数据是由excel表读取的，不是随机生成的，修改一下以上代码

如果你的数据是由Excel表格读取而来，你可以使用`pandas`库来读取Excel数据，并将其转换为PyTorch张量。以下是修改后的代码示例：

import torch
import torch.nn as nn
import torch.optim as optim
from torchvision.transforms import ToTensor
from torch.utils.data import Dataset, DataLoader
import pandas as pd
import matplotlib.pyplot as plt

# 自定义数据集类
class CustomDataset(Dataset):
    def __init__(self, data, labels):
        self.data = data
        self.labels = labels

    def __len__(self):
        return len(self.data)

    def __getitem__(self, idx):
        return self.data[idx], self.labels[idx]

# 自定义CNN模型
class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Conv2d(1, 16, kernel_size=3, stride=1, padding=1)
        self.relu = nn.ReLU()
        self.conv2 = nn.Conv2d(16, 32, kernel_size=3, stride=1, padding=1)
        self.conv3 = nn.Conv2d(32, 1, kernel_size=3, stride=1, padding=1)

    def forward(self, x):
        x = self.conv1(x)
        x = self.relu(x)
        x = self.conv2(x)
        x = self.relu(x)
        x = self.conv3(x)
        return x

# 从Excel表格读取数据
train_df = pd.read_excel('train_data.xlsx')
train_data = torch.tensor(train_df.values).float().unsqueeze(1)  # 添加通道维度

train_labels_df = pd.read_excel('train_labels.xlsx')
train_labels = torch.tensor(train_labels_df.values).float().unsqueeze(1)  # 添加通道维度

train_dataset = CustomDataset(train_data, train_labels)
train_dataloader = DataLoader(train_dataset, batch_size=32, shuffle=True)

test_df = pd.read_excel('test_data.xlsx')
test_data = torch.tensor(test_df.values).float().unsqueeze(1)  # 添加通道维度

test_labels_df = pd.read_excel('test_labels.xlsx')
test_labels = torch.tensor(test_labels_df.values).float().unsqueeze(1)  # 添加通道维度

test_dataset = CustomDataset(test_data, test_labels)
test_dataloader = DataLoader(test_dataset, batch_size=32, shuffle=False)

# 模型训练
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = CNN().to(device)
criterion = nn.MSELoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

train_loss_history = []
test_loss_history = []

for epoch in range(10):
    train_loss = 0.0
    model.train()
    for inputs, labels in train_dataloader:
        inputs, labels = inputs.to(device), labels.to(device)
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        train_loss += loss.item()
    train_loss /= len(train_dataloader)
    train_loss_history.append(train_loss)

    test_loss = 0.0
    model.eval()
    with torch.no_grad():
        for inputs, labels in test_dataloader:
            inputs, labels = inputs.to(device), labels.to(device)
            outputs = model(inputs)
            loss = criterion(outputs, labels)
            test_loss += loss.item()
        test_loss /= len(test_dataloader)
        test_loss_history.append(test_loss)

    print(f"Epoch {epoch+1}: Train Loss: {train_loss:.4f}, Test Loss: {test_loss:.4f}")

# 绘制误差图像
plt.plot(train_loss_history, label='Train Loss')
plt.plot(test_loss_history, label='Test Loss')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.legend()
plt.show()

在这个修改后的代码中，我们使用了`pandas`库来从Excel表格中读取训练和测试数据。你需要将`'train_data.xlsx'`、`'train_labels.xlsx'`、`'test_data.xlsx'`和`'test_labels.xlsx'`替换为你实际的Excel文件名。数据读取后，我们将其转换为PyTorch张量，并将其添加了一个通道维度（unsqueeze(1)）。然后，我们使用自定义的数据集类`CustomDataset`和数据加载器`DataLoader`来加载数据。

希望这次的修改对你有帮助！如果还有其他问题，请随时提问。