In class BahdanauAttnDecoderRNN, Should "word_embedded = self.embedding(word_input).view(1, 1, -1) # S=1 x B x N" be " word_embedded = self.embedding(word_input).view(1, word_input.size(0), -1) # S=1 x B x N"?
Because in the case of this tutorial, batch_size is not equal to 1.(word_input.size(0) is the batch_size)
In class BahdanauAttnDecoderRNN, Should "word_embedded = self.embedding(word_input).view(1, 1, -1) # S=1 x B x N" be " word_embedded = self.embedding(word_input).view(1, word_input.size(0), -1) # S=1 x B x N"? Because in the case of this tutorial, batch_size is not equal to 1.(word_input.size(0) is the batch_size)