大家好，又见面了，我是你们的朋友全栈君。如果您正在找激活码,请点击查看最新教程,关注关注公众号 “全栈程序员社区” 获取激活教程,可能之前旧版本教程已经失效.最新Idea2022.1教程亲测有效,一键激活。

Jetbrains全系列IDE稳定放心使用

选取经典的早期Pytorch官方实现代码进行分析

https://github.com/pytorch/vision/blob/9a481d0bec2700763a799ff148fe2e083b575441/torchvision/models/resnet.py
各种ResNet网络是由BasicBlock或者bottleneck构成的，它们是构成深度残差网络的基本模块

ResNet主体

ResNet的大部分各种结构是1层conv+4个block+1层fc

class ResNet(nn.Module):
def __init__(self, block, layers, zero_init_residual=False):
super(ResNet, self).__init__()
self.inplanes = 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)
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
# Zero-initialize the last BN in each residual branch,
# so that the residual branch starts with zeros, and each residual block behaves like an identity.
# This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
if zero_init_residual:
for m in self.modules():
if isinstance(m, Bottleneck):
nn.init.constant_(m.bn3.weight, 0)
elif isinstance(m, BasicBlock):
nn.init.constant_(m.bn2.weight, 0)
def _make_layer(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
# normly happened when stride = 2
downsample = nn.Sequential(
conv1x1(self.inplanes, planes * block.expansion, stride),
nn.BatchNorm2d(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample))
self.inplanes = planes * block.expansion
for _ in range(1, blocks):  
# only the first block need downsample thus there is no downsample and stride = 2
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)
c2 = self.layer1(x)
c3 = self.layer2(c2)
c4 = self.layer3(c3)
c5 = self.layer4(c4)
x = self.avgpool(x)
x = x.view(x.size(0), -1)
x = self.fc(x)
return c5

需要注意的是最后的avgpool是全局的平均池化

BasicBlock

class BasicBlock(nn.Module):
expansion = 1
def __init__(self, inplanes, planes, stride=1, downsample=None):
# here planes names channel number
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):
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

ResNet18

对应的就是[2,2,2,2]

def resnet18(pretrained=False, **kwargs):
"""Constructs a ResNet-18 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet """
model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
if pretrained:
print('Loading the pretrained model ...')
# strict = False as we don't need fc layer params.
model.load_state_dict(model_zoo.load_url(model_urls['resnet18']), strict=False)
return model

ResNet34

def resnet34(pretrained=False, **kwargs):
"""Constructs a ResNet-34 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet """
model = ResNet(BasicBlock, [3, 4, 6, 3], **kwargs)
if pretrained:
print('Loading the pretrained model ...')
model.load_state_dict(model_zoo.load_url(model_urls['resnet34']), strict=False)
return model

ResNet20

这个需要强调一下,正常的ResNet20应该是文章中提出，针对cifar数据集设计的n=3时候, 1+6*3+1=20

class ResNet4Cifar(nn.Module):
def __init__(self, block, num_block, num_classes=10):
super().__init__()
self.in_channels = 16
self.conv1 = nn.Sequential(
nn.Conv2d(3, 16, kernel_size=3, padding=1, bias=False),
nn.BatchNorm2d(16),
nn.ReLU(inplace=True))
# we use a different inputsize than the original paper
# so conv2_x's stride is 1
self.conv2_x = self._make_layer(block, 16, num_block[0], 1)
self.conv3_x = self._make_layer(block, 32, num_block[1], 2)
self.conv4_x = self._make_layer(block, 64, num_block[2], 2)
self.avg_pool = nn.AdaptiveAvgPool2d((1, 1))
self.fc = nn.Linear(64 * block.expansion, num_classes)
def _make_layer(self, block, out_channels, num_blocks, stride):
strides = [stride] + [1] * (num_blocks - 1)
layers = []
for stride in strides:
layers.append(block(self.in_channels, out_channels, stride))
self.in_channels = out_channels * block.expansion
return nn.Sequential(*layers)
def forward(self, x):
output = self.conv1(x)
output = self.conv2_x(output)
output = self.conv3_x(output)
output = self.conv4_x(output)
output = self.avg_pool(output)
output = output.view(output.size(0), -1)
output = self.fc(output)
return output
def resnet20(num_classes=10, **kargs):
""" return a ResNet 20 object """
return ResNet4Cifar(BasicBlock, [3, 3, 3], num_classes=num_classes)

我们通过参数量的计算也为0.27M，和论文中的一致，对[1,3,32,32]的输入，输出维度为[1,64,8,8]

但是也有一些文章只换了开头三层的3×3卷积层，通道数并没有采用16、32、64，仍是4层的64、128、256、512
，这样下来参数量是11.25M。针对的任务不同，但是如果不关注原始网络结构，这一点可以忽略。

Bottleneck Block

Bottleneck Block中使用了1×1卷积层。如输入通道数为256，1×1卷积层会将通道数先降为64，经过3×3卷积层后，再将通道数升为256。1×1卷积层的优势是在更深的网络中，用较小的参数量处理通道数很大的输入。
这种结构用在ResNet50、ResNet101中。

class Bottleneck(nn.Module):
expansion = 4
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(Bottleneck, self).__init__()
self.conv1 = conv1x1(inplanes, planes)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = conv3x3(planes, planes, stride)
self.bn2 = nn.BatchNorm2d(planes)
self.conv3 = conv1x1(planes, planes * self.expansion)
self.bn3 = nn.BatchNorm2d(planes * self.expansion)
self.relu = nn.ReLU(inplace=True)
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)
out = self.relu(out)
out = self.conv3(out)
out = self.bn3(out)
if self.downsample is not None:
identity = self.downsample(x)
out += identity
out = self.relu(out)
return out

ResNet50

和以上的网络结构一样，把Bottleneck按层数堆起来就可以了

def resnet50(pretrained=False, **kwargs):
"""Constructs a ResNet-50 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet """
model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
if pretrained:
print('Loading the pretrained model ...')
model.load_state_dict(model_zoo.load_url(model_urls['resnet50']), strict=False)
return model

ResNet到底解决了什么问题

推荐看知乎问题Resnet到底在解决一个什么问题呢？
贴一些我比较喜欢的回答：

A. 对于$L$层的网络来说，没有残差表示的Plain Net梯度相关性的衰减在$\frac{1}{2^L}$ ，而ResNet的衰减却只有$\frac{1}{\sqrt{L}}$ 。即使BN过后梯度的模稳定在了正常范围内，但梯度的相关性实际上是随着层数增加持续衰减的。而经过证明，ResNet可以有效减少这种相关性的衰减。

B. 对于“梯度弥散”观点来说，在输出引入一个输入x的恒等映射，则梯度也会对应地引入一个常数1，这样的网络的确不容易出现梯度值异常，在某种意义上，起到了稳定梯度的作用。

C. 跳连接相加可以实现不同分辨率特征的组合，因为浅层容易有高分辨率但是低级语义的特征，而深层的特征有高级语义，但分辨率就很低了。引入跳接实际上让模型自身有了更加“灵活”的结构，即在训练过程本身，模型可以选择在每一个部分是“更多进行卷积与非线性变换”还是“更多倾向于什么都不做”，抑或是将两者结合。模型在训练便可以自适应本身的结构。³

D. 当使用了残差网络时,就是加入了skip connection 结构,这时候由一个building block 的任务由: F(x) := H(x)，变成了F(x) := H(x)-x对比这两个待拟合的函数, 拟合残差图更容易优化,也就是说:F(x) := H(x)-x比F(x) := H(x)更容易优化⁴. 举了一个差分放大器的例子：F是求和前网络映射，H是从输入到求和后的网络映射。比如把5映射到5.1，那么引入残差前是F’(5)=5.1，引入残差后是H(5)=5.1, H(5)=F(5)+5, F(5)=0.1。这里的F’和F都表示网络参数映射，引入残差后的映射对输出的变化更敏感。比如s输出从5.1变到5.2，映射F’的输出增加了1/51=2%，而对于残差结构输出从5.1到5.2，映射F是从0.1到0.2，增加了100%。明显后者输出变化对权重的调整作用更大，所以效果更好。残差的思想都是去掉相同的主体部分，从而突出微小的变化。

说法众多，好用就完事儿了嗷~