import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, transforms
from torch.utils.data import DataLoader
import matplotlib.pyplot as plt
import numpy as np
# 设置中文字体支持
plt.rcParams["font.family"] = ["SimHei"]
plt.rcParams['axes.unicode_minus'] = False # 解决负号显示问题
# 1. 数据预处理
transform = transforms.Compose([
transforms.ToTensor(), # 转换为张量
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)) # 标准化处理
])
# 2. 加载CIFAR-10数据集
train_dataset = datasets.CIFAR10(
root='./data',
train=True,
download=True,
transform=transform
)
test_dataset = datasets.CIFAR10(
root='./data',
train=False,
transform=transform
)
# 3. 创建数据加载器
batch_size = 64
train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False)
# 4. 定义MLP模型（适应CIFAR-10的输入尺寸）
class MLP(nn.Module):
def __init__(self):
super(MLP, self).__init__()
self.flatten = nn.Flatten() # 将3x32x32的图像展平为3072维向量
self.layer1 = nn.Linear(3072, 512) # 第一层：3072个输入，512个神经元
self.relu1 = nn.ReLU()
self.dropout1 = nn.Dropout(0.2) # 添加Dropout防止过拟合
self.layer2 = nn.Linear(512, 256) # 第二层：512个输入，256个神经元
self.relu2 = nn.ReLU()
self.dropout2 = nn.Dropout(0.2)
self.layer3 = nn.Linear(256, 10) # 输出层：10个类别
def forward(self, x):
# 第一步：将输入图像展平为一维向量
x = self.flatten(x) # 输入尺寸: [batch_size, 3, 32, 32] → [batch_size, 3072]
# 第一层全连接 + 激活 + Dropout
x = self.layer1(x) # 线性变换: [batch_size, 3072] → [batch_size, 512]
x = self.relu1(x) # 应用ReLU激活函数
x = self.dropout1(x) # 训练时随机丢弃部分神经元输出
# 第二层全连接 + 激活 + Dropout
x = self.layer2(x) # 线性变换: [batch_size, 512] → [batch_size, 256]
x = self.relu2(x) # 应用ReLU激活函数
x = self.dropout2(x) # 训练时随机丢弃部分神经元输出
# 第三层（输出层）全连接
x = self.layer3(x) # 线性变换: [batch_size, 256] → [batch_size, 10]
return x # 返回未经过Softmax的logits
# 检查GPU是否可用
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
# 初始化模型
model = MLP()
model = model.to(device) # 将模型移至GPU（如果可用）
criterion = nn.CrossEntropyLoss() # 交叉熵损失函数
optimizer = optim.Adam(model.parameters(), lr=0.001) # Adam优化器
# 5. 训练模型（记录每个 iteration 的损失）
def train(model, train_loader, test_loader, criterion, optimizer, device, epochs):
model.train() # 设置为训练模式
# 记录每个 iteration 的损失
all_iter_losses = [] # 存储所有 batch 的损失
iter_indices = [] # 存储 iteration 序号
for epoch in range(epochs):
running_loss = 0.0
correct = 0
total = 0
for batch_idx, (data, target) in enumerate(train_loader):
data, target = data.to(device), target.to(device) # 移至GPU
optimizer.zero_grad() # 梯度清零
output = model(data) # 前向传播
loss = criterion(output, target) # 计算损失
loss.backward() # 反向传播
optimizer.step() # 更新参数
# 记录当前 iteration 的损失
iter_loss = loss.item()
all_iter_losses.append(iter_loss)
iter_indices.append(epoch * len(train_loader) + batch_idx + 1)
# 统计准确率和损失
running_loss += iter_loss
_, predicted = output.max(1)
total += target.size(0)
correct += predicted.eq(target).sum().item()
# 每100个批次打印一次训练信息
if (batch_idx + 1) % 100 == 0:
print(f'Epoch: {epoch+1}/{epochs} | Batch: {batch_idx+1}/{len(train_loader)} '
f'| 单Batch损失: {iter_loss:.4f} | 累计平均损失: {running_loss/(batch_idx+1):.4f}')
# 计算当前epoch的平均训练损失和准确率
epoch_train_loss = running_loss / len(train_loader)
epoch_train_acc = 100. * correct / total
# 测试阶段
model.eval() # 设置为评估模式
test_loss = 0
correct_test = 0
total_test = 0
with torch.no_grad():
for data, target in test_loader:
data, target = data.to(device), target.to(device)
output = model(data)
test_loss += criterion(output, target).item()
_, predicted = output.max(1)
total_test += target.size(0)
correct_test += predicted.eq(target).sum().item()
epoch_test_loss = test_loss / len(test_loader)
epoch_test_acc = 100. * correct_test / total_test
print(f'Epoch {epoch+1}/{epochs} 完成 | 训练准确率: {epoch_train_acc:.2f}% | 测试准确率: {epoch_test_acc:.2f}%')
# 绘制所有 iteration 的损失曲线
plot_iter_losses(all_iter_losses, iter_indices)
return epoch_test_acc # 返回最终测试准确率
# 6. 绘制每个 iteration 的损失曲线
def plot_iter_losses(losses, indices):
plt.figure(figsize=(10, 4))
plt.plot(indices, losses, 'b-', alpha=0.7, label='Iteration Loss')
plt.xlabel('Iteration（Batch序号）')
plt.ylabel('损失值')
plt.title('每个 Iteration 的训练损失')
plt.legend()
plt.grid(True)
plt.tight_layout()
plt.show()
# 7. 执行训练和测试
epochs = 20 # 增加训练轮次以获得更好效果
print("开始训练模型...")
final_accuracy = train(model, train_loader, test_loader, criterion, optimizer, device, epochs)
print(f"训练完成！最终测试准确率: {final_accuracy:.2f}%")
# # 保存模型
# torch.save(model.state_dict(), 'cifar10_mlp_model.pth')
# # print("模型已保存为: cifar10_mlp_model.pth")
