nmt_29.py

        # Combine the context vector and the LSTM output
        # Before combined, both have shape of (batch_size, 1, rnn_size),
        # so let's squeeze the axis 1 first
        # After combined, it will have shape of (batch_size, 2 * rnn_size)
        lstm_out = tf.concat([tf.squeeze(context, 1), tf.squeeze(lstm_out, 1)], 1)
        
        # lstm_out now has shape (batch_size, rnn_size)
        lstm_out = self.wc(lstm_out)
        
        # Finally, it is converted back to vocabulary space: (batch_size, vocab_size)
        logits = self.ws(lstm_out)

        return logits, state_h, state_c, alignment

Hello, thanks for writing your tutorial here https://trungtran.io/2019/03/29/neural-machine-translation-with-attention-mechanism/

I do have one question. Should line 11 not also have a softmax function applied?