b68db1aaf6abe4d2cea8321cc6f1564228dd60f5,deepchem/models/tensorgraph/models/seqtoseq.py,AspuruGuzikAutoEncoder,_create_decoder,#AspuruGuzikAutoEncoder#Any#Any#,529

Before Change

      prev_layer = layers.GRU(
          self._decoder_dimension, self.batch_size, in_layers=prev_layer)
    retval = layers.Dense(
        len(self._output_tokens),
        in_layers=prev_layer,
        activation_fn=tf.nn.softmax,
        name="output")

After Change

  def _create_decoder(self, n_layers, dropout):
    Create the decoder as a tf.keras.Model.
    input = Input(shape=(self._embedding_dimension,))
    prev_layer = Dense(self._embedding_dimension, activation=tf.nn.relu)(input)
    prev_layer = layers.Stack()(self._max_output_length * [prev_layer])
    for i in range(3):
      if dropout > 0.0:
        prev_layer = Dropout(dropout)(prev_layer)
      prev_layer = GRU(
          self._decoder_dimension, return_sequences=True)(prev_layer)
    output = Dense(
        len(self._output_tokens), activation=tf.nn.softmax)(prev_layer)
    return tf.keras.Model(inputs=input, outputs=output)

  def _create_input_array(self, sequences):
    return self._create_output_array(sequences)

Instances