# qfgaohao/pytorch-ssd

MobileNetV1, MobileNetV2, VGG based SSD/SSD-lite implementation in Pytorch 1.0 / Pytorch 0.4. Out-of-box support for retraining on Open Images dataset. ONNX and Caffe2 support. Experiment Ideas like CoordConv.

Repository: https://github.com/qfgaohao/pytorch-ssd
Canonical: https://ross.abutalabs.com/products/pytorch-ssd
Homepage: https://medium.com/@smallfishbigsea/understand-ssd-and-implement-your-own-caa3232cd6ad
Language: Python
License: MIT
License Family: permissive
Topics: ssd, pytorch, open-images, object-detection
Last push: 2023-03-11T09:50:27+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": 3029, "days_push": 1271, "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 1429, forks 540 (observed 2026-08-28T04:04:42.193680+00:00)

## What it is
A PyTorch implementation of the SSD (Single Shot MultiBox Detector) object detection algorithm with MobileNetV1, MobileNetV2, and VGG backbones. It includes pretrained models, out-of-box retraining on the Open Images dataset, and ONNX/Caffe2 export support.

## Use cases
- train a custom object detection model in pytorch
- run real-time object detection from a webcam
- fine-tune SSD on the Open Images dataset
- export an object detection model to ONNX or Caffe2
- deploy a lightweight mobile-friendly object detector
- compare MobileNetV1 vs MobileNetV2 SSD performance

## When to choose
- you need a modular, hackable SSD implementation in PyTorch
- you want lightweight real-time detection with MobileNet backbones
- you want to retrain detection on Open Images with minimal setup

## When to avoid
- you need YOLO or transformer-based detectors
- you want a maintained production training framework like MMDetection or Detectron2
- you need the latest PyTorch version compatibility

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: python, cross-platform
- tags: ssd, object-detection, mobilenet, pytorch, onnx, caffe2, open-images, transfer-learning, gpu

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

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:42.193680+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 2026-08-30T04:37:16.769494+00:00, confidence not recorded.
  - readme: https://github.com/qfgaohao/pytorch-ssd (fetched 2026-08-28T04:04:42.193680+00:00, sha 3acfeb3981d6)
  - homepage: https://medium.com/@smallfishbigsea/understand-ssd-and-implement-your-own-caa3232cd6ad (fetched 2026-08-29T11:48:51.826043+00:00, sha b566d2dadf77)
- Data as of 2026-08-30T08:39:29.467469+00:00.