绘制训练集准确度曲线和失函数曲线pytorch代码30轮次

以下是绘制训练集准确度曲线和损失函数曲线的 PyTorch 代码，共计 30 轮次：

import torch
import torch.nn as nn
import torch.optim as optim
import matplotlib.pyplot as plt

# 定义模型
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.fc1 = nn.Linear(10, 5)
        self.fc2 = nn.Linear(5, 2)

    def forward(self, x):
        x = torch.relu(self.fc1(x))
        x = self.fc2(x)
        return x

# 定义训练函数
def train(model, optimizer, criterion, train_loader, device):
    model.train()
    train_loss = 0
    correct = 0
    total = 0
    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()
        output = model(data)
        loss = criterion(output, target)
        loss.backward()
        optimizer.step()

        train_loss += loss.item()
        _, predicted = output.max(1)
        total += target.size(0)
        correct += predicted.eq(target).sum().item()

    train_acc = 100. * correct / total
    train_loss /= len(train_loader.dataset)
    return train_acc, train_loss

# 定义测试函数
def test(model, criterion, test_loader, device):
    model.eval()
    test_loss = 0
    correct = 0
    total = 0
    with torch.no_grad():
        for batch_idx, (data, target) in enumerate(test_loader):
            data, target = data.to(device), target.to(device)
            output = model(data)
            loss = criterion(output, target)

            test_loss += loss.item()
            _, predicted = output.max(1)
            total += target.size(0)
            correct += predicted.eq(target).sum().item()

    test_acc = 100. * correct / total
    test_loss /= len(test_loader.dataset)
    return test_acc, test_loss

# 加载数据集
train_loader = torch.utils.data.DataLoader(
    torch.randn(1000, 10), batch_size=32, shuffle=True)
test_loader = torch.utils.data.DataLoader(
    torch.randn(100, 10), batch_size=32, shuffle=True)

# 定义超参数
lr = 0.01
momentum = 0.9
epochs = 30

# 初始化模型、优化器和损失函数
model = Net().to("cuda")
optimizer = optim.SGD(model.parameters(), lr=lr, momentum=momentum)
criterion = nn.CrossEntropyLoss()

# 记录训练过程中的准确度和损失函数
train_acc_list = []
train_loss_list = []
test_acc_list = []
test_loss_list = []

# 开始训练
for epoch in range(1, epochs + 1):
    train_acc, train_loss = train(model, optimizer, criterion, train_loader, "cuda")
    test_acc, test_loss = test(model, criterion, test_loader, "cuda")

    train_acc_list.append(train_acc)
    train_loss_list.append(train_loss)
    test_acc_list.append(test_acc)
    test_loss_list.append(test_loss)

    print(f"Epoch {epoch}: Train Acc: {train_acc:.2f}%, Train Loss: {train_loss:.4f}, Test Acc: {test_acc:.2f}%, Test Loss: {test_loss:.4f}")

# 绘制训练集准确度曲线和损失函数曲线
plt.plot(range(1, epochs + 1), train_acc_list, label="Train Acc")
plt.plot(range(1, epochs + 1), train_loss_list, label="Train Loss")
plt.plot(range(1, epochs + 1), test_acc_list, label="Test Acc")
plt.plot(range(1, epochs + 1), test_loss_list, label="Test Loss")
plt.legend()
plt.show()

希望这个代码能够帮到你！