Hi everone,
I’m new to pytorch. When I try to understand code from http://pytorch.org/tutorials/intermediate/seq2seq_translation_tutorial.html, I don’t understand why encoder or decoder need resize input tensor, look the code:
class EncoderRNN(nn.Module):
def __init__(self, input_size, hidden_size, n_layers=1):
super(EncoderRNN, self).__init__()
self.n_layers = n_layers
self.hidden_size = hidden_size
self.embedding = nn.Embedding(input_size, hidden_size)
self.gru = nn.GRU(hidden_size, hidden_size)
def forward(self, input, hidden):
embedded = self.embedding(input).view(1, 1, -1)
output = embedded
for i in range(self.n_layers):
output, hidden = self.gru(output, hidden)
return output, hidden
def initHidden(self):
result = Variable(torch.zeros(1, 1, self.hidden_size))
if use_cuda:
return result.cuda()
else:
return result
above the code, input tensor after embedding be resize to (1,1,-1)(embedded = self.embedding(input).view(1, 1, -1)), why can’t use origin dim (seq_len, batch_size, feature_size). plz help.