This work has been published in arXiv: ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation.

• train contains tools for training network using various architectures. It can be further used for visulaization of network's performance. This section is mainly for pixelwise segmentation and scene-parsing.
• visualize can be used to view the performance of trained network on any video/image as an overlay. (Will be added soon)

Find a train model here:

• Dropbox link
• Repository release

• In Caffe by TimoSaemann
• In Keras by PavlosMelissinos

Thank you for your contribution. We have not verified results of the above two implementations but still we feel that researchers working on these different frameworks might find it useful.

This software is released under a creative commons 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/