https://github.com/e-lab/enet-training

https://github.com/e-lab/enet-training

Last synced: 6 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/e-lab/enet-training
• Owner: e-lab
• Created: 2016-06-16T15:18:24.000Z (over 8 years ago)
• Default Branch: master
• Last Pushed: 2017-06-26T18:15:27.000Z (over 7 years ago)
• Last Synced: 2024-07-12T07:33:56.640Z (4 months ago)
• Language: Lua
• Size: 132 KB
• Stars: 351
• Watchers: 39
• Forks: 88
• Open Issues: 14
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# ENet

This work has been published in arXiv: [`ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation`](https://arxiv.org/abs/1606.02147).

## Packages:

* [train](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](visualize) can be used to view the performance of trained network on any video/image as an overlay. (Will be added soon)

## Trained model

Find a train model here:

  + [Dropbox link](https://www.dropbox.com/sh/dywzk3gyb12hpe5/AAD5YkUa8XgMpHs2gCRgmCVCa)

  + [Repository release](https://github.com/e-lab/ENet-training/releases/latest)

## Implementation in other frameworks:

* [In Caffe](https://github.com/TimoSaemann/ENet) by [TimoSaemann](https://github.com/TimoSaemann)

* [In Keras](https://github.com/PavlosMelissinos/enet-keras) by [PavlosMelissinos](https://github.com/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.

### License

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/