Does it missing one LSTM layer in notebook (character level LSTM in PyTorch) ?

[MichelleNing]

In notebook Character_Level_RNN_Soulution file: Step: Defining the network with PyTorch The architecture of the network includes two layer LSTM, however, in class CharRNN, the forward function only has one LSTM layer.

def forward(self, x, hidden):
    ''' Forward pass through the network. 
        These inputs are x, and the hidden/cell state `hidden`. '''

    ## TODO: Get the outputs and the new hidden state from the lstm
    r_output, hidden = self.lstm(x, hidden)

    ## TODO: pass through a dropout layer
    out = self.dropout(r_output)

    # Stack up LSTM outputs using view
    # you may need to use contiguous to reshape the output
    out = out.contiguous().view(-1, self.n_hidden)

    ## TODO: put x through the fully-connected layer
    out = self.fc(out)

    # return the final output and the hidden state
    return out, hidden

If I was correct, there should be two LSTM layers in forward function. Currently, one one layer here.

[MichelleNing]

When set n_layers = 2, it is two hidden LSTM layer. There is no problem for the code. I will close this question.