ResNet理解

       随着网络深度的增加，精确度变得饱和，然后迅速退化。出乎意料是，这种退化并不是由于模型的过拟合造成的，而且在适当深度的模型中增加更多的层会导致更高的训练误差，为了训练更深层次的神经网络，提出了一种全新的网络，叫做深度残差网络。深度残差网络获得了ILSVRC & COCO 2015 竞赛第一名，而且在ImageNet检测、ImageNet定位、COCO检测以及COCO分割上均获得了第一名的成绩。

一，残差块

一个残差块包含两部分：identity mapping 和 residual mapping，其中identity mapping指的是曲线部分，resdual mapping表示的是非曲线部分，

形式上，将期望的底层映射为H(x)，将堆叠的非线性层拟合另一个映射F(x)=H(x) - x。原始的映射就变成F(x) + x，这里假设残差映射比原始的，为参考的映射更容易优化。

二，深度瓶颈结构

残差模块具有两种形式如上图所示：左边适用于小型网络结构，右图适用于较深的网络结构主要用来降低网络的计算量和参数。

右图主要使用两个1*1的卷积和一个3*3的卷积，1*1的卷积先对特征图进行降维，再增加特征图的维度。

使用瓶颈结构的残差块参数为：1 * 1 * 256 * 64 + 3 * 3 * 64 * 64 + 1 * 1 * 64 * 256 = 69632

不使用瓶颈结构的残差块参数为：3 * 3 * 256 * 256 * 2 = 1179648 

参数大概相差了17倍。

三，网络结构

1，平原网络

这里平原网络的基准主要受到VGG网络的启发，遵循两个简单的设计原则：

(1)相同的输出特征图尺寸，层的卷积核数量也是相同的。

(2)特征图的尺寸减半，卷积核的数量就加倍，保证每层的时间复杂度相同。

通过strides为2的卷积层来降低特征图的尺寸，如下图中间的网络所示。

2，残差网络

残差网络是在平原网络的基础上增加短路连接。当输入和输出维度相同时，可以shortcut可以直接使用；不相同时，需要进行维度匹配。其中主要的做法如下：

（1）采用零填充来增加维度；

（2）通过1 * 1 的卷积层来增加维度；

四，残差网络

主要的残差网络有resnet50/101/152:

resnet50主要由五个部分组成：

• 通过一个(3, 3)的zero-padding对输入进行填充；
• stage1:
•          conv1:shape（7，7)，filters of number 64，strides（2， 2）
•          BN：channels axis of the input
•          maxpooling: shape(3, 3), strides(2, 2)
• stage 2:
•          conv block: number of filters[64, 64, 256], f is 3, s is 1, block is a
•         identity block : number of filters[64, 64, 356], f is 3, block is b, c
• stage 3:
•            conv block:number of filters[128, 128, 512], f is 3, s is 2, block is a
•           identity block : number of filters[128, 128, 512], f is 3, block is b, c
• stage 4:
•            conv block : number of filters[256, 256, 1024], f is 3, s is 2,block is a
•            identity block: number of filters[256, 256, 1024], f is 3, block is b, c, d, e, f
• stage 5：
•           conv block: number of filters[512, 512, 2048], f is 3, s is 2, block is a
•          identity block : number of filters[512, 512, 2048], f is 3, block is b, c
•          avg_pool:shape is（2， 2）

 

五，ResNet50实现

使用keras对ResNet50网络进行复现：网络主要包括五个阶段.

from keras.layers import Input
from keras.layers import MaxPooling2D, GlobalAveragePooling2D, ZeroPadding2D
from keras.layers import Conv2D, BatchNormalization, Activation, add, Dense
from keras.models import Model
from keras.utils.vis_utils import plot_model


def conv_block(input_tensor, kernel_size, filters, stage, block, strides):
    assert len(filters) == 3
    filter1, filter2, filter3 = filters
    conv_name_base = 'conv'+ str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'
    # 1 * 1
    x = Conv2D(filter1, kernel_size=(1, 1),
               strides=strides, # stage2, strides=1; stage345, strides=2
               kernel_initializer='he_normal',
               name=conv_name_base + '2a')(input_tensor)
    x = BatchNormalization(axis=3, name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)
    # 3 * 3
    x = Conv2D(filter2, kernel_size, padding='same',
               kernel_initializer='he_normal', name=conv_name_base + '2b')(x)
    x = BatchNormalization(axis=3, name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)
    # 1 * 1
    x = Conv2D(filter3, kernel_size=(1, 1),
               kernel_initializer='he_normal',
               name=conv_name_base + '2c')(x)
    x = BatchNormalization(axis=3, name=bn_name_base + '2c')(x)
    shortcut = Conv2D(filter3, kernel_size=(1, 1),
                      strides=strides,
                      kernel_initializer='he_normal',
                      name=conv_name_base + '1')(input_tensor)
    shortcut = BatchNormalization(axis=3, name=bn_name_base + '1')(shortcut)
    x = add([x, shortcut])
    x = Activation('relu')(x)
    return x

def identity_block(input_tensor, kernel_size, filters, stage, block):
    assert len(filters) == 3
    filter1, filter2, filter3 = filters
    conv_name = 'res' + str(stage) + block + '_barnch'
    bn_name = 'bn' + str(stage) + block + '_branch'
    # 1 * 1
    x = Conv2D(filter1, kernel_size=(1, 1),
               kernel_initializer='he_normal',
               name=conv_name + '2a')(input_tensor)
    x = BatchNormalization(axis=3, name=bn_name + '2a')(x)
    x = Activation('relu')(x)
    # 3 * 3
    x = Conv2D(filter2, kernel_size,
               padding='same',
               kernel_initializer='he_normal',
               name=conv_name + '2b')(x)
    x = BatchNormalization(axis=3, name=bn_name + '2b')(x)
    x = Activation('relu')(x)
    # 1 * 1
    x = Conv2D(filter3, kernel_size=(1, 1),
               kernel_initializer='he_normal',
               name=conv_name + '2c')(x)
    x = BatchNormalization(axis=3, name=bn_name + '2c')(x)
    print(x.shape, input_tensor.shape)
    x = add([x, input_tensor])
    x = Activation('relu')(x)
    return x

def resnet50(input_tensor, include_top=True, classes=1000):
    # stage 1
    x = ZeroPadding2D((3, 3), name='padding')(input_tensor)
    x = Conv2D(64, kernel_size=(7, 7), strides=(2, 2),
               kernel_initializer='he_normal',
               name='conv1')(x)
    x = BatchNormalization(axis=3, name='conv1_bn')(x)
    x = Activation('relu', name='conv1_relu')(x)
    x = MaxPooling2D((3, 3), strides=(2, 2), name='pool')(x)
    # stage 2 repeat 3
    x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
    x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
    x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')
    # stage 3 repeat 4
    x = conv_block(x, 3, [128, 128, 512], stage=3, block='a', strides=(2, 2))
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')
    # stage 4 repeat 6
    x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a', strides=(2, 2))
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f')
    # stage 5 repeat 3
    x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a', strides=(2, 2))
    x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
    x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')

    if include_top:
        x = GlobalAveragePooling2D(name='avg_pool')(x)
        x = Dense(classes, activation='softmax', name='fc1000')(x)
    model = Model(input=inputs, output=x, name='ResNet50')
    return model


inputs = Input(shape=(224, 224, 3))
model = resnet50(inputs)
plot_model(model, to_file='./resnet50.jpg', show_shapes=True)

六，ResNet50网络结构图