Convolutional (Patch) Networks for Semantic Segmentation
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
ci .travis.yml: Added custom clBLAS installation script Sep 18, 2015
cmake CMakeLists: Added define for current git HEAD; cmake: Added GetGitRev… May 20, 2015
example
external/sqlite3
include
kernels kernels: Fixed strided im2col bug Apr 21, 2016
parser Parser: Started work on graph network parser Jun 15, 2015
scripts Script: Improved experiment-running scripts Dec 12, 2015
src TensorMath: Added missing CPU transfers to COL2IM and IM2COL Apr 21, 2016
tests SimpleLayerTest: Removed wrong continue out of inner for loop for wei… Apr 21, 2016
tools trainNetwork: Fixed bug when compiling with LAYERTIME enabled Jan 16, 2016
.gitignore Initial commit for public repository Jan 12, 2015
.travis.yml
CMakeLists.txt CMakeLists.txt: Removed boost settings for [ci] Mar 31, 2016
CONTRIBUTORS CONTRIBUTORS: Added recent contributions Sep 7, 2015
LICENSE License update Jan 14, 2015
README.md
compile-and-test.sh Merge branch 'demo' Feb 19, 2015

README.md

Build status:

master (production branch): Build Status develop (development branch): Build Status

Welcome to the CN24 GitHub repository!

CN24 is a complete semantic segmentation framework using fully convolutional networks. It supports a wide variety of platforms (Linux, Mac OS X and Windows) and libraries (OpenCL, Intel MKL, AMD ACML...) while providing dependency-free reference implementations. The software is developed in the Computer Vision Group at the University of Jena.

Why should I use CN24?

  1. Designed for pixel-wise labeling and semantic segmentation (train and test your own networks!)
  2. Suited for various applications in driver assistance systems, scene understanding, remote sensing, biomedical image processing and many more
  3. OpenCL support not only suited for NVIDIA GPUs
  4. High-performance implementation with minimal dependencies to other libraries

Getting started

To get started, clone this repository and visit the wiki! Installation is just a two command lines away. For an even faster introduction, check out one of these examples:

The repository contains pre-trained networks for these two applications, which are ready to use.

Licensing

CN24 is available under a 3-clause BSD license. See LICENSE for details. If you use CN24 for research, please cite our paper Clemens-Alexander Brust, Sven Sickert, Marcel Simon, Erik Rodner, Joachim Denzler. "Convolutional Patch Networks with Spatial Prior for Road Detection and Urban Scene Understanding". VISAPP 2015.

Remark: The paper does not discuss the fully convolutional network adaptations integrated in CN24.

Questions?

If you have questions, feedback, or experience problems. Let us know and write an e-mail to Clemens-Alexander Brust, Sven Sickert, Marcel Simon, and Erik Rodner.