# GOATmessi8/ASFF

yolov3 with mobilenet v2 and ASFF

Repository: https://github.com/GOATmessi8/ASFF
Canonical: https://ross.abutalabs.com/products/asff
Language: Python
License: GPL-3.0
License Family: copyleft
Last push: 2021-07-24T02:37:08+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2477, "days_push": 1867, "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 1085, forks 214 (observed 2026-08-28T04:03:31.652085+00:00)

## What it is
A PyTorch implementation of YOLOv3 with the Adaptively Spatial Feature Fusion (ASFF) module and optional MobileNetV2 backbone for single-shot object detection. It reproduces the paper 'Learning Spatial Fusion for Single-Shot Object Detection' with training, evaluation, and demo scripts on COCO.

## Use cases
- train a YOLOv3 object detector with ASFF feature fusion
- run object detection with a lightweight MobileNetV2 backbone
- reproduce ASFF paper results on COCO
- benchmark single-shot object detection models
- run object detection inference on images with a demo script

## When to choose
- you need a research-grade YOLOv3+ASFF implementation in PyTorch
- you want a lightweight MobileNetV2-based detector for edge or mobile use
- you want to reproduce or extend the ASFF paper

## When to avoid
- you need a modern, actively maintained detector like YOLOX or YOLOv5+
- you need FP16 training with MobileNetV2, which is unsupported
- you need production support, broad documentation, or recent PyTorch compatibility

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning, image-processing
- platform: python
- tags: object-detection, yolov3, asff, mobilenetv2, pytorch, single-shot-detector, feature-fusion, research-code, linux, gpu

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

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:31.652085+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 2026-08-30T06:49:40.829753+00:00, confidence not recorded.
  - readme: https://github.com/GOATmessi8/ASFF (fetched 2026-08-28T04:03:31.652085+00:00, sha 2e6f7c5f2bd9)
- Data as of 2026-08-30T08:39:29.467469+00:00.