conv_encoder_fairseq.py 文件源码

def _create_position_embedding(self, lengths, maxlen):

    # Slice to size of current sequence
    pe_slice = self.pos_embed[2:maxlen+2, :]
    # Replicate encodings for each element in the batch
    batch_size = tf.shape(lengths)[0]
    pe_batch = tf.tile([pe_slice], [batch_size, 1, 1])

    # Mask out positions that are padded
    positions_mask = tf.sequence_mask(
        lengths=lengths, maxlen=maxlen, dtype=tf.float32)
    positions_embed = pe_batch * tf.expand_dims(positions_mask, 2)

    positions_embed = tf.reverse_sequence(positions_embed, lengths, batch_dim=0, seq_dim=1)  # [[1,2,3,4,PAD,PAD,PAD],[2,3,PAD,PAD,PAD,PAD,PAD]]   [4,2]
    positions_embed = tf.reverse(positions_embed,[1])  # --> [[4,3,2,1,PAD,PAD,PAD],[3,2,PAD,PAD,PAD,PAD,PAD]] --> [[PAD,PAD,PAD,1,2,3,4],[PAD,PAD,PAD,PAD,PAD,2,3]]

    return positions_embed