# VDIGPKU/M2Det

M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network

Repository: https://github.com/VDIGPKU/M2Det
Canonical: https://ross.abutalabs.com/products/m2det
Language: Python
License: MIT
License Family: permissive
Last push: 2019-11-14T10:21:38+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2915, "days_push": 2484, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1438, forks 313 (observed 2026-08-28T04:04:43.930552+00:00)

## What it is
M2Det is a PyTorch implementation of a single-shot object detector based on a Multi-Level Feature Pyramid Network (MLFPN), published at AAAI 2019. It provides training, evaluation, and demo code for detecting objects while handling both scale and appearance-complexity variation.

## Use cases
- train a custom object detection model
- run single-shot object detection on images
- research multi-level feature pyramid networks
- benchmark object detectors on COCO-style datasets
- detect objects of varying appearance complexity
- reproduce AAAI 2019 paper results

## When to choose
- you need a research-grade single-shot detector with multi-level feature fusion
- you want to experiment with or extend MLFPN architectures
- you're reproducing or building on the M2Det paper

## When to avoid
- you need a maintained production detector with recent updates
- you want the latest state-of-the-art detection accuracy
- you need Windows or non-GPU support out of the box

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: object-detection, pytorch, single-shot-detector, feature-pyramid-network, research-code, aaai-2019, linux, gpu

## Member repositories
- VDIGPKU/M2Det (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:43.930552+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 2026-08-30T04:36:38.947939+00:00, confidence not recorded.
  - readme: https://github.com/VDIGPKU/M2Det (fetched 2026-08-28T04:04:43.930552+00:00, sha 005b4e291a1f)
- Data as of 2026-08-30T08:39:29.467469+00:00.