Skip to content
项目

taki0112/SENet-Tensorflow has 754 GitHub stars and 264 forks. GitHot measured 0 stars in 24 hours. Last checked 2026-11-19 18:52 UTC. Last push 2018-08-14.

这些数字如何统计

实测星标增长

24小时
0
7天
正在收集历史
15天
正在收集历史
1个月
正在收集历史

各周期内的星标净变化,周期相互重叠,并非每日新增。缺失的测量保持空白。星标代表关注度,不代表软件质量。

关于

Simple Tensorflow implementation of "Squeeze and Excitation Networks" using Cifar10 (ResNeXt, Inception-v4, Inception-resnet-v2)

机器学习

README.md

原文

SENet-Tensorflow

Simple Tensorflow implementation of Squeeze Excitation Networks using Cifar10

I implemented the following SENet

If you want to see the original author's code, please refer to this link

Requirements

  • Tensorflow 1.x
  • Python 3.x
  • tflearn (If you are easy to use global average pooling, you should install tflearn)

Issue

Image_size

  • In paper, experimented with ImageNet
  • However, due to image size issues in Inception network, so I used zero padding for the Cifar10
input_x = tf.pad(input_x, [[0, 0], [32, 32], [32, 32], [0, 0]]) # size 32x32 -> 96x96

NOT ENOUGH GPU Memory

  • If not enough GPU memory, Please edit the code
with tf.Session() as sess : NO
with tf.Session(config=tf.ConfigProto(allow_soft_placement=True)) as sess : OK

Idea

What is the "SE block" ?

senet

def Squeeze_excitation_layer(self, input_x, out_dim, ratio, layer_name):
    with tf.name_scope(layer_name) :
        squeeze = Global_Average_Pooling(input_x)

        excitation = Fully_connected(squeeze, units=out_dim / ratio, layer_name=layer_name+'_fully_connected1')
        excitation = Relu(excitation)
        excitation = Fully_connected(excitation, units=out_dim, layer_name=layer_name+'_fully_connected2')
        excitation = Sigmoid(excitation)

        excitation = tf.reshape(excitation, [-1,1,1,out_dim])

        scale = input_x * excitation

        return scale

How apply ? (Inception, Residual)

 

How "Reduction ratio" should I set?

reduction

  • original refers to ResNet-50

ImageNet Results

Benefits against Network Depth

depth

Incorporation with Modern Architecture

incorporation

Comparison with State-of-the-art

compare

Cifar10 Results

Will be soon

Related works

Reference

Author

Junho Kim