https://github.com/vivelev/senet-flow

Squeeze-and-Excitation Network - implementation in TensorFlow
https://github.com/vivelev/senet-flow

neural-network squeeze-and-excitation tensorflow

Last synced: about 1 month ago
JSON representation

Squeeze-and-Excitation Network - implementation in TensorFlow

• Host: GitHub
• URL: https://github.com/vivelev/senet-flow
• Owner: VIVelev
• License: mit
• Created: 2019-02-05T22:39:19.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2019-02-10T10:42:41.000Z (over 7 years ago)
• Last Synced: 2025-02-15T07:14:37.558Z (over 1 year ago)
• Topics: neural-network, squeeze-and-excitation, tensorflow
• Language: Jupyter Notebook
• Homepage:
• Size: 633 KB
• Stars: 1
• Watchers: 3
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# SENet-flow

Squeeze-and-Excitation Network (SENet) implementation in [TensorFlow](https://www.tensorflow.org)

***You can find the original paper [here](https://arxiv.org/pdf/1709.01507.pdf)*** 


written by Jie Hu, Li Shen, Gang Sun

If you want to see ***the original author's code***, please refer to this [link](https://github.com/hujie-frank/SENet)

## Requirements

 - Python 3.x

 - Tensorflow 1.x

## Idea

### What is SENet?



  





  Figure 1: Diagram of a Squeeze-and-Excitation building block



### How do you integrate it in existing powerful architectures? (Inception Network, ResNet)



   

  





  Figure 2: Schema of SE-Inception and SE-ResNet modules



### Hyper-parameters

 - Reduction Ratio - controls the bottleneck size (the number of units in the bottleneck dense layer)



   





  Figure 3: Different choices for the Reduction Ratio hyperparameter and the consequent results



## Why should you use Squeeze-and-Excitation Netwroks

### State-of-the-art performace on ILSVRC 2017 (ImageNet 2017 dataset)



   





  Figure 4: State-of-the-art performace on ILSVRC 2017