I found a mistake in an official case

https://pytorch.org/tutorials/intermediate/char_rnn_classification_tutorial
In this link, an RNN network is specified, and I think there is something wrong with its structure. This existing structure cannot collect hidden layer information for the last character. So I think the network should be modified to the structure shown below.


The modified network is shown below:

class RNN(nn.Module):
    def __init__(self, input_size, hidden_size, output_size):
        super(RNN, self).__init__()

        self.hidden_size = hidden_size

        self.i2h = nn.Linear(input_size + hidden_size, hidden_size)
        self.i2o = nn.Linear(hidden_size, output_size)
        self.softmax = nn.LogSoftmax(dim=1)

    def forward(self, input, hidden):
        combined = torch.cat((input, hidden), 1)
        hidden = F.relu(self.i2h(combined))
        output = self.i2o(hidden)
        output = self.softmax(output)
        return output, hidden