烛 BiRNN

使用烛实现 PyTorch LSTM 推理，包括双向 LSTM 推理的实现。

测试数据

1. lstm_test.pt：使用 PyTorch 演示程序生成的结果。代码如下

   import torch
   import torch.nn as nn
   
   rnn = nn.LSTM(10, 20, 1)
   input = torch.randn(5, 3, 10)
   output, (hn, cn) = rnn(input)
   
   state_dict = rnn.state_dict()
   state_dict['input'] = input
   state_dict['output'] = output
   state_dict['hn'] = hn
   state_dict['cn'] = cn
   torch.save(state_dict, "lstm_test.pt")
   

2. bi_lstm_test.pt：使用 PyTorch 演示程序生成的结果。代码如下

   import torch
   import torch.nn as nn
   
   rnn = nn.LSTM(10, 20, 1, bidirectional=True)
   input = torch.randn(5, 3, 10)
   output, (hn, cn) = rnn(input)
   
   state_dict = rnn.state_dict()
   state_dict['input'] = input
   state_dict['output'] = output
   state_dict['hn'] = hn
   state_dict['cn'] = cn
   torch.save(state_dict, "bi_lstm_test.pt")