import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader
from torchvision import datasets, transforms
import matplotlib.pyplot as plt
数据预处理:标准化+数据增强(仅用于训练集)
transform_train = transforms.Compose([
transforms.RandomCrop(32, padding=4), # 随机裁剪
transforms.RandomHorizontalFlip(), # 随机水平翻转
transforms.ToTensor(), # 转为Tensor
transforms.Normalize((0.4914, 0.4822, 0.4465), # CIFAR-10均值
(0.2023, 0.1994, 0.2010)) # CIFAR-10标准差
])
transform_test = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465),
(0.2023, 0.1994, 0.2010))
])
加载CIFAR-10数据集
train_dataset = datasets.CIFAR10(
root='./data', train=True, download=True, transform=transform_train
)
test_dataset = datasets.CIFAR10(
root='./data', train=False, download=True, transform=transform_test
)
构建数据加载器
train_loader = DataLoader(
train_dataset, batch_size=128, shuffle=True, num_workers=2
)
test_loader = DataLoader(
test_dataset, batch_size=128, shuffle=False, num_workers=2
)
类别名称
classes = ('plane', 'car', 'bird', 'cat', 'deer',
'dog', 'frog', 'horse', 'ship', 'truck')
class SimpleCNN(nn.Module):
def init(self):
super(SimpleCNN, self).init()
# 卷积层:3输入通道(RGB),32输出通道,5x5卷积核
self.conv1 = nn.Conv2d(3, 32, 5, padding=2)
# 池化层:2x2最大池化
self.pool = nn.MaxPool2d(2, 2)
# 卷积层:32输入通道,64输出通道
self.conv2 = nn.Conv2d(32, 64, 5, padding=2)
# 全连接层:展平后连接1024神经元
self.fc1 = nn.Linear(64 * 8 * 8, 1024) # 32/2/2=8(两次池化)
# 全连接层:输出10类(CIFAR-10)
self.fc2 = nn.Linear(1024, 10)
# ReLU激活函数
self.relu = nn.ReLU()
def forward(self, x):x = self.pool(self.relu(self.conv1(x))) # 卷积+激活+池化x = self.pool(self.relu(self.conv2(x)))x = x.view(-1, 64 * 8 * 8) # 展平特征图x = self.relu(self.fc1(x))x = self.fc2(x)return x
初始化模型并移动到GPU(如果可用)
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model = SimpleCNN().to(device)
交叉熵损失(适用于分类任务)
criterion = nn.CrossEntropyLoss()
Adam优化器(学习率0.001)
optimizer = optim.Adam(model.parameters(), lr=0.001)
训练参数
epochs = 20 # 可根据需要调整
记录训练过程
train_losses = []
train_accs = []
test_accs = []
for epoch in range(epochs):
model.train() # 训练模式
running_loss = 0.0
correct = 0
total = 0
for i, data in enumerate(train_loader, 0):# 获取输入数据和标签inputs, labels = data[0].to(device), data[1].to(device)# 清零梯度optimizer.zero_grad()# 前向传播outputs = model(inputs)loss = criterion(outputs, labels)# 反向传播+参数更新loss.backward()optimizer.step()# 统计损失和准确率running_loss += loss.item()_, predicted = torch.max(outputs.data, 1)total += labels.size(0)correct += (predicted == labels).sum().item()# 每100批次打印一次信息if i % 100 == 99:print(f'[{epoch + 1}, {i + 1}] loss: {running_loss / 100:.3f}')running_loss = 0.0# 计算训练集准确率
train_acc = 100 * correct / total
train_losses.append(running_loss / len(train_loader))
train_accs.append(train_acc)# 测试集评估
model.eval() # 评估模式
correct = 0
total = 0
with torch.no_grad(): # 关闭梯度计算for data in test_loader:images, labels = data[0].to(device), data[1].to(device)outputs = model(images)_, predicted = torch.max(outputs.data, 1)total += labels.size(0)correct += (predicted == labels).sum().item()test_acc = 100 * correct / total
test_accs.append(test_acc)
print(f'Epoch {epoch+1} - 训练准确率: {train_acc:.2f}% 测试准确率: {test_acc:.2f}%')
print('训练完成')
1. 测试集整体精度
model.eval()
correct = 0
total = 0
with torch.no_grad():
for data in test_loader:
images, labels = data[0].to(device), data[1].to(device)
outputs = model(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print(f'测试集整体准确率: {100 * correct / total:.2f}%')
2. 各类别精度
class_correct = list(0. for i in range(10))
class_total = list(0. for i in range(10))
with torch.no_grad():
for data in test_loader:
images, labels = data[0].to(device), data[1].to(device)
outputs = model(images)
_, predicted = torch.max(outputs, 1)
c = (predicted == labels).squeeze()
for label, prediction in zip(labels, c):
class_correct[label] += prediction.item()
class_total[label] += 1
for i in range(10):
print(f'类别 {classes[i]} 的准确率: {100 * class_correct[i] / class_total[i]:.2f}%')
plt.figure(figsize=(12, 4))
损失曲线
plt.subplot(1, 2, 1)
plt.plot(train_losses, label='训练损失')
plt.title('训练损失曲线')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.legend()
准确率曲线
plt.subplot(1, 2, 2)
plt.plot(train_accs, label='训练准确率')
plt.plot(test_accs, label='测试准确率')
plt.title('准确率曲线')
plt.xlabel('Epoch')
plt.ylabel('准确率 (%)')
plt.legend()
plt.tight_layout()
plt.show()