# chuanqi305/MobileNet-SSD

Caffe implementation of Google MobileNet SSD detection network, with pretrained weights on VOC0712 and mAP=0.727.

Repository: https://github.com/chuanqi305/MobileNet-SSD
Canonical: https://ross.abutalabs.com/products/mobilenet-ssd
Language: Python
License: MIT
License Family: permissive
Topics: ssd, mobilenet-ssd, caffe, mobilenet, detection
Last push: 2025-07-13T06:43:16+00:00

## Health v2 (maintenance only)
Score: 46/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 31, release rhythm 35, longevity 100
- inputs: {"age_days": 3373, "days_push": 416, "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 2127, forks 1167 (observed 2026-08-28T04:06:16.970249+00:00)

## What it is
A Caffe implementation of the MobileNet-SSD object detection network with pretrained weights on the VOC0712 dataset achieving mAP of 0.727. It includes scripts for running detection demos, creating LMDB datasets, and fine-tuning the model on custom datasets.

## Use cases
- run object detection with a fast lightweight model
- fine-tune SSD object detection on my own dataset
- get pretrained MobileNet-SSD weights for Caffe
- convert my labeled images to LMDB for SSD training
- deploy real-time object detection on resource-constrained devices
- reproduce MobileNet-SSD training results in Caffe

## When to choose
- you need a lightweight, fast object detection model in the Caffe framework
- you want pretrained VOC0712 weights to fine-tune on a custom dataset
- you are targeting embedded or mobile deployment where speed matters

## When to avoid
- you prefer PyTorch or TensorFlow instead of Caffe
- you need state-of-the-art detection accuracy rather than speed
- you need a maintained project with active updates and modern tooling

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, computer-vision, deep-learning
- domain: computer-vision, machine-learning, deep-learning
- platform: python, cross-platform
- tags: object-detection, ssd, mobilenet, caffe, pretrained-weights, voc0712, model-training, linux

## Member repositories
- chuanqi305/MobileNet-SSD (main) score 46

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:16.970249+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 2026-08-30T02:52:28.796758+00:00, confidence not recorded.
  - readme: https://github.com/chuanqi305/MobileNet-SSD (fetched 2026-08-28T04:06:16.970249+00:00, sha 22c12608c271)
- Data as of 2026-08-30T08:39:29.467469+00:00.