实现了残差网络，残差网络结构。代码比之前复杂很多

conv3x3：将输入数据进行一次卷积，将数据转换成为，残差块需要的shape大小

ResidualBlock：残差块，也是所谓的恒等块。为什么被称为恒等块，大概可以理解为经过几层卷积过后大小形状不变，并且能和输入相加；如果形状变了，那么输入也会利用一次卷积得到和残差块输出大小相同的数据块。

       可以看到在残差块中有一个判断，就是判断输入数据是否被向下采样，也就是形状是否变化，如果变化就进行上述处理。

ResNet：构建一个完整的残差网络。传入参数是一个残差块的结构，还有每一层中残差块的个数元组。重点看以下其中的层次结构。

       conv3x3：将输入图片变成16通道

       输入通道数：16

       layer1：输入通道：16，输出通道：16，padding = 0，stride = 0

       layer2：输入通道：16，输出通道：32，padding = 0， stride = 2。由于输入不等于输出通道数，增加了一层卷积层，并且带有对应的stride。

       layer3：输入通道：32，输出通道：64，其余同上

       pooling：均值池化

       fc：全连接

       update_lr：在每个epoch之后实现对learning_rate的下降

       同样由于加入了batchnorm层，测试时需要使用model.eval()

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)
)

代码如下 ：

import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms# Device configuration
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')# Hyper-parameters
num_epochs = 80
learning_rate = 0.001# Image preprocessing modules
transform = transforms.Compose([transforms.Pad(4),transforms.RandomHorizontalFlip(),transforms.RandomCrop(32),transforms.ToTensor()])# CIFAR-10 dataset
train_dataset = torchvision.datasets.CIFAR10(root='../../data/',train=True, transform=transform,download=True)test_dataset = torchvision.datasets.CIFAR10(root='../../data/',train=False, transform=transforms.ToTensor())# Data loader
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 convolution
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 = downsampledef forward(self, x):residual = xout = 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 += residualout = self.relu(out)return out# ResNet
class ResNet(nn.Module):def __init__(self, block, layers, num_classes=10):super(ResNet, self).__init__()self.in_channels = 16self.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[1], 2)self.layer3 = self.make_layer(block, 64, layers[2], 2)self.avg_pool = nn.AvgPool2d(8)self.fc = nn.Linear(64, num_classes)def make_layer(self, block, out_channels, blocks, stride=1):downsample = Noneif (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))self.in_channels = out_channelsfor 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 outmodel = ResNet(ResidualBlock, [2, 2, 2]).to(device)# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)# For updating learning rate
def update_lr(optimizer, lr):    for param_group in optimizer.param_groups:param_group['lr'] = lr# Train the model
total_step = len(train_loader)
curr_lr = learning_rate
for epoch in range(num_epochs):for i, (images, labels) in enumerate(train_loader):images = images.to(device)labels = labels.to(device)# Forward passoutputs = model(images)loss = criterion(outputs, labels)# Backward and optimizeoptimizer.zero_grad()loss.backward()optimizer.step()if (i+1) % 100 == 0:print ("Epoch [{}/{}], Step [{}/{}] Loss: {:.4f}".format(epoch+1, num_epochs, i+1, total_step, loss.item()))# Decay learning rateif (epoch+1) % 20 == 0:curr_lr /= 3update_lr(optimizer, curr_lr)# Test the model
model.eval()
with torch.no_grad():correct = 0total = 0for images, labels in test_loader:images = images.to(device)labels = labels.to(device)outputs = model(images)_, predicted = torch.max(outputs.data, 1)total += labels.size(0)correct += (predicted == labels).sum().item()print('Accuracy of the model on the test images: {} %'.format(100 * correct / total))# Save the model checkpoint
torch.save(model.state_dict(), 'resnet.ckpt')