seqtoseq_model.py 文件源码

def forward(self, input, hidden, encoder_output, encoder_outputs):
        embedded = self.embedding(input).view(1, 1, -1)
        embedded = self.dropout(embedded)

        attn_weights = F.softmax(
            self.attn(torch.cat((embedded[0], hidden[0]), 1)))
        attn_weights = attn_weights.cuda() if use_cuda else attn_weights
        attn_applied = torch.bmm(attn_weights.unsqueeze(0),
                                 encoder_outputs.unsqueeze(0))
        attn_applied = attn_applied.cuda() if use_cuda else attn_applied

        output = torch.cat((embedded[0], attn_applied[0]), 1)
        output = output.cuda() if use_cuda else output
        output = self.attn_combine(output).unsqueeze(0)

        for i in range(self.n_layers):
            output = F.relu(output)
            output = output.cuda() if use_cuda else output
            output, hidden = self.gru(output, hidden)

        output = F.log_softmax(self.out(output[0]))
        output = output.cuda() if use_cuda else output
        return output, hidden, attn_weights