双向RNN实现pytorch

import torch
import torch.nn as nn

class BiRNNClassifier(nn.Module):
    def __init__(self, input_size, hidden_size, num_classes):
        super(BiRNNClassifier, self).__init__()
        self.hidden_size = hidden_size
        self.num_classes = num_classes
        
        self.embedding = nn.Embedding(input_size, hidden_size)
        self.rnn = nn.RNN(hidden_size, hidden_size, batch_first=True, bidirectional=True)
        self.fc = nn.Linear(hidden_size*2, num_classes)
        
    def forward(self, x):
        embedded = self.embedding(x)
        output, _ = self.rnn(embedded)
        output = self.fc(output[:, -1, :])
        return output

# 创建模型实例
input_size = 100 # 输入数据的大小
hidden_size = 128 # RNN隐藏层的大小
num_classes = 10 # 分类的类别数
model = BiRNNClassifier(input_size, hidden_size, num_classes)

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)

# 准备输入数据和标签
input_data = torch.Tensor([[1, 2, 3, 4, 5], [6, 7, 8, 9, 10]])
labels = torch.Tensor([0, 1])

# 前向传播和反向传播
outputs = model(input_data)
loss = criterion(outputs, labels)
optimizer.zero_grad()
loss.backward()
optimizer.step()