transformer_decoder.py

def decoder(vocab_size,
            num_layers,
            units,
            d_model,
            num_heads,
            dropout,
            name='decoder'):
  inputs = tf.keras.Input(shape=(None,), name='inputs')
  enc_outputs = tf.keras.Input(shape=(None, d_model), name='encoder_outputs')
  look_ahead_mask = tf.keras.Input(
      shape=(1, None, None), name='look_ahead_mask')
  padding_mask = tf.keras.Input(shape=(1, 1, None), name='padding_mask')
  
  embeddings = tf.keras.layers.Embedding(vocab_size, d_model)(inputs)
  embeddings *= tf.math.sqrt(tf.cast(d_model, tf.float32))
  embeddings = PositionalEncoding(vocab_size, d_model)(embeddings)

  outputs = tf.keras.layers.Dropout(rate=dropout)(embeddings)

  for i in range(num_layers):
    outputs = decoder_layer(
        units=units,
        d_model=d_model,
        num_heads=num_heads,
        dropout=dropout,
        name='decoder_layer_{}'.format(i),
    )(inputs=[outputs, enc_outputs, look_ahead_mask, padding_mask])

  return tf.keras.Model(
      inputs=[inputs, enc_outputs, look_ahead_mask, padding_mask],
      outputs=outputs,
      name=name)