SE Block （Sequeze and Excitation）

最新推荐文章于 2024-07-01 14:28:14 发布

bl128ve900

最新推荐文章于 2024-07-01 14:28:14 发布

阅读量2.2w

点赞数 6

分类专栏：论文学习

本文链接：https://blog.csdn.net/bl128ve900/article/details/93778729

版权

看senet block的代码，明白如何实现

def Squeeze_excitation_layer(self, input_x, out_dim, ratio, layer_name):
    with tf.name_scope(layer_name) :
        squeeze = Global_Average_Pooling(input_x)#对每个通道取全局最大化
        excitation = Fully_connected(squeeze, units=out_dim / ratio, layer_name=layer_name+'_fully_connected1')
        excitation = Relu(excitation)
        #为什么用两个全卷基层， 而且为什么卷基层的unit不同？
        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])