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
- Tensorflow 1.x
- Python 3.x
- tflearn (If you are easy to use global average pooling, you should install tflearn)
- 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- 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
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
- original refers to ResNet-50
Will be soon
Junho Kim