pytorch训练vgg十分类任务的代码
时间: 2023-09-21 19:06:23 浏览: 42
好的,下面是一个简单的 PyTorch 训练 VGG-16 进行十分类任务的代码:
```python
import torch
import torch.nn as nn
import torch.optim as optim
import torchvision.datasets as datasets
import torchvision.transforms as transforms
import torchvision.models as models
# 定义模型
model = models.vgg16(pretrained=True)
num_features = model.classifier[6].in_features
features = list(model.classifier.children())[:-1] # Remove last layer
features.extend([nn.Linear(num_features, 10)]) # Add our layer with 10 outputs
model.classifier = nn.Sequential(*features) # Replace the model classifier
# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9)
# 加载数据集并进行数据增强
transform_train = transforms.Compose([
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
])
transform_val = transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
])
train_dataset = datasets.CIFAR10(root='./data', train=True, download=True, transform=transform_train)
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=32, shuffle=True, num_workers=4)
val_dataset = datasets.CIFAR10(root='./data', train=False, download=True, transform=transform_val)
val_loader = torch.utils.data.DataLoader(val_dataset, batch_size=32, shuffle=False, num_workers=4)
# 训练模型
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)
num_epochs = 10
for epoch in range(num_epochs):
train_loss = 0.0
train_correct = 0.0
model.train()
for images, labels in train_loader:
images = images.to(device)
labels = labels.to(device)
optimizer.zero_grad()
outputs = model(images)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
train_loss += loss.item() * images.size(0)
_, predicted = torch.max(outputs.data, 1)
train_correct += (predicted == labels).sum().item()
train_loss /= len(train_loader.dataset)
train_accuracy = 100.0 * train_correct / len(train_loader.dataset)
val_loss = 0.0
val_correct = 0.0
model.eval()
with torch.no_grad():
for images, labels in val_loader:
images = images.to(device)
labels = labels.to(device)
outputs = model(images)
loss = criterion(outputs, labels)
val_loss += loss.item() * images.size(0)
_, predicted = torch.max(outputs.data, 1)
val_correct += (predicted == labels).sum().item()
val_loss /= len(val_loader.dataset)
val_accuracy = 100.0 * val_correct / len(val_loader.dataset)
print("Epoch {}/{} - Train Loss: {:.4f}, Train Accuracy: {:.2f}%, Val Loss: {:.4f}, Val Accuracy: {:.2f}%"
.format(epoch+1, num_epochs, train_loss, train_accuracy, val_loss, val_accuracy))
```
这个代码加载 CIFAR-10 数据集,使用 VGG-16 进行训练,每个 epoch 计算训练集和验证集的损失和准确率,并输出结果。你可以根据需要调整超参数和数据增强方式。