pytorch中resnet_resnet18 50网络结构以及pytorch实现代码
1 resnet简介
关于resnet，网上有大量的文章讲解其原理和思路，简单来说，resnet巧妙地利用了shortcut连接，解决了深度网络中模型退化的问题。
2 论文中的结构如下
网络结构.png
2.1 参考pytorch中的实现，自己画了一个网络图,包含了每一层的参数和输出
resnet18&resnet50.jpg
PS：经评论区@字里行间_yan提醒，原始图片中部分描述有歧义，已更正。一般来说，特征图的尺寸变化应表述为上采样和下采样，通道数的变化才是升维和降维。
2020/4/17更新
本来自己随便写写，感觉看到这篇文章的人挺多，回来填坑
增加了pytorch中的代码解读。
修复了图中参数k的标识错误(1x1卷积 k=1)
新增SVG文件下载地址链接(虽然文件简单，下载后还请在本文点个赞鼓励下): 链接: 链接: https://pan.baidu.com/s/183ReRQMJXt2yUkhExnezBA 提取码: kmf2
3 pytorch中的resnet
3.1 代码文件
完整代码文件可在pytorch官方文档查到，地址https://pytorch.org/docs/stable/_modules/torchvision/models/resnet.html#resnet18
顺便说一句，torchvision里面实现了大部分经典的网络，分类分割检测都有，还包含了常用的一些数据库加载等，对于刚入门的同学来说会省很多事。
3.2 代码阅读
个人习惯从模型调用开始看，首先看调用
def _resnet(arch, block, layers, pretrained, progress, **kwargs):
model = ResNet(block, layers, **kwargs)
if pretrained:
state_dict = load_state_dict_from_url(model_urls[arch],
progress=progress)
model.load_state_dict(state_dict)
return model
def resnet50(pretrained=False, progress=True, **kwargs):
return _resnet('resnet50', Bottleneck, [3, 4, 6, 3], pretrained, progress,
**kwargs)
可以看到resnet至少需要两个显示的参数，分别是block和layers。这里的block就是论文里提到的resnet18和resnet50中应用的两种不同结构。layers就是网络层数，也就是每个block的个数，在前文图中也有体现。
然后看网络结构，代码略长，为了阅读体验就直接截取了重要部分以及在代码中注释,建议配合完整代码阅读。
class ResNet(nn.Module):
def __init__(self, block, layers, num_classes=1000, zero_init_residual=False,
groups=1, width_per_group=64, replace_stride_with_dilation=None,
norm_layer=None):
super(ResNet, self).__init__()
#参数比调用多几个，模型相较于最初发文章的时候有过更新
#block: basicblock或者bottleneck，后续会提到
#layers：每个block的个数，如resnet50， layers=[3,4,6,3]
#num_classes: 数据库类别数量
#zero_init_residual：其他论文中提到的一点小trick，残差参数为0
#groups：卷积层分组，应该是为了resnext扩展
#width_per_group：同上，此外还可以是wideresnet扩展
#replace_stride_with_dilation：空洞卷积，非原论文内容
#norm_layer：原论文用BN，此处设为可自定义
# 中间部分代码省略，只看模型搭建部分
self.layer1 = self._make_layer(block, 64, layers[0])
self.layer2 = self._make_layer(block, 128, layers[1], stride=2,
dilate=replace_stride_with_dilation[0])
self.layer3 = self._make_layer(block, 256, layers[2], stride=2,
dilate=replace_stride_with_dilation[1])
self.layer4 = self._make_layer(block, 512, layers[3], stride=2,
dilate=replace_stride_with_dilation[2])
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.fc = nn.Linear(512 * block.expansion, num_classes)
#中间部分代码省略
def _make_layer(self, block, planes, blocks, stride=1, dilate=False):
norm_layer = self._norm_layer
downsample = None
previous_dilation = self.dilation
if dilate:
self.dilation *= stride
stride = 1
if stride != 1 or self.inplanes != planes * block.expansion:
#当需要特征图需要降维或通道数不匹配的时候调用
downsample = nn.Sequential(
conv1x1(self.inplanes, planes * block.expansion, stride),
norm_layer(planes * block.expansion),
)
layers = []
#每一个self.layer的第一层需要调用downsample，所以单独写，跟下面range中的1 相对应
#block的定义看下文
layers.append(block(self.inplanes, planes, stride, downsample, self.groups,
self.base_width, previous_dilation, norm_layer))
self.inplanes = planes * block.expansion
for _ in range(1, blocks):
layers.append(block(self.inplanes, planes, groups=self.groups,
base_width=self.base_width, dilation=self.dilation,
norm_layer=norm_layer))
return nn.Sequential(*layers)
def _forward_impl(self, x):
#前向传播
# See note [TorchScript super()]
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
然后是论文中的block
def conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1):
"""3x3 convolution with padding"""
return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
padding=dilation, groups=groups, bias=False, dilation=dilation)
def conv1x1(in_planes, out_planes, stride=1):
"""1x1 convolution"""
return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)
#用在resnet18中的结构，也就是两个3x3卷积
class BasicBlock(nn.Module):
expansion = 1
__constants__ = ['downsample']
#inplanes：输入通道数
#planes：输出通道数
#base_width，dilation，norm_layer不在本文讨论范围
def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
base_width=64, dilation=1, norm_layer=None):
super(BasicBlock, self).__init__()
#中间部分省略
self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = norm_layer(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = norm_layer(planes)
self.downsample = downsample
self.stride = stride
def forward(self, x):
#为后续相加保存输入
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:
#遇到降尺寸或者升维的时候要保证能够相加
identity = self.downsample(x)
out += identity#论文中最核心的部分，resnet的简洁和优美的体现
out = self.relu(out)
return out
#bottleneck是应用在resnet50及其以上的结构，主要是1x1,3x3,1x1
class Bottleneck(nn.Module):
expansion = 4
__constants__ = ['downsample']
def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
base_width=64, dilation=1, norm_layer=None):
super(Bottleneck, self).__init__()
#中间省略
self.conv1 = conv1x1(inplanes, width)
self.bn1 = norm_layer(width)
self.conv2 = conv3x3(width, width, stride, groups, dilation)
self.bn2 = norm_layer(width)
self.conv3 = conv1x1(width, planes * self.expansion)
self.bn3 = norm_layer(planes * self.expansion)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
#同basicblock
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
我已经很熟悉resnet，不知道在哪些地方存在阅读问题，所以只在代码中把一些关键的地方注释了，代码可以跟我画的那个图结合起来看，更容易理解。
如有问题欢迎留言，我看到就会回复。