ycjcy / VGG-depthwise-SSD

Adopting the VGG to improve the feature extraction, combined with depthwise structure makes the improved detection network not only has stronger than MobileNet feature extraction ability, greatly reduces the model at the same time, makes the detection speed compared with the SSD is faster.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

This repository is not active

About

Adopting the VGG to improve the feature extraction, combined with depthwise structure makes the improved detection network not only has stronger than MobileNet feature extraction ability, greatly reduces the model at the same time, makes the detection speed compared with the SSD is faster.


Languages

Language:Cuda 46.5%Language:C++ 27.2%Language:Python 24.9%Language:Shell 1.5%