https://github.com/scheckmedia/keras-shufflenet

ShuffleNet Implementation using Keras Functional Framework 2.0
https://github.com/scheckmedia/keras-shufflenet

deep-learning keras machine-learning neural-network python2 python3 research tensorflow

Last synced: about 1 month ago
JSON representation

ShuffleNet Implementation using Keras Functional Framework 2.0

• Host: GitHub
• URL: https://github.com/scheckmedia/keras-shufflenet
• Owner: scheckmedia
• License: mit
• Archived: true
• Created: 2017-10-20T11:35:07.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2020-10-16T16:25:44.000Z (about 4 years ago)
• Last Synced: 2024-08-01T22:50:06.504Z (4 months ago)
• Topics: deep-learning, keras, machine-learning, neural-network, python2, python3, research, tensorflow
• Language: Python
• Homepage:
• Size: 15.8 MB
• Stars: 78
• Watchers: 5
• Forks: 40
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

• awesome-image-classification - unofficial-keras : https://github.com/scheckmedia/keras-shufflenet
• awesome-image-classification - unofficial-keras : https://github.com/scheckmedia/keras-shufflenet

README

        
# Keras ShuffleNet [![Build Status](https://travis-ci.org/scheckmedia/keras-shufflenet.svg?branch=master)](https://travis-ci.org/scheckmedia/keras-shufflenet)

ShuffleNet Implementation using Keras Functional Framework 2.0

There is a [weight file](weigths/ShuffleNet_1X_g3_br_0.25_373.hdf5) for groups=3 but I was not able to reproduce the accuracy from the paper.

Current accuracy for ImageNet is **0.5228**.

### Library Versions

- Keras v2.0.8+

- Tensorflow 1.0+

### References

1) [Keras Framework](https://www.keras.io)

2) [ShuffleNet Paper](https://arxiv.org/pdf/1707.01083.pdf)

### Licence 

MIT License 

Note: If you find this project useful, please include reference link in your work.