# GOATmessi8/RFBNet

Receptive Field Block Net for Accurate and Fast Object Detection, ECCV 2018

Repository: https://github.com/GOATmessi8/RFBNet
Canonical: https://ross.abutalabs.com/products/rfbnet
Language: Python
License: MIT
License Family: permissive
Topics: detection, pytorch, mobilenet, rfbnet
Last push: 2021-11-02T18:19:57+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3203, "days_push": 1765, "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 1419, forks 347 (observed 2026-08-28T04:04:40.467581+00:00)

## What it is
PyTorch implementation of RFBNet, a Receptive Field Block Net object detector presented at ECCV 2018. It enhances SSD-style detectors with an RFB module for fast, accurate object detection on VOC and COCO, including lightweight MobileNet variants.

## Use cases
- train an object detection model in pytorch
- run fast real-time object detection on images
- reproduce ECCV 2018 RFBNet results on COCO and VOC
- build a lightweight mobile-friendly detector with mobilenet backbone
- compare SSD and RFBNet detection accuracy and speed
- fine-tune a pretrained object detector on custom datasets

## When to choose
- you need a fast SSD-style detector with strong accuracy benchmarks
- you want a research reference implementation of the RFB paper
- you need a lightweight mobilenet-based detector with few parameters

## When to avoid
- you need a modern, actively maintained detection framework
- you want built-in ONNX/TensorRT deployment support
- you need the latest state-of-the-art detectors like YOLOX or transformers

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, computer-vision, deep-learning
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: object-detection, pytorch, ssd, mobilenet, eccv-2018, research-code, gpu, linux

## Member repositories
- GOATmessi8/RFBNet (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:40.467581+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 2026-08-30T04:37:51.078210+00:00, confidence not recorded.
  - readme: https://github.com/GOATmessi8/RFBNet (fetched 2026-08-28T04:04:40.467581+00:00, sha 45427fd7404a)
- Data as of 2026-08-30T08:39:29.467469+00:00.