test rnn

• lstm_test.pt: A simple LSTM model with 1 layer.
  python

  1import torch 2import torch.nn as nn 3 4rnn = nn.LSTM(10, 20, num_layers=1, batch_first=True) 5input = torch.randn(5, 3, 10) 6output, (hn, cn) = rnn(input) 7 8state_dict = rnn.state_dict() 9state_dict['input'] = input 10state_dict['output'] = output.contiguous() 11state_dict['hn'] = hn 12state_dict['cn'] = cn 13torch.save(state_dict, "lstm_test.pt")
• gru_test.pt: A simple GRU model with 1 layer.
  python

  1import torch 2import torch.nn as nn 3 4rnn = nn.GRU(10, 20, num_layers=1, batch_first=True) 5input = torch.randn(5, 3, 10) 6output, hn = rnn(input) 7 8state_dict = rnn.state_dict() 9state_dict['input'] = input 10state_dict['output'] = output.contiguous() 11state_dict['hn'] = hn 12torch.save(state_dict, "gru_test.pt")
• bi_lstm_test.pt: A bidirectional LSTM model with 1 layer.
  python

  1import torch 2import torch.nn as nn 3 4rnn = nn.LSTM(10, 20, num_layers=1, bidirectional=True, batch_first=True) 5input = torch.randn(5, 3, 10) 6output, (hn, cn) = rnn(input) 7 8state_dict = rnn.state_dict() 9state_dict['input'] = input 10state_dict['output'] = output.contiguous() 11state_dict['hn'] = hn 12state_dict['cn'] = cn 13torch.save(state_dict, "bi_lstm_test.pt")
• bi_gru_test.pt: A bidirectional GRU model with 1 layer.
  python

  1import torch 2import torch.nn as nn 3 4rnn = nn.GRU(10, 20, num_layers=1, bidirectional=True, batch_first=True) 5input = torch.randn(5, 3, 10) 6output, hn = rnn(input) 7 8state_dict = rnn.state_dict() 9state_dict['input'] = input 10state_dict['output'] = output.contiguous() 11state_dict['hn'] = hn 12torch.save(state_dict, "bi_gru_test.pt")
• lstm_nlayer_test.pt: A LSTM model with 3 layers.
  python

  1import torch 2import torch.nn as nn 3 4rnn = nn.LSTM(10, 20, num_layers=3, batch_first=True) 5input = torch.randn(5, 3, 10) 6output, (hn, cn) = rnn(input) 7 8state_dict = rnn.state_dict() 9state_dict['input'] = input 10state_dict['output'] = output.contiguous() 11state_dict['hn'] = hn 12state_dict['cn'] = cn 13torch.save(state_dict, "lstm_nlayer_test.pt")
• bi_lstm_nlayer_test.pt: A bidirectional LSTM model with 3 layers.
  python

  1import torch 2import torch.nn as nn 3 4rnn = nn.LSTM(10, 20, num_layers=3, bidirectional=True, batch_first=True) 5input = torch.randn(5, 3, 10) 6output, (hn, cn) = rnn(input) 7 8state_dict = rnn.state_dict() 9state_dict['input'] = input 10state_dict['output'] = output.contiguous() 11state_dict['hn'] = hn 12state_dict['cn'] = cn 13torch.save(state_dict, "bi_lstm_nlayer_test.pt")
• gru_nlayer_test.pt: A GRU model with 3 layers.
  python

  1import torch 2import torch.nn as nn 3 4rnn = nn.GRU(10, 20, num_layers=3, batch_first=True) 5input = torch.randn(5, 3, 10) 6output, hn = rnn(input) 7 8state_dict = rnn.state_dict() 9state_dict['input'] = input 10state_dict['output'] = output.contiguous() 11state_dict['hn'] = hn 12torch.save(state_dict, "gru_nlayer_test.pt")
• bi_gru_nlayer_test.pt: A bidirectional GRU model with 3 layers.
  python

  1import torch 2import torch.nn as nn 3 4rnn = nn.GRU(10, 20, num_layers=3, bidirectional=True, batch_first=True) 5input = torch.randn(5, 3, 10) 6output, hn = rnn(input) 7 8state_dict = rnn.state_dict() 9state_dict['input'] = input 10state_dict['output'] = output.contiguous() 11state_dict['hn'] = hn 12torch.save(state_dict, "bi_gru_nlayer_test.pt")