balancap/SSD-Tensorflow

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

4101 stars · 1832 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing computer-vision deep-learning machine-learning image-processing python cross-platform object-detection ssd tensorflow vgg pascal-voc pretrained-models jupyter-notebook gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="balancap/SSD-Tensorflow")