src/RNNmodel.py

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)