import torch
import torch.nn as nn
from d2l import torch as d2l


class AttentionDecoder(d2l.Decoder):
    """带有注意力机制的解码器基本接口"""

    def __init__(self, **kwargs):
        super(AttentionDecoder, self).__init__(**kwargs)

    @property
    def attention_weights(self):
        raise NotImplementedError


# 定义注意力解码器
class Seq2SeqAttentionDecoder(AttentionDecoder):
    def __init__(self, vocab_size, embed_size, num_hiddens, num_layers,
                 dropout=0.0, **kwargs):
        super(Seq2SeqAttentionDecoder, self).__init__(**kwargs)
        self.attention = d2l.AdditiveAttention(
            num_hiddens, num_hiddens, num_hiddens, dropout)
        self.embedding = nn.Embedding(vocab_size, embed_size)
        self.rnn = nn.GRU(embed_size + num_hiddens, num_hiddens, num_layers,
                          dropout=dropout)
        self.dense = nn.Linear(num_hiddens, vocab_size)

    def init_state(self, enc_outputs, enc_valid_lens, *args):
        # outputs的形状为(batch_size,num_steps,num_hiddens)
        # hidden_state的形状为(num_layers,batch_size,num_hiddens)
        outputs, hidden_state = enc_outputs
        return (outputs.permute(1, 0, 2), hidden_state, enc_valid_lens)

    def forward(self, X, state):
        # enc_outputs的形状为(batch_size,num_steps,num_hiddens)
        # hidden_state的形状为(num_layers,batch_size,num_hiddens)
        enc_outputs, hidden_state, enc_valid_lens = state
        # 输出X的形状为(num_steps,batch_size,embed_size)
        X = self.embedding(X).permute(1, 0, 2)
        outputs, self._attention_weights = [], []
        for x in X:
            # query的形状为(batch_size,1,num_hiddens)
            query = torch.unsqueeze(hidden_state[-1], dim=1)
            context = self.attention(query, enc_outputs, enc_outputs, enc_valid_lens)
            # 在特征维度上连接
            x = torch.cat((context, torch.unsqueeze(x, dim=1)), dim=-1)
            # 将x变形为(1,batch_size,embed_size+num_hiddens)
            out, hidden_state = self.rnn(x.permute(1, 0, 2), hidden_state)
            outputs.append(out)
            self._attention_weights.append(self.attention.attention_weights)
        outputs = self.dense(torch.cat(outputs, dim=0))
        return outputs.permute(1, 0, 2), [enc_outputs, hidden_state, enc_valid_lens]


# train
embed_size, num_hiddens, num_layers, dropout = 32, 32, 2, 0.1
batch_size, num_steps = 64, 10
lr, num_epochs, device = 0.005, 300, d2l.try_gpu()
train_iter, src_vocab, tgt_vocab = d2l.load_data_nmt(batch_size, num_steps)
encoder = d2l.Seq2SeqEncoder(
    len(src_vocab), embed_size, num_hiddens, num_layers, dropout)
decoder = Seq2SeqAttentionDecoder(
    len(tgt_vocab), embed_size, num_hiddens, num_layers, dropout)
net = d2l.EncoderDecoder(encoder, decoder)
d2l.train_seq2seq(net, train_iter, lr, num_epochs, tgt_vocab, device)
d2l.plt.show()