# amdegroot/ssd.pytorch

A PyTorch Implementation of Single Shot MultiBox Detector

Repository: https://github.com/amdegroot/ssd.pytorch
Canonical: https://ross.abutalabs.com/products/ssdpytorch
Language: Python
License: MIT
License Family: permissive
Topics: pytorch, deep-learning, ssd, object-detection, computer-vision, machine-learning, image-recognition, webcam
Last push: 2021-12-29T03:19:26+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": 3494, "days_push": 1708, "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 5221, forks 1723 (observed 2026-08-28T04:09:13.223348+00:00)

## What it is
A PyTorch implementation of the Single Shot MultiBox Detector (SSD) object detection model from the 2016 paper by Wei Liu et al. It includes training and evaluation scripts for the VOC and COCO datasets, pretrained VGG-16 base weights, and live loss visualization via Visdom.

## Use cases
- train an SSD object detection model in PyTorch
- detect objects in images with a single-shot detector
- evaluate object detection on Pascal VOC or COCO
- reproduce SSD paper results in PyTorch
- fine-tune SSD on a custom dataset
- run real-time object detection from a webcam

## When to choose
- you want a faithful PyTorch port of the original SSD architecture
- you need to train or evaluate SSD on VOC or COCO
- you're studying or teaching single-shot object detection implementations

## When to avoid
- you need state-of-the-art detection accuracy (newer models like YOLO or DETR outperform SSD)
- you need actively maintained code with recent PyTorch version support
- you need production-ready detection pipelines rather than a research reference implementation

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning, image-processing
- platform: python, cross-platform
- tags: object-detection, ssd, pytorch, vgg16, pascal-voc, coco, single-shot-detector, gpu

## Member repositories
- amdegroot/ssd.pytorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:13.223348+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 2026-08-29T18:00:08.348818+00:00, confidence not recorded.
  - readme: https://github.com/amdegroot/ssd.pytorch (fetched 2026-08-28T04:09:13.223348+00:00, sha 738acd7c2634)
- Data as of 2026-08-30T08:39:29.467469+00:00.