CN24 Convolutional Neural Networks for Semantic Segmentation 1.0

Clemens Alexander Brust, Sven Sickert, Marcel Simon, Erik Rodner — Mon, 23 Feb 2015 09:02:06 -0000

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 at the Computer Vision Group, University of Jena.

Why should I use CN24?

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

mloss.org CN24 Convolutional Neural Networks for Semantic Segmentation

CN24 Convolutional Neural Networks for Semantic Segmentation 1.0