1. ResNet block

ResNet block有两个convolution和一个short cut层，如下图：

代码：

class ResBlk(nn.Module):def __init__(self, ch_in, ch_out, stride):super(ResBlk, self).__init__()self.conv1 = nn.Conv2d(ch_in, ch_out, kernel_size=3, stride=stride, padding=1)self.bn1 = nn.BatchNorm2d(ch_out)self.conv2 = nn.Conv2d(ch_out, ch_out, kernel_size=3, stride=1, padding=1)self. bn2 = nn.BatchNorm2d(ch_out)self.extra = nn.Sequential()if ch_in != ch_out:self.extra = nn.Sequential(nn.Conv2d(ch_in, ch_out, kernel_size=1, stride=stride),nn.BatchNorm2d(ch_out))def forward(self, x):out = F.relu(self.bn1(self.conv1(x)))out = self.bn2(self.conv2(out))out = self.extra(x) + outout = F.relu(out)return out

2. ResNet18网络结构

从上图可以看出，resnet18有1个卷积层，4个残差层和1一个线性输出层，其中每个残差层有2个resnet块，每个块有2个卷积层。
对于cifar10数据来说，输入层[b, 64, 32,32]，输出是10分类
代码：

class ResNet(nn.Module):def __init__(self, block, num_blocks, num_classes=1000):super(ResNet, self).__init__()self.in_planes = 64# 初始卷积层self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)self.bn1 = nn.BatchNorm2d(64)# 四个残差层self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)# 全连接层self.linear = nn.Linear(512 * block.expansion, num_classes)# 创建一个残差层def _make_layer(self, block, planes, num_blocks, stride):strides = [stride] + [1] * (num_blocks - 1)layers = []for stride in strides:layers.append(block(self.in_planes, planes, stride))self.in_planes = planes * block.expansionreturn nn.Sequential(*layers)def forward(self, x):out = F.relu(self.bn1(self.conv1(x)))out = F.max_pool2d(out, kernel_size=3, stride=2, padding=1)out = self.layer1(out)out = self.layer2(out)out = self.layer3(out)out = self.layer4(out)#out = F.avg_pool2d(out, 4)out = F.adaptive_avg_pool2d(out, [1, 1])out = out.view(out.size(0), -1)out = self.linear(out)return out

3. 完整代码

3.1 网络代码

import torch
from torch import nn
from torch.nn import functional as Fclass ResBlk(nn.Module):expansion = 1def __init__(self, ch_in, ch_out, stride):super(ResBlk, self).__init__()self.conv1 = nn.Conv2d(ch_in, ch_out, kernel_size=3, stride=stride, padding=1)self.bn1 = nn.BatchNorm2d(ch_out)self.conv2 = nn.Conv2d(ch_out, ch_out, kernel_size=3, stride=1, padding=1)self.bn2 = nn.BatchNorm2d(ch_out)self.extra = nn.Sequential()if ch_in != ch_out:self.extra = nn.Sequential(nn.Conv2d(ch_in, ch_out, kernel_size=1, stride=stride),nn.BatchNorm2d(ch_out))def forward(self, x):out = F.relu(self.bn1(self.conv1(x)))out = self.bn2(self.conv2(out))out = self.extra(x) + outout = F.relu(out)return outclass ResNet(nn.Module):def __init__(self, block, num_blocks, num_classes=1000):super(ResNet, self).__init__()self.in_planes = 64# 初始卷积层self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)self.bn1 = nn.BatchNorm2d(64)# 四个残差层self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)# 全连接层self.linear = nn.Linear(512 * block.expansion, num_classes)# 创建一个残差层def _make_layer(self, block, planes, num_blocks, stride):strides = [stride] + [1] * (num_blocks - 1)layers = []for stride in strides:layers.append(block(self.in_planes, planes, stride))self.in_planes = planes * block.expansionreturn nn.Sequential(*layers)def forward(self, x):out = F.relu(self.bn1(self.conv1(x)))out = F.max_pool2d(out, kernel_size=3, stride=2, padding=1)out = self.layer1(out)out = self.layer2(out)out = self.layer3(out)out = self.layer4(out)#out = F.avg_pool2d(out, 4)out = F.adaptive_avg_pool2d(out, [1, 1])out = out.view(out.size(0), -1)out = self.linear(out)return outdef ResNet18():return ResNet(ResBlk, [2, 2, 2, 2], 10)if __name__ == '__main__':model = ResNet18()print(model)

3.2 训练代码

import torch
from torchvision import datasets
from torch.utils.data import DataLoader
from torchvision import transforms
from torch import nn, optim
import syssys.path.append('.')
#from Lenet5 import Lenet5
from resnet import ResNet18def main():batchz = 128cifar_train = datasets.CIFAR10('cifa', True, transform=transforms.Compose([transforms.Resize((32, 32)),transforms.ToTensor(),transforms.Normalize(mean=[0.485, 0.456, 0.406],std=[0.229, 0.224, 0.225])]), download=True)cifar_train = DataLoader(cifar_train, batch_size=batchz, shuffle=True)cifar_test = datasets.CIFAR10('cifa', False, transform=transforms.Compose([transforms.Resize((32, 32)),transforms.ToTensor(),transforms.Normalize(mean=[0.485, 0.456, 0.406],std=[0.229, 0.224, 0.225])]), download=True)cifar_test = DataLoader(cifar_test, batch_size=batchz, shuffle=True)device = torch.device('cuda')#model = Lenet5().to(device)model = ResNet18().to(device)crition = nn.CrossEntropyLoss().to(device)optimizer = optim.Adam(model.parameters(), lr=1e-3)for epoch in range(1000):model.train()for batch, (x, label) in enumerate(cifar_train):x, label = x.to(device), label.to(device)logits = model(x)loss = crition(logits, label)optimizer.zero_grad()loss.backward()optimizer.step()# testmodel.eval()with torch.no_grad():total_correct = 0total_num = 0for x, label in cifar_test:x, label = x.to(device), label.to(device)logits = model(x)pred = logits.argmax(dim=1)correct = torch.eq(pred, label).float().sum().item()total_correct += correcttotal_num += x.size(0)acc = total_correct / total_numprint(epoch, 'test acc:', acc)if __name__ == '__main__':main()