双向LSTM pytorch 代码示例

好的，以下是双向LSTM的PyTorch代码示例：

import torch
import torch.nn as nn

class BiLSTM(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers, output_size):
        super(BiLSTM, 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, bidirectional=True)
        self.fc = nn.Linear(hidden_size*2, output_size)
        
    def forward(self, x):
        h0 = torch.zeros(self.num_layers*2, x.size(0), self.hidden_size).to(device=x.device)
        c0 = torch.zeros(self.num_layers*2, x.size(0), self.hidden_size).to(device=x.device)
        
        out, _ = self.lstm(x, (h0, c0))
        
        out = self.fc(out[:, -1, :])
        
        return out

其中，`input_size`为输入特征的维度，`hidden_size`为LSTM隐藏层的维度，`num_layers`为LSTM的层数，`output_size`为输出的维度。在`forward`函数中，我们首先初始化LSTM的初始隐藏状态和记忆状态，然后将输入`x`传入LSTM中得到输出`out`，最后将最后一个时间步的输出通过全连接层得到最终的输出。