Skip to content

Latest commit

 

History

History

segmentation

ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network

This repository contains the source code that we used for semantic segmentation in our paper of our paper, ESPNetv2.

Note: New segmentation models for the PASCAL VOC and the Cityscapes are coming soon. Our new models achieves mIOU of 68.0 and 66.15 on the PASCAL VOC and the Cityscapes test sets, respectively.

IMPORTANT NOTE We released a new repository EdgeNets that contains our work on efficient network design. See EdgeNets for performance comparison and pretrained models.

THIS REPO IS OBSOLETE