class DecoderRNN([nn.Module](https://docs.pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module "torch.nn.Module")):
    def __init__(self, hidden_size, output_size):
        super([DecoderRNN](https://docs.pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module "torch.nn.Module"), self).__init__()
        self.embedding = [nn.Embedding](https://docs.pytorch.org/docs/stable/generated/torch.nn.Embedding.html#torch.nn.Embedding "torch.nn.Embedding")(output_size, hidden_size)
        self.gru = [nn.GRU](https://docs.pytorch.org/docs/stable/generated/torch.nn.GRU.html#torch.nn.GRU "torch.nn.GRU")(hidden_size, hidden_size, batch_first=True)
        self.out = [nn.Linear](https://docs.pytorch.org/docs/stable/generated/torch.nn.Linear.html#torch.nn.Linear "torch.nn.Linear")(hidden_size, output_size)

    def forward(self, encoder_outputs, encoder_hidden, target_tensor=None):
        batch_size = encoder_outputs.size(0)
        decoder_input = [torch.empty](https://docs.pytorch.org/docs/stable/generated/torch.empty.html#torch.empty "torch.empty")(batch_size, 1, dtype=[torch.long](https://docs.pytorch.org/docs/stable/tensor_attributes.html#torch.dtype "torch.dtype"), [device](https://docs.pytorch.org/docs/stable/tensor_attributes.html#torch.device "torch.device")=[device](https://docs.pytorch.org/docs/stable/tensor_attributes.html#torch.device "torch.device")).fill_(SOS_token)
        decoder_hidden = encoder_hidden
        decoder_outputs = []

        for i in range(MAX_LENGTH):
            decoder_output, decoder_hidden  = self.forward_step(decoder_input, decoder_hidden)
            decoder_outputs.append(decoder_output)

            if target_tensor is not None:
                # Teacher forcing: Feed the target as the next input
                decoder_input = target_tensor[:, i].unsqueeze(1) # Teacher forcing
            else:
                # Without teacher forcing: use its own predictions as the next input
                _, topi = decoder_output.topk(1)
                decoder_input = topi.squeeze(-1).detach()  # detach from history as input

        decoder_outputs = [torch.cat](https://docs.pytorch.org/docs/stable/generated/torch.cat.html#torch.cat "torch.cat")(decoder_outputs, dim=1)
        decoder_outputs = [F.log_softmax](https://docs.pytorch.org/docs/stable/generated/torch.nn.functional.log_softmax.html#torch.nn.functional.log_softmax "torch.nn.functional.log_softmax")(decoder_outputs, dim=-1)
        return decoder_outputs, decoder_hidden, None # We return `None` for consistency in the training loop

    def forward_step(self, input, hidden):
        output = self.embedding(input)
        output = [F.relu](https://docs.pytorch.org/docs/stable/generated/torch.nn.functional.relu.html#torch.nn.functional.relu "torch.nn.functional.relu")(output)
        output, hidden = self.gru(output, hidden)
        output = self.out(output)
        return output, hidden