残差网络ResNet

残差网络的核心思想每个附加层更容易地包含原始函数作为其元素之一。 通俗点就是类似与一个嵌套的函数结构保证更接近真实的函数。

残差块串联一个层改变函数类相当于扩大函数类加入快速通道来得到相应的结构类似于一个跳跃的操作。残差块的优点就是使得很深的网络更加容易训练输入可通过跨层更快地向前传播。

ResNet架构类似于VGG但是是替换成了ResNet块残差快里首先是两个有相同输出通道的3*3卷积层每个卷积层后面是一个批量规范化层和ReLU激活函数。通过跨层数据通路跳过这两个卷积运算将输入加在最后的ReLU激活函数之前。如果改变通道数的话可以再引入一个1*1的卷积层将输入变换成需要的形状后再做相加运算。

import torch
from torch import nn
from torch.nn import functional as F
from d2l import torch as d2l

class Residual(nn.Module): 
    def __init__(self, input_channels, num_channels,
                 use_1x1conv=False, strides=1):
        super().__init__()
        self.conv1 = nn.Conv2d(input_channels, num_channels,
                               kernel_size=3, padding=1, stride=strides)
        self.conv2 = nn.Conv2d(num_channels, num_channels,
                               kernel_size=3, padding=1)
        if use_1x1conv:
            self.conv3 = nn.Conv2d(input_channels, num_channels,
                                   kernel_size=1, stride=strides)
        else:
            self.conv3 = None
        self.bn1 = nn.BatchNorm2d(num_channels)
        self.bn2 = nn.BatchNorm2d(num_channels)

    def forward(self, X):
        Y = F.relu(self.bn1(self.conv1(X)))
        Y = self.bn2(self.conv2(Y))
        if self.conv3:
            X = self.conv3(X)
        Y += X
        return F.relu(Y)

blk = Residual(3,3)
X = torch.rand(4, 3, 6, 6)
Y = blk(X)

# 在增加输出通道数的同时减半输出的高和宽
blk = Residual(3,6, use_1x1conv=True, strides=2)

#在输出通道数为64、步幅为2的7*7卷积层后接步幅为2的3*3的最大汇聚层ResNet每个卷积层后增加了批量规范化层
b1 = nn.Sequential(nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3),
                   nn.BatchNorm2d(64), nn.ReLU(),
                   nn.MaxPool2d(kernel_size=3, stride=2, padding=1))

def resnet_block(input_channels, num_channels, num_residuals,
                 first_block=False):
    blk = []
    for i in range(num_residuals):
        if i == 0 and not first_block:
            blk.append(Residual(input_channels, num_channels,
                                use_1x1conv=True, strides=2))
        else:
            blk.append(Residual(num_channels, num_channels))
    return blk

# 在ResNet加入所有残差块每个模块使用2个残差块
b2 = nn.Sequential(*resnet_block(64, 64, 2, first_block=True))
b3 = nn.Sequential(*resnet_block(64, 128, 2))
b4 = nn.Sequential(*resnet_block(128, 256, 2))
b5 = nn.Sequential(*resnet_block(256, 512, 2))

# 在ResNet中加入全局平均汇聚层以及全连接层输出
net = nn.Sequential(b1, b2, b3, b4, b5,
                    nn.AdaptiveAvgPool2d((1,1)),
                    nn.Flatten(), nn.Linear(512, 10))