建立一个5输入，1输出，70%训练集，30%测试集的bp神经网络的pytorch代码

要在PyTorch中建立一个有5个输入、1个输出，使用70%数据作为训练集，30%数据作为测试集的BP（Backpropagation，反向传播）神经网络，你可以按照以下步骤编写代码：

import torch
import torch.nn as nn
from torch.utils.data import DataLoader, random_split

# 定义网络结构
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.fc1 = nn.Linear(5, 16)  # 输入层到隐藏层
        self.fc2 = nn.Linear(16, 8)   # 隐藏层到另一隐藏层
        self.fc_out = nn.Linear(8, 1)  # 输出层

    def forward(self, x):
        x = torch.relu(self.fc1(x))  # 使用ReLU激活函数
        x = torch.relu(self.fc2(x))
        return self.fc_out(x)

# 创建数据集假设你已经有了`data`, `labels`变量
data = ...  # 输入特征数据
labels = ...  # 目标标签数据

# 划分数据集
train_size = int(len(data) * 0.7)
test_size = len(data) - train_size
train_data, test_data = random_split(data, [train_size, test_size])

# 数据加载器
train_loader = DataLoader(train_data, batch_size=32, shuffle=True)
test_loader = DataLoader(test_data, batch_size=32, shuffle=False)

# 初始化模型并设置损失函数和优化器
model = Net()
criterion = nn.MSELoss() if you want to use mean squared error else nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)  # 使用SGD优化器

# 训练过程
num_epochs = 10  # 根据需求调整迭代次数
for epoch in range(num_epochs):
    for inputs, targets in train_loader:
        optimizer.zero_grad()  # 梯度清零
        outputs = model(inputs)
        loss = criterion(outputs, targets)
        loss.backward()  # 反向传播
        optimizer.step()  # 更新权重

# 测试过程
model.eval()  # 设置模型为评估模式
with torch.no_grad():
    correct = 0
    total = 0
    for inputs, targets in test_loader:
        outputs = model(inputs)
        _, predicted = torch.max(outputs.data, 1)
        total += targets.size(0)
        correct += (predicted == targets).sum().item()

accuracy = 100 * correct / total
print(f"Accuracy on the test set: {accuracy}%")