用pytorch做CNN的新冠肺炎患者图像分类代码

在PyTorch中，做新冠病毒（COVID-19）患者图像分类通常涉及到深度学习，特别是卷积神经网络（Convolutional Neural Networks，简称CNN）。以下是一个基本的步骤概述：

# 首先，确保安装了必要的库
import torch
import torchvision
import torchvision.transforms as transforms

# 数据预处理
data_transforms = {
    'train': transforms.Compose([
        transforms.Resize((224, 224)),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize([0.5], [0.5])
    ]),
    'val': transforms.Compose([
        transforms.Resize((224, 224)),
        transforms.ToTensor(),
        transforms.Normalize([0.5], [0.5])
    ])
}

# 加载数据集，例如从Covid Chest X-ray dataset
train_dataset = torchvision.datasets.CxrDataset(
    root='./data', train=True, transform=data_transforms['train'])
val_dataset = torchvision.datasets.CxrDataset(
    root='./data', train=False, transform=data_transforms['val'])

# 创建数据加载器
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=32, shuffle=True)
val_loader = torch.utils.data.DataLoader(val_dataset, batch_size=32)

# 定义CNN模型，如ResNet、VGG等
import torchvision.models as models
model = models.resnet18(pretrained=True)  # 使用预训练的模型作为基础
num_classes = len(train_dataset.classes)  # 确定类别数
model.fc = torch.nn.Linear(model.fc.in_features, num_classes)  # 修改最后一层为分类层

# 损失函数和优化器
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)

# 训练过程
for epoch in range(num_epochs):
    for inputs, labels in train_loader:
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        optimizer.zero_grad()  # 清零梯度
        loss.backward()  # 反向传播
        optimizer.step()  # 更新参数

# 测试模型
model.eval()  # 转换到评估模式
with torch.no_grad():
    correct = 0
    total = 0
    for inputs, labels in val_loader:
        outputs = model(inputs)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print(f"验证集准确率: {correct / total * 100:.2f}%")

#