive
Topics: machine-learning, pascal-voc, average-precision, ground-truth, object-detection, computer-vision, metrics, detection, neural-network, darkflow, yolo, darknet
Last push: 2024-08-15T13:09:32+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3100, "days_push": 748, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2966, forks 918 (observed 2026-08-28T04:07:32.547846+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: machine-learning, computer-vision, data-visualization, benchmarking
- domain: machine-learning, computer-vision, deep-learning
- platform: python, cross-platform, cli
- tags: mean-average-precision, pascal-voc, object-detection-metrics, iou, precision-recall, yolo, darknet, evaluation-metrics, detection-evaluation, ground-truth, algorithms

## Member repositories
- Cartucho/mAP (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:32.547846+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:31:53.535204+00:00, confidence not recorded.
  - readme: https://github.com/Cartucho/mAP (fetched 2026-08-28T04:07:32.547846+00:00, sha deac9d89baf0)
- Data as of 2026-08-30T08:39:29.467469+00:00.