keras中的ResNet-50和SENet结合。

最新推荐文章于 2025-06-12 18:00:26 发布

原创最新推荐文章于 2025-06-12 18:00:26 发布 · 5.5k 阅读

17 ·

CC 4.0 BY-SA版权

文章标签：

#Keras #SENet #ResNet

keras 专栏收录该内容

8 篇文章

订阅专栏

本文深入解析了SENet与ResNet在网络架构上的融合应用，详细介绍了如何通过全局平均池化、全连接层和激活函数等操作实现特征的挤压与激励，以及如何将此机制整合到ResNet中，提升模型的表达能力。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

参考caffe：https://github.com/hujie-frank/SENet

def expand_dim_backend(self,x):
    x1 = K.reshape(x,(-1,1,256))
    print('x1:',x1)
    return x1
def multiply(self,a):
    x = np.multiply(a[0], a[1])
    print('x:',x)
    return x

def make_net_Res(self, encoding):
    # Input
    x = ZeroPadding1D(padding=3)(encoding)
    x = Conv1D(filters=64, kernel_size=7, strides=2, padding='valid', activation='relu')(x)
    x = BatchNormalization(axis=1, scale=True)(x)
    x_pool = MaxPooling1D(pool_size=3, strides=2, padding='same')(x)



 #RESNet_1
    x = Conv1D(filters=128, kernel_size=1, strides=1, padding='valid', activation='relu')(x_pool)
    x = BatchNormalization(axis=1, scale=True)(x)
    
    x = Conv1D(filters=128, kernel_size=3, strides=1, padding='valid', activation='relu')(x)
    x = BatchNormalization(axis=1, scale=True)(x)
    
    RES_1 = Conv1D(filters=256, kernel_size=1, strides=1, padding='valid', activation='relu')(x)
    x = BatchNormalization(axis=1, scale=True)(RES_1)

# SENet
squeeze = GlobalAveragePooling1D()(x)
squeeze = Lambda(self.expand_dim_backend)(squeeze)

excitation = Conv1D(filters=16, kernel_size=1, strides=1, padding='valid', activation='relu')(squeeze)
excitation = Conv1D(filters=256, kernel_size=1, strides=1, padding='valid', activation='sigmoid')(excitation)

x_pool_1 = Conv1D(filters=256, kernel_size=1, strides=1, padding='valid', activation='relu')(x_pool)
x_pool_1 = BatchNormalization(axis=1, scale=True)(x_pool_1)

scale = Lambda(self.multiply)([RES_1, excitation])
res_1 = Concatenate(axis=1)([x_pool_1, scale])

#RESNet_2
x = Conv1D(filters=128, kernel_size=1, activation='relu')(res_1)
x = BatchNormalization(axis=1, scale=True)(x)

x = Conv1D(filters=128, kernel_size=3,  activation='relu')(x)
x = BatchNormalization(axis=1, scale=True)(x)

RES_2 = Conv1D(filters=256, kernel_size=1)(x)

# SENet
squeeze = GlobalAveragePooling1D()(RES_2)
squeeze = Lambda(self.expand_dim_backend)(squeeze)

excitation = Conv1D(filters=16, kernel_size=1, strides=1, padding='valid', activation='relu')(squeeze)
excitation = Conv1D(filters=256, kernel_size=1, strides=1, padding='valid', activation='sigmoid')(excitation)

scale = Lambda(self.multiply)([RES_2, excitation])
x = Concatenate(axis=1)([res_1, scale])

x = GlobalMaxPooling1D()(x)
print('x:', x)
output = Dense(1, activation='sigmoid')(x)
return (output)