2.0- Bahdanau_attention.py

#from pytorch 

class BahdanauAttnDecoderRNN(nn.Module):
    def __init__(self, hidden_size, output_size, n_layers=1, dropout_p=0.1):
        super(AttnDecoderRNN, self).__init__()
        
        # Define parameters
        self.hidden_size = hidden_size
        self.output_size = output_size
        self.n_layers = n_layers
        self.dropout_p = dropout_p
        self.max_length = max_length
        
        # Define layers
        self.embedding = nn.Embedding(output_size, hidden_size)
        self.dropout = nn.Dropout(dropout_p)
        self.attn = GeneralAttn(hidden_size)
        self.gru = nn.GRU(hidden_size * 2, hidden_size, n_layers, dropout=dropout_p)
        self.out = nn.Linear(hidden_size, output_size)
    
    def forward(self, word_input, last_hidden, encoder_outputs):
        # Note that we will only be running forward for a single decoder time step, but will use all encoder outputs
        
        # Get the embedding of the current input word (last output word)
        word_embedded = self.embedding(word_input).view(1, 1, -1) # S=1 x B x N
        word_embedded = self.dropout(word_embedded)
        
        # Calculate attention weights and apply to encoder outputs
        attn_weights = self.attn(last_hidden[-1], encoder_outputs)
        context = attn_weights.bmm(encoder_outputs.transpose(0, 1)) # B x 1 x N
        
        # Combine embedded input word and attended context, run through RNN
        rnn_input = torch.cat((word_embedded, context), 2)
        output, hidden = self.gru(rnn_input, last_hidden)
        
        # Final output layer
        output = output.squeeze(0) # B x N
        output = F.log_softmax(self.out(torch.cat((output, context), 1)))
        
        # Return final output, hidden state, and attention weights (for visualization)
        return output, hidden, attn_weights