1、ResNet残差网络的bottlenet结构
代码编写如下:
regul = regularizers.l2(l2)
optim = Adam(lr=lr)
kwargs = {'padding':'same', 'kernel_regularizer':regul}
bottlenet:
def subblock(x, filter, **kwargs):
x = BatchNormalization()(x)
y = x
y = Conv2D(filter, (1, 1), activation='relu', **kwargs)(y) # 减少特征数量
y = BatchNormalization()(y)
y = Conv2D(filter, (3, 3), activation='relu', **kwargs)(y) # 扩展特征域
y = BatchNormalization()(y)
y = Conv2D(K.int_shape(x)[-1], (1, 1), **kwargs)(y) # 无激活函数 # 恢复原始特征的数量
y = Add()([x,y]) # Add the bypass connection
y = Activation('relu')(y)
return y
当然还有conv block如下图:
2、网络层数
我们所说的网络层数,主要指的是Conv的层和fc全连接层,如下图的VGG19网络