MXNet-SSD

MXNet port of SSD: Single Shot MultiBox Object Detector

Posted by Joshua Z. Zhang on October 1, 2016

MXNet port of SSD: Single Shot MultiBox Object Detector. SSD is an unified framework for object detection with a single network.

Github repository

mxnet-ssd

Disclaimer

This is a re-implementation of original SSD which is based on caffe. The official repository is available here. The arXiv paper is available here.

This example is intended for reproducing the nice detector while fully utilize the remarkable traits of MXNet.

  • The model is fully compatible with caffe version.
  • Model converter from caffe is available now!
  • The result is almost identical to the original version. However, due to different implementation details, the results might differ slightly.

Demo results

demo1 demo2 demo3

mAP

Model Training data Test data mAP Note
VGG16_reduced 300x300 VOC07+12 trainval VOC07 test 77.8 fast
VGG16_reduced 512x512 VOC07+12 trainval VOC07 test 79.9 slow
Inception-v3 512x512 VOC07+12 trainval VOC07 test 78.9 fastest
Resnet-50 512x512 VOC07+12 trainval VOC07 test 78.9 fast

Speed

Model GPU CUDNN Batch-size FPS*
VGG16_reduced 300x300 TITAN X(Maxwell) v5.1 16 95
VGG16_reduced 300x300 TITAN X(Maxwell) v5.1 8 95
VGG16_reduced 300x300 TITAN X(Maxwell) v5.1 1 64
VGG16_reduced 300x300 TITAN X(Maxwell) N/A 8 36
VGG16_reduced 300x300 TITAN X(Maxwell) N/A 1 28