pythorch建立一个LSTM模型，预测14日后的股票价格

Sure! Here's an example of how you can build an LSTM model in PyTorch to predict stock prices 14 days into the future:

import torch
import torch.nn as nn

class LSTMNet(nn.Module):
    def __init__(self, input_size, hidden_size, output_size):
        super(LSTMNet, self).__init__()
        self.hidden_size = hidden_size
        self.lstm = nn.LSTM(input_size, hidden_size, batch_first=True)
        self.fc = nn.Linear(hidden_size, output_size)

    def forward(self, x):
        out, _ = self.lstm(x)
        out = self.fc(out[:, -1, :])
        return out

# Define the hyperparameters
input_size = 1  # Number of features in the input
hidden_size = 64  # Number of hidden units in the LSTM layer
output_size = 1  # Number of output predictions

# Create an instance of the LSTM model
model = LSTMNet(input_size, hidden_size, output_size)

# Define the loss function and optimizer
criterion = nn.MSELoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)

# Training loop
for epoch in range(num_epochs):
    # Forward pass
    outputs = model(inputs)
    loss = criterion(outputs, targets)
    
    # Backward and optimize
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

    # Print the loss at every epoch
    print(f'Epoch [{epoch+1}/{num_epochs}], Loss: {loss.item():.4f}')

# Predict future stock prices
future_inputs = ...  # Prepare future inputs (shape: [batch_size, 14, input_size])
predicted_prices = model(future_inputs)

Note that you need to prepare your training data (`inputs` and `targets`) and future inputs (`future_inputs`) according to your dataset. Also, make sure to adjust the hyperparameters (e.g., `hidden_size`, `num_epochs`, learning rate) based on your specific task and data.