【深度学习21天学习挑战赛】8、卷积神经网络（认识Xception模型）：动物识别

活动地址：CSDN21天学习挑战赛

• 本文为365天深度学习训练营 中的学习记录博客
• 参考文章地址： 深度学习100例 | 第24天-卷积神经网络（Xception）：动物识别
• 作者：K同学啊

1、 Xception模型主要思想

传统的卷积操作同时对输入的feature mapping的跨通道交互性（cross-channel correlations）、空间交互性（spatial correlations) 进行了映射。

Inception系列结构着力于将上述过程进行分解，在一定程度上实现了跨通道相关性和空间相关性的解耦。

在Inception的基础上进行改进，使用深度可分离卷积（depthwise separate convolution）替代传统的Inception块，实现跨通道相关性和空间相关性的完全解耦。此外，文章还引入了残差连接，最终提出了Xception的网络结构。

Xception是谷歌公司继Inception后，提出的InceptionV3的一种改进模型，其中Inception模块已被深度可分离卷积（depthwise separable convolution）替换。它与Inception-v1（23M）的参数数量大致相同。

2、深度可分离卷积

2.1 标准卷积

输入一个12×12×3的一个输入特征图，经过 5×5×3的卷积核得到一个8×8×1的输出特征图。如果我们此时有256个卷积核，我们将会得到一个8×8×256的输出特征图。

2.2 深度卷积

与标准卷积网络不一样的是，这里会将卷积核拆分成单通道形式，在不改变输入特征图像的深度的情况下，对每一通道进行卷积操作，这样就得到了和输入特征图通道数一致的输出特征图。如上图，输入12x12x3 的特征图，经过5x5x1x3的深度卷积之后，得到了8x8x3的输出特征图。输入和输出的维度是不变的3，这样就会有一个问题，通道数太少，特征图的维度太少，能获得足够的有效信息吗?

2.3逐点卷积

逐点卷积就是1*1卷积，主要作用就是对特征图进行升维和降维，如下图：

在深度卷积的过程中，我们得到了8x8x3的输出特征图，我们用256个1x1x3的卷积核对输入特征图进行卷积操作，输出的特征图和标准的卷积操作一样都是8x8x256了。

标准卷积与深度可分离卷积的过程对比如下：

可见，深度可分离卷积可以实现更少的参数，更少的运算量。

3、构建Xception模型

数据导入及预处理部分略

#====================================#
#     Xception的网络部分
#====================================#
from tensorflow.keras.preprocessing import image

from tensorflow.keras.models import Model
from tensorflow.keras import layers
from tensorflow.keras.layers import Dense,Input,BatchNormalization,Activation,Conv2D,SeparableConv2D,MaxPooling2D
from tensorflow.keras.layers import GlobalAveragePooling2D,GlobalMaxPooling2D
from tensorflow.keras import backend as K
from tensorflow.keras.applications.imagenet_utils import decode_predictions


def Xception(input_shape = [299,299,3],classes=1000):

    img_input = Input(shape=input_shape)
    
    #=================#
    #   Entry flow
    #=================#
    #  block1
    # 299,299,3 -> 149,149,64
    x = Conv2D(32, (3, 3), strides=(2, 2), use_bias=False, name='block1_conv1')(img_input)
    x = BatchNormalization(name='block1_conv1_bn')(x)
    x = Activation('relu', name='block1_conv1_act')(x)
    x = Conv2D(64, (3, 3), use_bias=False, name='block1_conv2')(x)
    x = BatchNormalization(name='block1_conv2_bn')(x)
    x = Activation('relu', name='block1_conv2_act')(x)


    # block2
    # 149,149,64 -> 75,75,128
    residual = Conv2D(128, (1, 1), strides=(2, 2), padding='same', use_bias=False)(x)
    residual = BatchNormalization()(residual)

    x = SeparableConv2D(128, (3, 3), padding='same', use_bias=False, name='block2_sepconv1')(x)
    x = BatchNormalization(name='block2_sepconv1_bn')(x)
    x = Activation('relu', name='block2_sepconv2_act')(x)
    x = SeparableConv2D(128, (3, 3), padding='same', use_bias=False, name='block2_sepconv2')(x)
    x = BatchNormalization(name='block2_sepconv2_bn')(x)

    x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block2_pool')(x)
    x = layers.add([x, residual])

    # block3
    # 75,75,128 -> 38,38,256
    residual = Conv2D(256, (1, 1), strides=(2, 2),padding='same', use_bias=False)(x)
    residual = BatchNormalization()(residual)

    x = Activation('relu', name='block3_sepconv1_act')(x)
    x = SeparableConv2D(256, (3, 3), padding='same', use_bias=False, name='block3_sepconv1')(x)
    x = BatchNormalization(name='block3_sepconv1_bn')(x)
    x = Activation('relu', name='block3_sepconv2_act')(x)
    x = SeparableConv2D(256, (3, 3), padding='same', use_bias=False, name='block3_sepconv2')(x)
    x = BatchNormalization(name='block3_sepconv2_bn')(x)

    x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block3_pool')(x)
    x = layers.add([x, residual])

    # block4
    # 38,38,256 -> 19,19,728
    residual = Conv2D(728, (1, 1), strides=(2, 2),padding='same', use_bias=False)(x)
    residual = BatchNormalization()(residual)

    x = Activation('relu', name='block4_sepconv1_act')(x)
    x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block4_sepconv1')(x)
    x = BatchNormalization(name='block4_sepconv1_bn')(x)
    x = Activation('relu', name='block4_sepconv2_act')(x)
    x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block4_sepconv2')(x)
    x = BatchNormalization(name='block4_sepconv2_bn')(x)

    x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block4_pool')(x)
    x = layers.add([x, residual])

    #=================#
    # Middle flow
    #=================#
    # block5--block12
    # 19,19,728 -> 19,19,728
    for i in range(8):
        residual = x
        prefix = 'block' + str(i + 5)

        x = Activation('relu', name=prefix + '_sepconv1_act')(x)
        x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv1')(x)
        x = BatchNormalization(name=prefix + '_sepconv1_bn')(x)
        x = Activation('relu', name=prefix + '_sepconv2_act')(x)
        x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv2')(x)
        x = BatchNormalization(name=prefix + '_sepconv2_bn')(x)
        x = Activation('relu', name=prefix + '_sepconv3_act')(x)
        x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv3')(x)
        x = BatchNormalization(name=prefix + '_sepconv3_bn')(x)

        x = layers.add([x, residual])

    #=================#
    #    Exit flow
    #=================#
    # block13
    # 19,19,728 -> 10,10,1024
    residual = Conv2D(1024, (1, 1), strides=(2, 2),
                      padding='same', use_bias=False)(x)
    residual = BatchNormalization()(residual)

    x = Activation('relu', name='block13_sepconv1_act')(x)
    x = SeparableConv2D(728, (3, 3), padding='same', use_bias=False, name='block13_sepconv1')(x)
    x = BatchNormalization(name='block13_sepconv1_bn')(x)
    x = Activation('relu', name='block13_sepconv2_act')(x)
    x = SeparableConv2D(1024, (3, 3), padding='same', use_bias=False, name='block13_sepconv2')(x)
    x = BatchNormalization(name='block13_sepconv2_bn')(x)

    x = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='block13_pool')(x)
    x = layers.add([x, residual])

    # block14
    # 10,10,1024 -> 10,10,2048
    x = SeparableConv2D(1536, (3, 3), padding='same', use_bias=False, name='block14_sepconv1')(x)
    x = BatchNormalization(name='block14_sepconv1_bn')(x)
    x = Activation('relu', name='block14_sepconv1_act')(x)

    x = SeparableConv2D(2048, (3, 3), padding='same', use_bias=False, name='block14_sepconv2')(x)
    x = BatchNormalization(name='block14_sepconv2_bn')(x)
    x = Activation('relu', name='block14_sepconv2_act')(x)

    x = GlobalAveragePooling2D(name='avg_pool')(x)
    x = Dense(classes, activation='softmax', name='predictions')(x)

    inputs = img_input

    model = Model(inputs, x, name='xception')

    return model

打印模型如下：

Model: "xception"
__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input_1 (InputLayer)            [(None, 299, 299, 3) 0                                            
__________________________________________________________________________________________________
block1_conv1 (Conv2D)           (None, 149, 149, 32) 864         input_1[0][0]                    
__________________________________________________________________________________________________
block1_conv1_bn (BatchNormaliza (None, 149, 149, 32) 128         block1_conv1[0][0]               
__________________________________________________________________________________________________
......
__________________________________________________________________________________________________
block14_sepconv2 (SeparableConv (None, 10, 10, 2048) 3159552     block14_sepconv1_act[0][0]       
__________________________________________________________________________________________________
block14_sepconv2_bn (BatchNorma (None, 10, 10, 2048) 8192        block14_sepconv2[0][0]           
__________________________________________________________________________________________________
block14_sepconv2_act (Activatio (None, 10, 10, 2048) 0           block14_sepconv2_bn[0][0]        
__________________________________________________________________________________________________
avg_pool (GlobalAveragePooling2 (None, 2048)         0           block14_sepconv2_act[0][0]       
__________________________________________________________________________________________________
predictions (Dense)             (None, 1000)         2049000     avg_pool[0][0]                   
==================================================================================================
Total params: 22,910,480
Trainable params: 22,855,952
Non-trainable params: 54,528
__________________________________________________________________________________________________

模型学习率、编译、训练部分略

4、评估

5、启发

Xception作为Inception v3的改进，主要是在Inception v3的基础上引入了depthwise separable convolution，在基本不增加网络复杂度的前提下提高了模型的效果。