ResNet代码详解与具体实现

现在在搞一个项目，想将目前模型架构中的vgg换成resnet网络，所以写了这篇文章。代码都是官网的代码，只是对内容进行了解释。

 1.BasicBlock类中的init()函数是先定义网络架构，forward()的函数是前向传播，实现的功能就是残差块，

import torch.nn as nn
import math
import torch.utils.model_zoo as model_zoo

# 这个文件内包括6中不同的网络架构
__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
           'resnet152']

# 每一种架构下都有训练好的可以用的参数文件
model_urls = {
    'resnet18': 'https://s3.amazonaws.com/pytorch/models/resnet18-5c106cde.pth',
    'resnet34': 'https://s3.amazonaws.com/pytorch/models/resnet34-333f7ec4.pth',
    'resnet50': 'https://s3.amazonaws.com/pytorch/models/resnet50-19c8e357.pth',
    'resnet101': 'https://s3.amazonaws.com/pytorch/models/resnet101-5d3b4d8f.pth',
    'resnet152': 'https://s3.amazonaws.com/pytorch/models/resnet152-b121ed2d.pth',
}

# 常见的3x3卷积
def conv3x3(in_planes, out_planes, stride=1):
    "3x3 convolution with padding"
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
                     padding=1, bias=False)

# 这是残差网络中的basicblock，实现的功能如下方解释：
class BasicBlock(nn.Module):
    expansion = 1
    def __init__(self, inplanes, planes, stride=1, downsample=None):    # inplanes代表输入通道数，planes代表输出通道数。
        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

2.Bottleneck类是另一种blcok类型，同上，init()函数是预定义网络架构，forward函数是进行前向传播。该block中有三个卷积，分别是1x1,3x3,1x1，分别完成的功能就是维度压缩，卷积，恢复维度！故bottleneck实现的功能就是对通道数进行压缩，再放大。注意：这里的plane不再是输出的通道数，输出通道数应该就是plane*expansion，即4*plane。

class Bottleneck(nn.Module):
    expansion = 4      # 输出通道数的倍乘

    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

这两个class讲清楚的话，后面的网络主体架构就还蛮好理解的了，6中架构之间的不同在于basicblock和bottlenek之间的不同以及block的输入参数的不同。因为ResNet一般有4个stack，每一个stack里面都是block的堆叠，所以[3, 4, 6, 3]就是每一个stack里面堆叠block的个数，故而造就了不同深度的ResNet。

resnet18： ResNet(BasicBlock, [2, 2, 2, 2])

resnet34： ResNet(BasicBlock, [3, 4, 6, 3])

resnet50：ResNet(Bottleneck, [3, 4, 6, 3])

resnet101:ResNet(Bottleneck, [3, 4, 23, 3])

resnet152:ResNet(Bottleneck, [3, 8, 36, 3])

def resnet18(pretrained=False):
    """Constructs a ResNet-18 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(BasicBlock, [2, 2, 2, 2])
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet18']))
    return model


def resnet34(pretrained=False):
    """Constructs a ResNet-34 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(BasicBlock, [3, 4, 6, 3])
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet34']))
    return model


def resnet50(pretrained=False):
    """Constructs a ResNet-50 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(Bottleneck, [3, 4, 6, 3])
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet50']))
    return model


def resnet101(pretrained=False):
    """Constructs a ResNet-101 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(Bottleneck, [3, 4, 23, 3])
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet101']))
    return model


def resnet152(pretrained=False):
    """Constructs a ResNet-152 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(Bottleneck, [3, 8, 36, 3])
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet152']))
    return model

最后的ResNet类其实可以根据列表大小来构建不同深度的resnet网络架构。resnet一共有5个阶段，第一阶段是一个7x7的卷积，stride=2，然后再经过池化层，得到的特征图大小变为原图的1/4。_make_layer()函数用来产生4个layer，可以根据输入的layers列表来创建网络。

class ResNet(nn.Module):
    def __init__(self, block, layers, num_classes=1000):  # layers=参数列表 block选择不同的类
        self.inplanes = 64 
        super(ResNet, self).__init__()
        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.AvgPool2d(7)
        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)) # 每个blocks的第一个residual结构保存在layers列表中。
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes))   #该部分是将每个blocks的剩下residual 结构保存在layers列表中，这样就完成了一个blocks的构造。

        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)   # 将输出结果展成一行
        x = self.fc(x)

        return x