https://github.com/opconty/keras-shufflenetV2

Keras implementation of ShuffleNet V2
https://github.com/opconty/keras-shufflenetV2

Last synced: about 1 month ago
JSON representation

Keras implementation of ShuffleNet V2

• Host: GitHub
• URL: https://github.com/opconty/keras-shufflenetV2
• Owner: opconty
• Created: 2018-08-14T09:53:02.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2018-08-14T10:02:22.000Z (over 6 years ago)
• Last Synced: 2024-08-01T22:50:09.792Z (4 months ago)
• Language: Python
• Size: 5.89 MB
• Stars: 96
• Watchers: 6
• Forks: 44
• Open Issues: 8
• Metadata Files:
  • Readme: readme.md

Awesome Lists containing this project

• awesome-image-classification - unofficial-keras : https://github.com/opconty/keras-shufflenetV2
• awesome-image-classification - unofficial-keras : https://github.com/opconty/keras-shufflenetV2

README

        
## Keras ShuffleNet V2

> Keras implementation of ShuffleNet V2

### Example

The example is from  [kaggle emotion recognition challenge](https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge), this is the [pre-trained model](./weights/shufflenetv2_emotion_recogn.h5) using shufflenet v2

demo result:

![demo](./images/a_emo.png)

### References

[(repo)keras-shufflenet](https://github.com/scheckmedia/keras-shufflenet)

[(paper)ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://arxiv.org/abs/1807.11164)

### Licence

[MIT License](https://opensource.org/licenses/MIT)