pytorch残差神经网络项目实战

以下是使用PyTorch实现残差神经网络的项目实战步骤：

1.导入必要的库和模块

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms

2.定义残差块

class ResidualBlock(nn.Module):
    def __init__(self, in_channels, out_channels, stride=1):
        super(ResidualBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(out_channels)
        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.stride != 1 or identity.shape[1] != out.shape[1]:
            identity = nn.Conv2d(identity.shape[1], out.shape[1], kernel_size=1, stride=self.stride, bias=False)(identity)
            identity = nn.BatchNorm2d(out.shape[1])(identity)

        out += identity
        out = self.relu(out)

        return out

3.定义残差神经网络

class ResNet(nn.Module):
    def __init__(self, block, layers, num_classes=10):
        super(ResNet, self).__init__()
        self.in_channels = 64

        self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)

        self.layer1 = self.make_layer(block, 64, layers[0], stride=1)
        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.avg_pool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(512, num_classes)

    def make_layer(self, block, out_channels, blocks, stride=1):
        layers = []
        layers.append(block(self.in_channels, out_channels, stride))
        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.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.layer1(out)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.layer4(out)

        out = self.avg_pool(out)
        out = out.view(out.size(0), -1)
        out = self.fc(out)

        return out

4.实例化残差神经网络并定义损失函数和优化器

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

model = ResNet(ResidualBlock, [2, 2, 2, 2]).to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.1, momentum=0.9, weight_decay=5e-4)

5.加载数据集并进行数据增强

transform_train = transforms.Compose([
    transforms.RandomCrop(32, padding=4),
    transforms.RandomHorizontalFlip(),
    transforms.ToTensor(),
    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))
])

transform_test = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))
])

trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform_train)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=128, shuffle=True, num_workers=2)

testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform_test)
testloader = torch.utils.data.DataLoader(testset, batch_size=100, shuffle=False, num_workers=2)

6.训练模型

def train(model, device, trainloader, criterion, optimizer, epoch):
    model.train()
    train_loss = 0
    correct = 0
    total = 0

    for batch_idx, (inputs, targets) in enumerate(trainloader):
        inputs, targets = inputs.to(device), targets.to(device)
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, targets)
        loss.backward()
        optimizer.step()

        train_loss += loss.item()
        _, predicted = outputs.max(1)
        total += targets.size(0)
        correct += predicted.eq(targets).sum().item()

    print('Train Epoch: {} | Loss: {:.3f} | Acc: {:.3f}% ({}/{})'.format(
        epoch, train_loss/(batch_idx+1), 100.*correct/total, correct, total))

def test(model, device, testloader, criterion, epoch):
    model.eval()
    test_loss = 0
    correct = 0
    total = 0

    with torch.no_grad():
        for batch_idx, (inputs, targets) in enumerate(testloader):
            inputs, targets = inputs.to(device), targets.to(device)
            outputs = model(inputs)
            loss = criterion(outputs, targets)

            test_loss += loss.item()
            _, predicted = outputs.max(1)
            total += targets.size(0)
            correct += predicted.eq(targets).sum().item()

    print('Test Epoch: {} | Loss: {:.3f} | Acc: {:.3f}% ({}/{})'.format(
        epoch, test_loss/(batch_idx+1), 100.*correct/total, correct, total))

for epoch in range(1, 201):
    train(model, device, trainloader, criterion, optimizer, epoch)
    test(model, device, testloader, criterion, epoch)