resnet18与resnet50

ResNet18的18层代表的是带有权重的 18层，包括卷积层和全连接层，不包括池化层和BN层。

Resnet论文给出的结构图

参考ResNet详细解读

结构解析：

1. 首先是第一层卷积使用7∗77∗7大小的模板，步长为2，padding为3。之后进行BN，ReLU和maxpool。这些构成了第一部分卷积模块conv1。

2. 然后是四个stage，代码中用make_layer()来生成stage，每个stage中有多个模块，每个模块叫做building block，resnet18= [2,2,2,2]，就有8个building block。注意到他有两种模块BasicBlock和Bottleneck。resnet18和resnet34用的是BasicBlock，resnet50及以上用的是Bottleneck。无论BasicBlock还是Bottleneck模块，都用到了shortcut connection连接方式：

   

   • BasicBlock架构中，主要使用了两个3x3的卷积，然后进行BN，之后的out += residual这一句在输出上叠加了输入xx（注意到一开始定义了residual = x）

     class BasicBlock(nn.Module):
         expansion = 1
     
         def __init__(self, inplanes, planes, stride=1, downsample=None):
             super(BasicBlock, self).__init__()
             self.conv1 = conv3x3(inplanes, planes, stride)
             self.bn1 = nn.BatchNorm2d(planes)
             self.relu = nn.ReLU(inplace=True)
             self.conv2 = conv3x3(planes, planes)
             self.bn2 = nn.BatchNorm2d(planes)
             self.downsample = downsample
             self.stride = stride
     
         def forward(self, x):
             residual = x
     
             out = self.conv1(x)
             out = self.bn1(out)
             out = self.relu(out)
     
             out = self.conv2(out)
             out = self.bn2(out)
     
             if self.downsample is not None:
                 residual = self.downsample(x)
     
             out += residual
             out = self.relu(out)
     
             return out
     

   • Bottleneck模块使用1x1，3x3，1x1的卷积模板，使用Bottleneck结构可以减少网络参数数量。他首先用1x1卷积将通道数缩减为一半，3x3卷积维持通道数不变，1x1卷积将通道数放大为4倍。则总体来看，经过这个模块后通道数变为两倍。

     class Bottleneck(nn.Module):
         expansion = 4
     
         def __init__(self, inplanes, planes, stride=1, downsample=None):
             super(Bottleneck, self).__init__()
             self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
             self.bn1 = nn.BatchNorm2d(planes)
             self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
                                    padding=1, bias=False)
             self.bn2 = nn.BatchNorm2d(planes)
             self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
             self.bn3 = nn.BatchNorm2d(planes * 4)
             self.relu = nn.ReLU(inplace=True)
             self.downsample = downsample
             self.stride = stride
     
         def forward(self, x):
             residual = 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)
     
             if self.downsample is not None:
                 residual = self.downsample(x)
     
             out += residual
             out = self.relu(out)
     
             return out
     

3. 最后是avgpool和一个全连接层，映射到1000维上（因为ImageNet有1000个类别）。

结构图和更多细节：

参考https://www.jianshu.com/p/085f4c8256f1

https://blog.csdn.net/weixin_40548136/article/details/88820996

resnet18

resnet50