/Tensorflow-2-SSD

Implementation of SSD pipeline in Tensorflow 2.0

Primary LanguagePythonMIT LicenseMIT

Single Shot MultiBox Detector Implementation in Tensorflow 2.0

This repo implements SSD (Single Shot MultiBox Detector). The implementation is a rewrite of pytorch-ssd so all credit for implementation details go to them. The design goal is modularity and extensibility.

Currently, it has MobileNetV1, MobileNetV2, and VGG based SSD/SSD-Lite implementations.

Added features include TFRecord support as well as a data generator that augments a directory of masked images and pastes them on top of provided background images.