ResNet 超详细手工推到（小白都可以看懂）

1、Resnet来源

          ResNet（Residual Neural Network）来源于微软研究院的Kaiming He等人的论文《Deep Residual Learning for Image Recognition》。

Resnet框架如下图：

                                                  

        ResNet沿用了VGG完整的3×3卷积层设计，主要贡献就是发现了"退化现象"，退化的含义就是 一开始深度越深，模型的准确率越高。后来继续加深，模型的准确率出现了毫无征兆的下降。ResNet的出现推翻了以前层数越高，准确率越高的思想。 Resnet增加了快捷链接分支，在线性转换核非线性转换之间寻求一个平衡。以下为不同深度的残差网络：

 

接下来我们以Renet画一个简单的流程图：

 

      

 Pytorch实现Resnet18:

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


class RestNetBasicBlock(nn.Module):
    def __init__(self, in_channels, out_channels, stride):
        super(RestNetBasicBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1)
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=stride, padding=1)
        self.bn2 = nn.BatchNorm2d(out_channels)

    def forward(self, x):
        output = self.conv1(x)
        output = F.relu(self.bn1(output))
        output = self.conv2(output)
        output = self.bn2(output)
        return F.relu(x + output)


class RestNetDownBlock(nn.Module):
    def __init__(self, in_channels, out_channels, stride):
        super(RestNetDownBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride[0], padding=1)
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=stride[1], padding=1)
        self.bn2 = nn.BatchNorm2d(out_channels)
        self.extra = nn.Sequential(
            nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=stride[0], padding=0),
            nn.BatchNorm2d(out_channels)
        )

    def forward(self, x):
        extra_x = self.extra(x)
        output = self.conv1(x)
        out = F.relu(self.bn1(output))

        out = self.conv2(out)
        out = self.bn2(out)
        return F.relu(extra_x + out)


class RestNet18(nn.Module):
    def __init__(self):
        super(RestNet18, self).__init__()
        self.layer1=nn.Sequential(nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3),
                                  nn.BatchNorm2d(64),
                                  nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        )

        self.layer2 = nn.Sequential(RestNetBasicBlock(64, 64, 1),
                                    RestNetBasicBlock(64, 64, 1))

        self.layer3 = nn.Sequential(RestNetDownBlock(64, 128, [2, 1]),
                                    RestNetBasicBlock(128, 128, 1))

        self.layer4 = nn.Sequential(RestNetDownBlock(128, 256, [2, 1]),
                                    RestNetBasicBlock(256, 256, 1))

        self.layer5 = nn.Sequential(RestNetDownBlock(256, 512, [2, 1]),
                                    RestNetBasicBlock(512, 512, 1))

        self.avgpool = nn.AdaptiveAvgPool2d(output_size=(1, 1))

        self.fc = nn.Linear(512, 10)

    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.layer4(out)
        out = self.layer5(out)
        
        out = self.avgpool(out)
        out = out.reshape(x.shape[0], -1)
        out = self.fc(out)
        return out