ResNet

ResNet意义

在深层网络能够收敛的前提下，随着网络深度的增加，正确率开始饱和甚至下降，称之为网络的退化(degradation)问题。而网络退化的根本原因是优化问题。 因此为了解决优化的难题，提出了残差网络ResNet。其中ResNet提出了两种mapping：一是identity mapping，指的就是图中”弯曲线”，另一种residual mapping，指的就是除了”弯曲线“那部分，所以最后的输出是

identity mapping顾名思义，就是指本身，也就是公式中的xx，而residual mapping指的是“差”，也就是y−xy−x，所以残差指的就是F(x)F(x)部分。

网络结构

上图说明：

1. 图左为基本residual block，residual mapping为两个64通道的3x3卷积，输入输出均为64通道，可直接相加。该block主要使用在相对浅层网络，比如ResNet-34；

2. 图右为针对深层网络提出的block，称为“bottleneck” block，主要目的就是为了降维。首先通过一个1x1卷积将256维通道（channel）降到64通道，最后通过一个256通道的1x1卷积恢复。

代码实现

class ResNet(nn.Module):

    def __init__(self, block, layers, num_classes=1000):
        self.inplanes = 64
        super(ResNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
                               bias=False)#7x7,64
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)#maxpool
        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
        self.avgpool = nn.AvgPool2d(7, stride=1)#average pool
        self.fc = nn.Linear(512 * block.expansion, num_classes)

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                m.weight.data.normal_(0, math.sqrt(2. / n))
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()

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

        layers = []
        layers.append(block(self.inplanes, planes, stride, downsample))
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes))

        return nn.Sequential(*layers)

    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)

        x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)

        return x

参考文章：ResNet介绍
ResNet解析-详细精华版
ResNet理论基础与具体实现（详细教程）