利用Pytorch实现ResNet网络构建及模型训练

class ResNet(nn.Module):
    def __init__(self, num_classes=1000):
        super().__init__()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace
（续）
即模型需要在输入层加入一些 normalization 和激活层。
```python
import torch.nn.init as init
class Flatten(nn.Module):
    def __init__(self):
        super().__init__()
    def forward(self, x):
        return x.view(x.size(0), -1)
class ResNet(nn.Module):
    def __init__(self, num_classes=1000):
        super().__init__()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.layer1 = nn.Sequential(
            ResidualBlock(64, 256, stride=1),
            *[ResidualBlock(256, 256) for _ in range(1, 3)]
        )
        self.layer2 = nn.Sequential(
            ResidualBlock(256, 512, stride=2),
            *[ResidualBlock(512, 512) for _ in range(1, 4)]
        )
        self.layer3 = nn.Sequential(
            ResidualBlock(512, 1024, stride=2),
            *[ResidualBlock(1024, 1024) for _ in range(1, 6)]
        )
        self.layer4 = nn.Sequential(
            ResidualBlock(1024, 2048, stride=2),
            *[ResidualBlock(2048, 2048) for _ in range(1, 3)]
        )
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.flatten = Flatten()
        self.fc = nn.Linear(2048, num_classes)
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                init.kaiming_normal_(m.weight, mode="fan_out", nonlinearity="relu")
            elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
                init.constant_(m.weight, 1)
                init.constant_(m.bias, 0)
    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        x = self.avgpool(x)
        x = self.flatten(x)
        x = self.fc(x)
        return x

import torch.optim as optim
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = ResNet(num_classes=1000).to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

def train(model, optimizer, criterion, train_loader, device):
    model.train()
    train_loss = 0
    correct = 0
    total = 0
    for batch_idx, (inputs, targets) in enumerate(train_loader):
        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()
    acc = 100 * correct / total
    avg_loss = train_loss / len(train_loader)
    return acc, avg_loss