请使用pytorch 编写LSTM时间序列预测代码包含激活函数ReLU的配置

以下是一个使用PyTorch编写LSTM时间序列预测代码的示例。其中包括一个使用ReLU激活函数的LSTM模型配置。

import torch
import torch.nn as nn
import numpy as np

# 定义LSTM模型
class LSTM(nn.Module):
    def __init__(self, input_size, hidden_size, output_size, num_layers):
        super(LSTM, self).__init__()
        self.hidden_size = hidden_size
        self.num_layers = num_layers
        self.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True)
        self.fc = nn.Linear(hidden_size, output_size)
        self.relu = nn.ReLU()

    def forward(self, x):
        h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device) 
        c0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)
        out, _ = self.lstm(x, (h0, c0))
        out = self.fc(out[:, -1, :])
        out = self.relu(out)
        return out

# 定义超参数
input_size = 1
hidden_size = 32
output_size = 1
num_layers = 2
learning_rate = 0.01
num_epochs = 100

# 加载数据
data = np.array([1, 2, 3, 4, 5, 6, 7, 8, 9, 10], dtype=np.float32)
data = data.reshape(-1, 1)

# 将数据转换为张量
x_train = torch.tensor(data[:-1, :]).unsqueeze(0)
y_train = torch.tensor(data[1:, :]).unsqueeze(0)

# 将模型移动到GPU（如果可用）
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = LSTM(input_size, hidden_size, output_size, num_layers).to(device)

# 定义损失函数和优化器
criterion = nn.MSELoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

# 训练模型
for epoch in range(num_epochs):
    # 前向传播
    outputs = model(x_train.to(device))
    loss = criterion(outputs, y_train.to(device))

    # 反向传播和优化
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

    if (epoch + 1) % 10 == 0:
        print('Epoch [{}/{}], Loss: {:.4f}'.format(epoch + 1, num_epochs, loss.item()))

# 测试模型
with torch.no_grad():
    future = 3
    test_inputs = data[-1].copy()
    test_inputs = torch.tensor(test_inputs).float().unsqueeze(0).unsqueeze(0).to(device)
    test_outputs = []
    for i in range(future):
        out = model(test_inputs)
        test_outputs.append(out.item())
        test_inputs = torch.cat([test_inputs[:, :, 1:], out.unsqueeze(1).unsqueeze(1)], dim=2)

    print('Test Outputs:', test_outputs)

在这个示例中，我们定义了一个LSTM模型，其中包括一个使用ReLU激活函数的线性层。我们使用MSE损失函数和Adam优化器来训练模型。在训练完成后，我们使用训练好的模型来预测未来的数据点