问PyTorch -有效地应用注意力

EN

import torch
import torch.nn as nn
import torch.nn.functional as F

class RNN_LM(nn.Module):
    def __init__(self, hidden_size, vocab_size, embedding_dim=None, droprate=0.5):
        super().__init__()
        if not embedding_dim:
            embedding_dim = hidden_size
        self.embedding_matrix = nn.Embedding(vocab_size, embedding_dim)

        self.lstm = nn.LSTM(input_size=embedding_dim, hidden_size=hidden_size, batch_first=False)
        self.attn = nn.Linear(hidden_size, hidden_size)
        self.vocab_dist = nn.Linear(hidden_size, vocab_size)
        self.dropout = nn.Dropout(droprate)

    def forward(self, x):
        x = self.dropout(self.embedding_matrix(x.view(-1, 1)))
        x, states = self.lstm(x)
        #print(x.size())
        x = x.squeeze()
        content_vectors = [x[0].view(1, -1)]
        # for-loop over hidden states and attention
        for i in range(1, x.size(0)):
            prev_states = x[:i]
            current_state = x[i].view(1, -1)

            attn_prod = torch.mm(self.attn(current_state), prev_states.t())
            attn_weights = F.softmax(attn_prod, dim=1)
            context = torch.mm(attn_weights, prev_states)
            content_vectors.append(context)

        return self.vocab_dist(self.dropout(torch.cat(content_vectors)))