ResNet实现

class ResNet(nn.Module):

    def __init__(self, block, layers, num_classes=1000):
        super(ResNet, self).__init__()
        self.in_channels = 64
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        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.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(512 * block.expansion, num_classes)

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

        layers = []
        layers.append(block(self.in_channels, out_channels, stride, downsample))
        self.in_channels = out_channels * block.expansion
        for _ in range(1, blocks):
            layers.append(block(self.in_channels, out_channels))
            self.in_channels = out_channels * block.expansion
        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 = torch.flatten(x, 1)
        x = self.fc(x)

        return x

# 创建不同深度的 ResNet 模型
def resnet18(num_classes=1000):
    return ResNet(BasicBlock, [2, 2, 2, 2], num_classes)

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

def resnet50(num_classes=1000):
    return ResNet(Bottleneck, [3, 4, 6, 3], num_classes)

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

def resnet152(num_classes=1000):
    return ResNet(Bottleneck, [3, 8, 36, 3], num_classes)

ResNet(BasicBlock, [2, 2, 2, 2], num_classes)：

BasicBlock是一个pytorch自带的实现残差块得一个类具体源码之后再说， [2, 2, 2, 2]这个意思是有4个残差层，每一层有2个残差块。这个残差块是什么有什么作用，看了这个BasicBlock源码之后就知道了。num_classes是分类得类型有多少以上是把resnet网络用在了图像分类。

看ResNet初始化方法：

self.in_channels = 64

这个东西定义了进入第一个残差层的时候这输入通道是多少。

self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)

这就是一个简单的提取特征。

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)

这里定义了4层残差层。

_make_layer(block, 256, layers[2], stride=2)这个方法block是ResNet(BasicBlock, [2, 2, 2, 2], num_classes）这个方法中传递的BasicBlock用于构造一个残差块。

这个方法具体内容：

downsample = None
if stride != 1 or self.in_channels != out_channels * block.expansion:
    downsample = nn.Sequential(
        nn.Conv2d(self.in_channels, out_channels * block.expansion,
                  kernel_size=1, stride=stride, bias=False),
        nn.BatchNorm2d(out_channels * block.expansion),
    )

layers = []
layers.append(block(self.in_channels, out_channels, stride, downsample))
self.in_channels = out_channels * block.expansion
for _ in range(1, blocks):
    layers.append(block(self.in_channels, out_channels))
return nn.Sequential(*layers)

downsample = None，这个downsample是一个网络结构这个是用于输入残差块的维度和所需要的维度不相同的时候进行转换把输入维度转化为需要维度。stride != 1 or self.in_channels != out_channels * block.expansion 这个if条件第一个stride==1为什么stride一定要等于1，确保这个经过一个残差块进入下一个残差块的时候不改变这个输入特征图的大小，这个大小改变会改变这个特征图会丢失一些信息为了不丢失信息。如果stride>1会导致得到的特征图大小发生变化。 self.in_channels这个是固定的在resnet初始化函数中写好的

self.in_channels = 64，这个代表的是输入残差快的输入通道大小。out_channels * block.expansion这个是残差块的输出大小。确保残差块输入维度等于需要维度。

layers = []
layers.append(block(self.in_channels, out_channels, stride, downsample))
self.in_channels = out_channels * block.expansion

这里layers是一个数组里面有残差块，这里单独把第一个残差块拿出来是因为要更改这个self.in_channels把下一个残差块的输入改成第一个残差块的输出self.in_channels = out_channels * block.expansionnn.Sequential(*layers)最后返回一个残差层。

import torch.nn as nn

class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, in_channels, out_channels, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(out_channels)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        identity = 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:
            identity = self.downsample(x)

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

        return out

上述代码是BasicBlack源码，

identity = x这个就是定义上一个块或者层输出的特征图。

out += identity这个确保了经过上述卷积层提取特征之后这个效果不会比没有经过这些层的效果差。

这就是f(x) = F(x)+x

结束