深度学习（08）-- Residual Network （ResNet）

目录

1.残差网络基础

1.1基本概念

非常非常深的神经网络是很难训练的，因为存在梯度消失和梯度爆炸问题。ResNets是由残差块（Residual block）构建的，首先解释一下什么是残差块。
残差块结构：

1.2VGG19、ResNet34结构图

1.3 梯度弥散和网络退化

1.4 残差块变体

自AlexNet以来，state-of-the-art的CNN结构都在不断地变深。VGG和GoogLeNet分别有19个和22个卷积层，而AlexNet只有5个。

ResNet基本思想：引入跳过一层或多层的shortcut connection。

1.5 ResNet模型变体

（1）ResNeXt


（2）DenseNet

1.6 Residual Network补充

1.7 1*1卷积核（补充）

*1的卷积核相当于对一个切片上的nc个单元，都应用了一个全连接的神经网络

2.残差网络介绍（何凯明）

3.ResNet-50(Ng)

3.1 非常深的神经网络问题

3.2 建立一个残差网络

使用 short connect的残差块，能很容易的学习标识功能。在其他ResNet块上进行堆栈，不会损害训练集的性能。
（1）identity block （标准块）

（2）convolutional block
当输入和输出的尺寸不匹配时，使用

3.3first ResNet model（50layers）

3.4 代码实现

def identity_block(X, f, filters, stage, block):
    """
    X       -- 输入tensor, shape=(m, n_H_prev, n_W_prev, n_C_prev)
    f       -- identity block主路径，中间卷积层的滤波器大小
    filters -- [f1,f2,f3]对应主路径中三个卷积层的滤波器个数
    stage   -- 用于命名层，阶段（数字表示:1/2/3/4/5...）
    block   -- 用于命名层，每个阶段中的残差块（字符表示：a/b/c/d/e/f...）

    Return   X  -- identity block 输出tensor  shape=(m, n_H, n_W, n_C)    
    """

    "define name basis"
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base   = 'bn'  + str(stage) + block + '_branch'

    "get filter number"
    F1, F2, F3 = filters

    "save the input value"
    X_shortcut = X

    "主路径的第一层：conv-bn-relu"
    X = Conv2D(filters=F1, kernel_size=(1,1), strides=(1,1), padding='valid',
               name=conv_name_base+'2a', kernel_initializer=glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis=3, name=bn_name_base+'2a')(X)
    X = Activation('relu')(X)

    "主路径的第二层：conv-bn-relu"
    X = Conv2D(filters=F2, kernel_size=(f,f), strides=(1,1), padding='same',
               name=conv_name_base+'2b', kernel_initializer=glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis=3, name=bn_name_base+'2b')(X)
    X = Activation('relu')(X)

    "主路径的第三层：conv-bn"
    X = Conv2D(filters=F3, kernel_size=(1,1), strides=(1,1), padding='valid',
               name=conv_name_base+'2c', kernel_initializer=glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis=3, name=bn_name_base+'2c')(X)

    "add shortcut and relu"
    X = Add()([X, X_shortcut])
    X = Activation('relu')(X)

    return X

"""s -- convolutional block中，主路径第一个卷积层和shortcut卷积层，滤波器滑动步长，s=2，用来降低图片大小"""
def convolutional_block(X, f, filters, stage, block, s=2):

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base   = 'bn'  + str(stage) + block + '_branch'

    F1, F2, F3 = filters

    X_shortcut = X

    "1st layer"
    X = Conv2D(filters=F1, kernel_size=(1,1), strides=(s,s), padding='valid',
               name=conv_name_base+'2a', kernel_initializer=glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis=3, name=bn_name_base+'2a')(X)
    X = Activation('relu')(X)

    "2nd layer"
    X = Conv2D(filters=F2, kernel_size=(f,f), strides=(1,1), padding='same',
               name=conv_name_base+'2b', kernel_initializer=glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis=3, name=bn_name_base+'2b')(X)
    X = Activation('relu')(X)

    "3rd layer"
    X = Conv2D(filters=F3, kernel_size=(1,1), strides=(1,1), padding='valid',
               name=conv_name_base+'2c', kernel_initializer=glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis=3, name=bn_name_base+'2c')(X)

    "shortcut path"
    X_shortcut = Conv2D(filters=F3, kernel_size=(1,1), strides=(s,s), padding='valid',
            name=conv_name_base+'1', kernel_initializer=glorot_uniform(seed=0))(X_shortcut)
    X_shortcut = BatchNormalization(axis=3, name=bn_name_base+'1')(X_shortcut)

    X = Add()([X, X_shortcut])
    X = Activation('relu')(X)

    return X

def ResNet50(input_shape=(64,64,3), classes=6):
    """
    input - zero padding 
    stage1：conv - BatchNorm - relu - maxpool
    stage2: conv block - identity block *2
    stage3: conv block - identity block *3
    stage4: conv block - identity block *5
    stage5: conv block - identity block *2
    avgpool - flatten - fully connect

    input_shape  -- 输入图像的shape
    classes      -- 类别数

    Return： a model() instance in Keras
    """

    "用input_shape定义一个输入tensor"
    X_input = Input(input_shape)

    "zero padding"
    X = ZeroPadding2D((3,3))(X_input)

    "stage 1"
    X = Conv2D(filters=64, kernel_size=(7,7), strides=(2,2), padding='valid',
            name='conv1', kernel_initializer=glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis=3, name='bn_conv1')(X)
    X = MaxPooling2D((3,3), strides=(2,2))(X)

    "stage 2"
    X = convolutional_block(X, f=3, filters=[64,64,256], stage=2, block='a', s=1)
    X = identity_block(X,f=3, filters=[64,64,256], stage=2, block='b')
    X = identity_block(X,f=3, filters=[64,64,256], stage=2, block='c')

    "stage 3"
    X = convolutional_block(X, f=3, filters=[128,128,512], stage=3, block='a', s=2)
    X = identity_block(X, f=3, filters=[128,128,512], stage=3, block='b')
    X = identity_block(X, f=3, filters=[128,128,512], stage=3, block='c')
    X = identity_block(X, f=3, filters=[128,128,512], stage=3, block='d')

    "stage 4"
    X = convolutional_block(X, f=3, filters=[256,256,1024], stage=4, block='a', s=2)
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='b')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='c')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='d')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='e')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='f')

    "stage 5"
    X = convolutional_block(X, f=3, filters=[512,512,2048], stage=5, block='a', s=2)
    X = identity_block(X, f=3, filters=[512,512,2048], stage=5, block='b')
    X = identity_block(X, f=3, filters=[512,512,2048], stage=5, block='c')

    "fully connect"
    X = AveragePooling2D((2,2), name='avg_pool')(X)
    X = Flatten()(X)
    X = Dense(classes, activation='softmax', name='fc'+str(classes),
              kernel_initializer=glorot_uniform(seed=0))(X)

    "a model() instance in Keras"
    model = Model(inputs=X_input, outputs=X, name='ResNet50')

    return model

4.ResNet 100-1000层

4.1 152层

代码

def ResNet101(input_shape=(64,64,3), classes=6):
    """
    input - zero padding 
    stage1：conv - BatchNorm - relu - maxpool
    stage2: conv block - identity block *2
    stage3: conv block - identity block *3
    stage4: conv block - identity block *22
    stage5: conv block - identity block *2
    avgpool - flatten - fully connect

    input_shape  -- 输入图像的shape
    classes      -- 类别数

    Return： a model() instance in Keras
    """

    "用input_shape定义一个输入tensor"
    X_input = Input(input_shape)

    "zero padding"
    X = ZeroPadding2D((3,3))(X_input)

    "stage 1"
    X = Conv2D(filters=64, kernel_size=(7,7), strides=(2,2), padding='valid',
            name='conv1', kernel_initializer=glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis=3, name='bn_conv1')(X)
    X = MaxPooling2D((3,3), strides=(2,2))(X)

    "stage 2"
    X = convolutional_block(X, f=3, filters=[4,4,16], stage=2, block='a', s=1)
    X = identity_block(X,f=3, filters=[4,4,16], stage=2, block='b')
    X = identity_block(X,f=3, filters=[4,4,16], stage=2, block='c')

    "stage 3"
    X = convolutional_block(X, f=3, filters=[8,8,32], stage=3, block='a', s=2)
    X = identity_block(X, f=3, filters=[8,8,32], stage=3, block='b')
    X = identity_block(X, f=3, filters=[8,8,32], stage=3, block='c')
    X = identity_block(X, f=3, filters=[8,8,32], stage=3, block='d')

    "stage 4"
    "identity block from 5(50 layers) to 22(101 layers)"
    X = convolutional_block(X, f=3, filters=[16,16,64], stage=4, block='a', s=2)
    X = identity_block(X, f=3, filters=[16,16,64], stage=4, block='b')
    X = identity_block(X, f=3, filters=[16,16,64], stage=4, block='c')
    X = identity_block(X, f=3, filters=[16,16,64], stage=4, block='d')
    X = identity_block(X, f=3, filters=[16,16,64], stage=4, block='e')
    X = identity_block(X, f=3, filters=[16,16,64], stage=4, block='f')
    X = identity_block(X, f=3, filters=[16,16,64], stage=4, block='g')
    X = identity_block(X, f=3, filters=[16,16,64], stage=4, block='h')
    X = identity_block(X, f=3, filters=[16,16,64], stage=4, block='i')
    X = identity_block(X, f=3, filters=[16,16,64], stage=4, block='j')
    X = identity_block(X, f=3, filters=[16,16,64], stage=4, block='k')
    X = identity_block(X, f=3, filters=[16,16,64], stage=4, block='l')
    X = identity_block(X, f=3, filters=[16,16,64], stage=4, block='m')
    X = identity_block(X, f=3, filters=[16,16,64], stage=4, block='n')
    X = identity_block(X, f=3, filters=[16,16,64], stage=4, block='o')
    X = identity_block(X, f=3, filters=[16,16,64], stage=4, block='p')
    X = identity_block(X, f=3, filters=[16,16,64], stage=4, block='q')
    X = identity_block(X, f=3, filters=[16,16,64], stage=4, block='r')
    X = identity_block(X, f=3, filters=[16,16,64], stage=4, block='s')
    X = identity_block(X, f=3, filters=[16,16,64], stage=4, block='t')
    X = identity_block(X, f=3, filters=[16,16,64], stage=4, block='u')
    X = identity_block(X, f=3, filters=[16,16,64], stage=4, block='v')
    X = identity_block(X, f=3, filters=[16,16,64], stage=4, block='w')


    "stage 5"
    X = convolutional_block(X, f=3, filters=[32,32,128], stage=5, block='a', s=2)
    X = identity_block(X, f=3, filters=[32,32,128], stage=5, block='b')
    X = identity_block(X, f=3, filters=[32,32,128], stage=5, block='c')

    "fully connect"
    X = AveragePooling2D((2,2), name='avg_pool')(X)
    X = Flatten()(X)
    X = Dense(classes, activation='softmax', name='fc'+str(classes),
              kernel_initializer=glorot_uniform(seed=0))(X)

    "a model() instance in Keras"
    model = Model(inputs=X_input, outputs=X, name='ResNet101')

    return model

def ResNet152(input_shape=(64,64,3), classes=6):
    """
    input - zero padding 
    stage1：conv - BatchNorm - relu - maxpool
    stage2: conv block - identity block *2
    stage3: conv block - identity block *7
    stage4: conv block - identity block *35
    stage5: conv block - identity block *2
    avgpool - flatten - fully connect

    input_shape  -- 输入图像的shape
    classes      -- 类别数

    Return： a model() instance in Keras
    """

    "用input_shape定义一个输入tensor"
    X_input = Input(input_shape)

    "zero padding"
    X = ZeroPadding2D((3,3))(X_input)

    "stage 1"
    X = Conv2D(filters=64, kernel_size=(7,7), strides=(2,2), padding='valid',
            name='conv1', kernel_initializer=glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis=3, name='bn_conv1')(X)
    X = MaxPooling2D((3,3), strides=(2,2))(X)

    "stage 2"
    X = convolutional_block(X, f=3, filters=[64,64,256], stage=2, block='a', s=1)
    X = identity_block(X,f=3, filters=[64,64,256], stage=2, block='b')
    X = identity_block(X,f=3, filters=[64,64,256], stage=2, block='c')

    "stage 3"
    "identity block from 3(101 layers) to 7(152 layers)"
    X = convolutional_block(X, f=3, filters=[128,128,512], stage=3, block='a', s=2)
    X = identity_block(X, f=3, filters=[128,128,512], stage=3, block='b')
    X = identity_block(X, f=3, filters=[128,128,512], stage=3, block='c')
    X = identity_block(X, f=3, filters=[128,128,512], stage=3, block='d')
    X = identity_block(X, f=3, filters=[128,128,512], stage=3, block='e')
    X = identity_block(X, f=3, filters=[128,128,512], stage=3, block='f')
    X = identity_block(X, f=3, filters=[128,128,512], stage=3, block='g')
    X = identity_block(X, f=3, filters=[128,128,512], stage=3, block='h')


    "stage 4"
    "identity block from 22(101 layers) to 35(152 layers)"
    X = convolutional_block(X, f=3, filters=[256,256,1024], stage=4, block='a', s=2)
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='b')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='c')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='d')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='e')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='f')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='g')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='h')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='i')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='j')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='k')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='l')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='m')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='n')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='o')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='p')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='q')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='r')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='s')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='t')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='u')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='v')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='w')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='x')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='y')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='z')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='z1')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='z2')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='z3')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='z4')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='z5')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='z6')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='z7')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='z8')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='z9')
    X = identity_block(X, f=3, filters=[256,256,1024], stage=4, block='z10')

    "stage 5"
    X = convolutional_block(X, f=3, filters=[512,512,2048], stage=5, block='a', s=2)
    X = identity_block(X, f=3, filters=[512,512,2048], stage=5, block='b')
    X = identity_block(X, f=3, filters=[512,512,2048], stage=5, block='c')

    "fully connect"
    X = AveragePooling2D((2,2), name='avg_pool')(X)
    X = Flatten()(X)
    X = Dense(classes, activation='softmax', name='fc'+str(classes),
              kernel_initializer=glorot_uniform(seed=0))(X)

    "a model() instance in Keras"
    model = Model(inputs=X_input, outputs=X, name='ResNet152')

    return model