Skip to content

Eromera/erfnet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ERFNet

This code is a toolbox that uses Torch library for training and evaluating the ERFNet architecture for semantic segmentation.

NEW!! New PyTorch version is available HERE

Example segmentation

Publications

If you use this software in your research, please cite our publications:

"Efficient ConvNet for Real-time Semantic Segmentation", E. Romera, J. M. Alvarez, L. M. Bergasa and R. Arroyo, IEEE Intelligent Vehicles Symposium (IV), pp. 1789-1794, Redondo Beach (California, USA), June 2017. [Best Student Paper Award], [pdf]

"ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation", E. Romera, J. M. Alvarez, L. M. Bergasa and R. Arroyo, Transactions on Intelligent Transportation Systems (T-ITS), [Accepted paper, to be published in Dec 2017]. [pdf]

Packages

  • train contains tools for training the network for semantic segmentation.
  • eval contains tools for evaluating/visualizing the network's output.
  • trained_models Contains the trained models used in the papers.

Requirements

The Cityscapes dataset, which can be downloaded here.

Torch Library (installation tutorial) with CUDA and CuDNN backends.

NOTE: The code has been tested in Ubuntu 16.04 and Torch7 with CUDA 8.0 and CuDNN 5.1. It should work with other versions but we cannot guarantee it.

Usage

Usage and examples for either training or evaluating the models are described in the READMEs of each section.

License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License, which allows for personal and research use only. For a commercial license please contact the authors. You can view a license summary here: http://creativecommons.org/licenses/by-nc/4.0/

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages