rykov8/ssd_keras

Health v2 · maintenance only

Flags: no_releases archived

Adoption not part of the score

1083 stars · 540 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Keras port of the SSD (Single Shot MultiBox Detector) object detection model, including pretrained weights ported from the original Caffe implementation. It provides notebooks for forward-pass inference and training on 300x300 models, plus utilities for testing on video or camera input.

Use cases

• run object detection on images with a pretrained SSD model in Keras
• train an SSD300 detector on a custom dataset
• detect objects in live video or webcam streams
• port Caffe SSD weights to a TensorFlow/Keras workflow
• study or reproduce the SSD paper implementation

When to choose

• you need a classic single-shot object detector in Keras/TensorFlow
• you want pretrained SSD300 weights without training from scratch
• you are reproducing the SSD paper or learning object detection internals

When to avoid

• you need modern detectors like YOLO or DETR with active development
• you require recent TensorFlow/Keras 2.x+ compatibility out of the box
• you need production-supported object detection with regular updates

Facets

library · maturity maintenance

machine-learning deep-learning computer-vision computer-vision deep-learning machine-learning python object-detection ssd keras tensorflow pretrained-weights

Member repositories

For agents

markdown · JSON · MCP: product_card(name="rykov8/ssd_keras")