1.创新点：

1.1 超深的网络

超深的网络存在 梯度弥散或者梯度爆炸（比如反向传播的过程中我的值是0.9那么100层之后就是0.92¹⁰⁰ $\approx$ 0) 大于1则是∞。

1.2 解决方法

residual（残差）模块，这里看到有两种残差，一种是虚线的，一种是实线的。

1.3 BN

是一种归一化的手段，用在卷积和激活函数之间的函数。具体可以参考这个大佬的博客（我目前都是跟着这个大佬学习）：
https://blog.csdn.net/qq_37541097/article/details/104434557

2.网络结构

3.代码解析

model.py中的Resnet定义

def resnet34(num_classes=1000, include_top=True):
    return ResNet(BasicBlock, [3, 4, 6, 3], num_classes=num_classes, include_top=include_top)


def resnet101(num_classes=1000, include_top=True):
    return ResNet(Bottleneck, [3, 4, 23, 3], num_classes=num_classes, include_top=include_top)

这部分就是一个初始化一个类即一个resnet，接下来看定义。
return ResNet(BasicBlock, [3, 4, 6, 3], num_classes=num_classes, include_top=include_top)中，我们先看第一个函数的定义：

class BasicBlock(nn.Module):
    expansion = 1
    def __init__(self, in_channel, out_channel, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=out_channel,
                               kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(out_channel)
        self.relu = nn.ReLU()
        self.conv2 = nn.Conv2d(in_channels=out_channel, out_channels=out_channel,
                               kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(out_channel)
        self.downsample = downsample
    def forward(self, x):
        identity = x
        if self.downsample is not None:
            identity = self.downsample(x)

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)

        out += identity
        out = self.relu(out)

        return out

这一块是定义了18和34层resnet的残差结构。可以看到第二层的卷积的步距是写死的，也就是1。为什么第一块是可以变的，这就要回顾到刚刚的网络结构，可以看到，虚线的残差结构就是步距为2。故需要灵活改变。而downsample!=None这个状态，也就是对应虚线部分，要进过一个卷积，这个函数定义在下面。
【小结】残差结构无非就是两种第一种就是普通的也就是downsample=None的情况，实线的残差。第二种，因为你主线的第一个卷积的步距是2，会改变高，宽。所以我们残差的时候支线要进过一个卷积去协调大小。
看完残差结构。我们再整体的去看整个ResNet。

class ResNet(nn.Module):

    def __init__(self, block, blocks_num, num_classes=1000, include_top=True):
        super(ResNet, self).__init__()
        self.include_top = include_top
        self.in_channel = 64

        self.conv1 = nn.Conv2d(3, self.in_channel, kernel_size=7, stride=2,
                               padding=3, bias=False)
        self.bn1 = nn.BatchNorm2d(self.in_channel)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(block, 64, blocks_num[0])
        self.layer2 = self._make_layer(block, 128, blocks_num[1], stride=2)
        self.layer3 = self._make_layer(block, 256, blocks_num[2], stride=2)
        self.layer4 = self._make_layer(block, 512, blocks_num[3], stride=2)
        if self.include_top:
            self.avgpool = nn.AdaptiveAvgPool2d((1, 1))  # output size = (1, 1)
            self.fc = nn.Linear(512 * block.expansion, num_classes)

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')

    def _make_layer(self, block, channel, block_num, stride=1):
        downsample = None
        if stride != 1 or self.in_channel != channel * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.in_channel, channel * block.expansion, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(channel * block.expansion))

        layers = []
        layers.append(block(self.in_channel, channel, downsample=downsample, stride=stride))
        self.in_channel = channel * block.expansion

        for _ in range(1, block_num):
            layers.append(block(self.in_channel, channel))
        return nn.Sequential(*layers)

可以看到layer就是定义每个层，第一个大层的结构没有虚线，第二层有虚线，所以先加入一个虚线的残差结构（步距为2），剩下的加入的残差结构（步距为1，默认值是1可以看到最上边的定义）

正向传播

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool(x)

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)

        if self.include_top:
            x = self.avgpool(x)
            x = torch.flatten(x, 1)
            x = self.fc(x)

        return x

resnet 50 101 152的残差结构定义

class Bottleneck(nn.Module):
    expansion = 4

    def __init__(self, in_channel, out_channel, stride=1, downsample=None):
        super(Bottleneck, self).__init__()
        self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=out_channel,
                               kernel_size=1, stride=1, bias=False)  # squeeze channels
        self.bn1 = nn.BatchNorm2d(out_channel)
        # -----------------------------------------
        self.conv2 = nn.Conv2d(in_channels=out_channel, out_channels=out_channel,
                               kernel_size=3, stride=stride, bias=False, padding=1)
        self.bn2 = nn.BatchNorm2d(out_channel)
        # -----------------------------------------
        self.conv3 = nn.Conv2d(in_channels=out_channel, out_channels=out_channel*self.expansion,
                               kernel_size=1, stride=1, bias=False)  # unsqueeze channels
        self.bn3 = nn.BatchNorm2d(out_channel*self.expansion)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample

    def forward(self, x):
        identity = x
        if self.downsample is not None:
            identity = self.downsample(x)

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)
        out = self.relu(out)

        out = self.conv3(out)
        out = self.bn3(out)

        out += identity
        out = self.relu(out)

        return out