has anyone implemented this tutorial with an lstm?
https://pytorch.org/tutorials/intermediate/seq2seq_translation_tutorial.html
I have tried to implement it with an lstm but i am getting an error. Below is my code.
class Encoder(nn.Module):
def __init__(self, input_size, hidden_size):
super(Encoder, self).__init__()
self.hidden_size = hidden_size
self.word_embed = nn.Embedding(input_size, hidden_size)
self.pos_embed = nn.Embedding(input_size, hidden_size)
self.lstm = nn.LSTM(hidden_size, hidden_size)
def forward(self, words, hidden):
word_embed = self.word_embed(words).view(1, 1, -1)
output = torch.cat([word_embed, pos_embed], 2)
output, hidden = self.lstm(output, hidden)
return output, hidden
def initHidden(self):
return (torch.zeros(1, 1, self.hidden_size, device=device), torch.zeros(1, 1, self.hidden_size, device=device))
class AttnDecoder(nn.Module):
def __init__(self, hidden_size, output_size, dropout_p=0.1, max_length=MAX_LENGTH):
super(AttnDecoder, self).__init__()
self.hidden_size = hidden_size
self.output_size = output_size
self.dropout_p = dropout_p
self.max_length = max_length
self.embedding = nn.Embedding(self.output_size, self.hidden_size)
self.attn = nn.Linear(self.hidden_size * 2, self.max_length)
self.attn_combine = nn.Linear(self.hidden_size * 2, self.hidden_size)
self.dropout = nn.Dropout(self.dropout_p)
self.lstm = nn.LSTM(self.hidden_size, self.hidden_size)
self.out = nn.Linear(self.hidden_size, self.output_size)
def forward(self, input, hidden, encoder_outputs):
embedded = self.embedding(input).view(1, 1, -1)
embedded = self.dropout(embedded)
attn_weights = F.softmax(
self.attn(torch.cat((embedded[0], hidden[0]), 1)), dim=1)
attn_applied = torch.bmm(attn_weights.unsqueeze(0),
encoder_outputs.unsqueeze(0))
output = torch.cat((embedded[0], attn_applied[0]), 1)
output = self.attn_combine(output).unsqueeze(0)
output = F.relu(output)
output, hidden = self.lstm(output, hidden)
output = F.log_softmax(self.out(output[0]), dim=1)
return output, hidden, attn_weights
I am getting the error
self.attn(torch.cat((embedded[0], hidden[0]), 1)), dim=1)
RuntimeError: Tensors must have same number of dimensions: got 2 and 3
Thanks!