Squeeze-and-Excitation Network (SENet) implementation in TensorFlow
You can find the original paper here
written by Jie Hu, Li Shen, Gang Sun
If you want to see the original author's code, please refer to this link
- Python 3.x
- Tensorflow 1.x
Figure 1: Diagram of a Squeeze-and-Excitation building block
Figure 2: Schema of SE-Inception and SE-ResNet modules
- 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
Figure 4: State-of-the-art performace on ILSVRC 2017