DrSleep / GDN

Code for "Global Deconvolutional Networks" paper (BMVC 2016)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Global Deconvolutional Networks for Semantic Segmentation Code

Installation

You need to install Caffe with the support of Python layer enabled. The Caffe version provided here can differ significantly from the most recent one. You will also need to download the corresponding caffemodel file: link, and put it into the model/ folder.

A running example can be seen in the gdn_caffe notebook file.

Description

Online segmentation demo is available at http://saildemo.unist.ac.kr/semantic_segmentation/

For details on the underlying model please refer to the following paper:

@inproceedings{BMVCNekrasovJC16,
  author    = {Vladimir Nekrasov and
               Janghoon Ju and
               Jaesik Choi},
  title     = {Global Deconvolutional Networks for Semantic Segmentation},
  booktitle = {Proceedings of the British Machine Vision Conference 2016, {BMVC}
               2016, York, UK, September 19-22, 2016},
  year      = {2016}
}

About

Code for "Global Deconvolutional Networks" paper (BMVC 2016)


Languages

Language:Jupyter Notebook 60.4%Language:C++ 30.9%Language:Python 3.8%Language:Cuda 2.1%Language:CMake 1.1%Language:Protocol Buffer 0.6%Language:MATLAB 0.3%Language:Makefile 0.3%Language:Shell 0.3%Language:CSS 0.1%Language:HTML 0.1%Language:M 0.0%