Spaces:
Runtime error
Runtime error
File size: 2,136 Bytes
639ef39 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 | import torch.nn as nn
import torch
class RNN(nn.Module):
def __init__(self, vocab_size, embedding_dim, hidden_dim, n_layers,
bidirectional, dropout, pad_idx):
"""
@param vocab_size (int)
@param embedding_dim (int)
@param hidden_dim (int)
@param n_layers (int)
@param bidirectional (bool)
@param dropout (float)
@param pad_idx (int)
"""
super().__init__()
self.embedding = nn.Embedding(vocab_size, embedding_dim, padding_idx = pad_idx)
self.rnn = nn.LSTM(embedding_dim,
hidden_dim,
num_layers=n_layers,
bidirectional=bidirectional,
dropout=dropout)
self.fc = nn.Linear(hidden_dim * 2, 1)
self.dropout = nn.Dropout(dropout)
def forward(self, text, text_lengths):
"""
@param text (torch.Tensor): shape = [sent len, batch size]
@param text_lengths (torch.Tensor): shape = [batch size]
@return
"""
#text = [sent len, batch size]
embedded = self.dropout(self.embedding(text))
#embedded = [sent len, batch size, emb dim]
#pack sequence
# lengths need to be on CPU!
packed_embedded = nn.utils.rnn.pack_padded_sequence(embedded, text_lengths.to('cpu'))
packed_output, (hidden, cell) = self.rnn(packed_embedded)
#unpack sequence
output, output_lengths = nn.utils.rnn.pad_packed_sequence(packed_output)
#output = [sent len, batch size, hid dim * num directions]
#output over padding tokens are zero tensors
#hidden = [num layers * num directions, batch size, hid dim]
#cell = [num layers * num directions, batch size, hid dim]
#concat the final forward (hidden[-2,:,:]) and backward (hidden[-1,:,:]) hidden layers
#and apply dropout
hidden = self.dropout(torch.cat((hidden[-2,:,:], hidden[-1,:,:]), dim = 1))
#hidden = [batch size, hid dim * num directions]
return self.fc(hidden)
|