densenet121实现图片大小为48×48×3四分类代码

以下是使用PyTorch实现densenet121进行48x48x3图像四分类的示例代码：

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision.transforms as transforms
from torch.utils.data import DataLoader
from torchvision.datasets import ImageFolder
from torchvision.models import densenet121

# 定义超参数
batch_size = 32
learning_rate = 0.001
num_epochs = 10

# 数据预处理
transform = transforms.Compose([
    transforms.Resize(48),
    transforms.CenterCrop(48),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])
])

# 加载数据集
train_dataset = ImageFolder(root="./train", transform=transform)
train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)

val_dataset = ImageFolder(root="./val", transform=transform)
val_loader = DataLoader(val_dataset, batch_size=batch_size, shuffle=False)

test_dataset = ImageFolder(root="./test", transform=transform)
test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False)

# 定义模型
model = densenet121(pretrained=True)
num_ftrs = model.classifier.in_features
model.classifier = nn.Linear(num_ftrs, 4)  # 四分类问题，输出节点数为4

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

# 训练模型
for epoch in range(num_epochs):
    model.train()
    for images, labels in train_loader:
        optimizer.zero_grad()
        outputs = model(images)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
    
    # 在验证集上测试模型性能
    model.eval()
    with torch.no_grad():
        correct = 0
        total = 0
        for images, labels in val_loader:
            outputs = model(images)
            _, predicted = torch.max(outputs.data, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
        val_acc = correct / total
        print("Epoch {}, Validation Accuracy: {:.2f}%".format(epoch+1, val_acc*100))

# 在测试集上测试模型性能
model.eval()
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()
    test_acc = correct / total
    print("Test Accuracy: {:.2f}%".format(test_acc*100))

在上述代码中，我们使用ImageFolder类从文件夹中加载图像数据集，并使用DataLoader类进行批量读取。我们使用预训练的densenet121模型，将其全连接层的输出节点数修改为4。使用交叉熵损失函数进行训练，使用Adam优化器进行参数更新。在每个epoch结束时，我们在验证集上测试模型性能，并输出验证集准确率。最后，在测试集上测试模型性能并输出测试集准确率。