# balancap/SSD-Tensorflow

Single Shot MultiBox Detector in TensorFlow

Repository: https://github.com/balancap/SSD-Tensorflow
Canonical: https://ross.abutalabs.com/products/ssd-tensorflow
Language: Jupyter Notebook
License Family: other
Topics: tensorflow, ssd, deep-learning, yolo, object-detection
Last push: 2021-08-12T11:13:20+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": 3514, "days_push": 1847, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4101, forks 1832 (observed 2026-08-28T04:08:35.543028+00:00)

## What it is
A TensorFlow re-implementation of the Single Shot MultiBox Detector (SSD) for object detection, including VGG-based SSD-300 and SSD-512 networks with converted pretrained checkpoints. It provides dataset conversion to TF-Records, network definitions, and pre-processing/augmentation routines, with a Jupyter notebook demo.

## Use cases
- run object detection on images with a pretrained SSD model
- train an SSD detector on Pascal VOC
- convert VOC datasets to TF-Records for training
- detect objects in a Jupyter notebook demo
- fine-tune SSD variants on custom datasets

## When to choose
- you need a classic single-shot object detector in TensorFlow 1.x
- you want pretrained SSD-300/512 VGG checkpoints converted from Caffe
- you are reproducing SSD paper results on Pascal VOC

## When to avoid
- you need TensorFlow 2.x or modern APIs
- you want the latest detectors like YOLOv8 or DETR
- you need active maintenance or official support

## 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, cross-platform
- tags: object-detection, ssd, tensorflow, vgg, pascal-voc, pretrained-models, jupyter-notebook, gpu

## Member repositories
- balancap/SSD-Tensorflow (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:35.543028+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 2026-08-29T18:23:16.530527+00:00, confidence not recorded.
  - readme: https://github.com/balancap/SSD-Tensorflow (fetched 2026-08-28T04:08:35.543028+00:00, sha 5c2fd125f20a)
- Data as of 2026-08-30T08:39:29.467469+00:00.