https://github.com/cvjena/cn24
Convolutional (Patch) Networks for Semantic Segmentation
https://github.com/cvjena/cn24
convolutional-networks deep-learning opencl segmentation
Last synced: 6 months ago
JSON representation
Convolutional (Patch) Networks for Semantic Segmentation
- Host: GitHub
- URL: https://github.com/cvjena/cn24
- Owner: cvjena
- License: bsd-3-clause
- Created: 2015-01-06T11:29:30.000Z (over 11 years ago)
- Default Branch: master
- Last Pushed: 2021-09-01T14:53:09.000Z (almost 5 years ago)
- Last Synced: 2024-07-31T22:52:55.989Z (almost 2 years ago)
- Topics: convolutional-networks, deep-learning, opencl, segmentation
- Language: C++
- Homepage:
- Size: 8.41 MB
- Stars: 123
- Watchers: 16
- Forks: 44
- Open Issues: 9
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
#### Build status:
master (production branch): [](https://travis-ci.org/cvjena/cn24)
develop (development branch): [](https://travis-ci.org/cvjena/cn24)
## 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](http://www.inf-cv.uni-jena.de) at the [University of Jena](http://www.uni-jena.de).
## 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](http://hera.inf-cv.uni-jena.de:6680/pdf/Brust15:CPN.pdf), 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](https://github.com/cvjena/cn24/wiki)! Installation is just a two command lines away. For an even faster introduction, check out one of these examples:
* [Urban Scene Understanding Example](https://github.com/cvjena/cn24/wiki/Urban-Scene-Understanding-Example)
* [Road Detection Example](https://github.com/cvjena/cn24/wiki/Road-Detection-Example)
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](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](https://pub.inf-cv.uni-jena.de/pdf/Brust2015CPN).
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](http://github.com/clrokr), [Sven Sickert](http://www.inf-cv.uni-jena.de/sickert), [Marcel Simon](http://www.inf-cv.uni-jena.de/simon), and [Erik Rodner](http://www.erodner.de).