Seq2vec

Layers mapping sequences to vectors

Modules


YangAttention

Reduce time dimension by applying attention using learned variables

Arguments

  • n_units (int): Attention’s variables units

  • name (str): Layer name

Input shape

(batch_size, time_steps, channels)

Output shape

(batch_size, channels)

Examples

import tensorflow as tf
import tavolo as tvl


model = tf.keras.Sequential([tf.keras.layers.Embedding(vocab_size, 8, input_length=max_sequence_length),
                             tvl.seq2vec.YangAttention()])