pytorch Resnet 网络结构

最近在学习廖老师的pytorch教程，学到Resnet 这部分着实的烧脑，这个模型都捣鼓了好长时间才弄懂，附上我学习过程中最为不解的网络的具体结构连接（网上一直没有找到对应网络结构，对与一个自学的学渣般的我，很是无奈，所以搞懂后我就...分享给有需要的的你了）

我们先大致了解一下残差模型

ResNet在2015年被提出，在ImageNet比赛classification任务上获得第一名，因为它“简单与实用”并存，之后很多方法都建立在ResNet50或者ResNet101的基础上完成的，检测，分割，识别等领域都纷纷使用ResNet，Alpha zero也使用了ResNet，所以可见ResNet确实很好用。
下面我们从实用的角度去看看ResNet。

1.ResNet意义

随着网络的加深，出现了训练集准确率下降的现象，我们可以确定这不是由于Overfit过拟合造成的(过拟合的情况训练集应该准确率很高)；所以作者针对这个问题提出了一种全新的网络，叫深度残差网络，它允许网络尽可能的加深，其中引入了全新的结构如图1；
这里问大家一个问题
残差指的是什么？
其中ResNet提出了两种mapping：一种是identity mapping，指的就是图1中”弯弯的曲线”，另一种residual mapping，指的就是除了”弯弯的曲线“那部分，所以最后的输出是 y=F(x)+x

identity mapping顾名思义，就是指本身，也就是公式中的x，而residual mapping指的是“差”，也就是y−x，所以残差指的就是F(x)部分。

我们可以看到一个“弯弯的弧线“这个就是所谓的”shortcut connection“，也是文中提到identity mapping，这张图也诠释了ResNet的真谛,当然残差的结构可不会像图中这样单一，

下面是对通过Resnet 对cafir10数据的训练代码以及网络结构图

import torch
import torch.nn as nn
import torchvision.datasets as normal_datasets
import torchvision.transforms as transforms
from torch.autograd import Variable

num_epochs = 2
lr = 0.001


def get_variable(x):
    x = Variable(x)
    return x.cuda() if torch.cuda.is_available() else x


# 图像预处理
transform = transforms.Compose([
    transforms.Scale(40),
    transforms.RandomHorizontalFlip(),
    transforms.RandomCrop(32),
    transforms.ToTensor()])

# 加载CIFAR-10
train_dataset = normal_datasets.CIFAR10(root='./data/',
                                        train=True,
                                        transform=transform,
                                        download=False)

test_dataset = normal_datasets.CIFAR10(root='./data/',
                                       train=False,
                                       transform=transforms.ToTensor())

train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                                           batch_size=100,
                                           shuffle=True)

test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                                          batch_size=100,
                                          shuffle=False)


# 3x3 卷积
def conv3x3(in_channels, out_channels, stride=1):
    return nn.Conv2d(in_channels, out_channels, kernel_size=3,
                     stride=stride, padding=1, bias=False)


# Residual Block
class ResidualBlock(nn.Module):
    def __init__(self, in_channels, out_channels, stride=1, downsample=None):
        
        super(ResidualBlock, self).__init__()
        self.conv1 = conv3x3(in_channels, out_channels, stride)
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(out_channels, out_channels)
        self.bn2 = nn.BatchNorm2d(out_channels)
        self.downsample = downsample

    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:
            residual = self.downsample(x)
        out += residual
        out = self.relu(out)
        return out



class ResNet(nn.Module):
    
    def __init__(self, block, layers, num_classes=10):
        super(ResNet, self).__init__()
        self.in_channels = 16
        self.conv = conv3x3(3, 16)
        self.bn = nn.BatchNorm2d(16)
        self.relu = nn.ReLU(inplace=True)
        self.layer1 = self.make_layer(block, 16, layers[0])
        self.layer2 = self.make_layer(block, 32, layers[0], 2)
        self.layer3 = self.make_layer(block, 64, layers[1], 2)
       
        self.avg_pool = nn.AvgPool2d(8)
        self.fc = nn.Linear(64, num_classes)
        
    def make_layer(self, block, out_channels, blocks, stride=1,mm=0):
        #print(out_channels,blocks,'****')
        downsample = None
        if (stride != 1) or (self.in_channels != out_channels):
            downsample = nn.Sequential(
                conv3x3(self.in_channels, out_channels, stride=stride),
                nn.BatchNorm2d(out_channels))
            
            
        layers = []
        layers.append(block(self.in_channels, out_channels, stride, downsample))
        mm+=1
        
        self.in_channels = out_channels
        for i in range(1, blocks):
            
            layers.append(block(out_channels, out_channels))
        return nn.Sequential(*layers)

    def forward(self, x):
        out = self.conv(x)
        out = self.bn(out)
        out = self.relu(out)
        out = self.layer1(out)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.avg_pool(out)
        out = out.view(out.size(0), -1)
        out = self.fc(out)
        return out


resnet = ResNet(ResidualBlock, [2,2 ,2,2])  #blocks 
print(resnet)
if torch.cuda.is_available():
    resnet = resnet.cuda()

loss_func = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(resnet.parameters(), lr=lr)

# 训练
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = get_variable(images)
        labels = get_variable(labels)

        outputs = resnet(images)
        loss = loss_func(outputs, labels)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if (i + 1) % 100 == 0:
            print("Epoch [%d/%d], Iter [%d/%d] Loss: %.4f" % (epoch + 1, num_epochs, i + 1, 500, loss.data[0]))

    # 衰减学习率
    if (epoch + 1) % 20 == 0:
        lr /= 3
        optimizer = torch.optim.Adam(resnet.parameters(), lr=lr)

# 测试
correct = 0
total = 0
for images, labels in test_loader:
    images = get_variable(images)
    labels = get_variable(labels)
    outputs = resnet(images)
    _, predicted = torch.max(outputs.data, 1)
    total += labels.size(0)
    correct += (predicted == labels.data).sum()

print(' 测试 准确率: %d %%' % (100 * correct / total))

# 保存模型参数
torch.save(resnet.state_dict(), 'resnet.pkl')

网络结构

ResNet(
  (conv): Conv2d(3, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  (bn): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (relu): ReLU(inplace)
  (layer1): Sequential(
    (0): ResidualBlock(
      (conv1): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (conv2): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (1): ResidualBlock(
      (conv1): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (conv2): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
  )
  (layer2): Sequential(
    (0): ResidualBlock(
      (conv1): Conv2d(16, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (conv2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (downsample): Sequential(
        (0): Conv2d(16, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (1): ResidualBlock(
      (conv1): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (conv2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
  )
  (layer3): Sequential(
    (0): ResidualBlock(
      (conv1): Conv2d(32, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (downsample): Sequential(
        (0): Conv2d(32, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (1): ResidualBlock(
      (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
  )
  (avg_pool): AvgPool2d(kernel_size=8, stride=8, padding=0)
  (fc): Linear(in_features=64, out_features=10, bias=True)
)

网络结构的图