b68db1aaf6abe4d2cea8321cc6f1564228dd60f5,deepchem/models/tensorgraph/models/seqtoseq.py,SeqToSeq,_create_decoder,#SeqToSeq#Any#Any#,163

Before Change

    for i in range(n_layers):
      if dropout > 0.0:
        prev_layer = layers.Dropout(dropout, in_layers=prev_layer)
      prev_layer = layers.GRU(
          self._embedding_dimension, self.batch_size, in_layers=prev_layer)
    return layers.Dense(
        len(self._output_tokens),
        in_layers=prev_layer,
        activation_fn=tf.nn.softmax)

  def _create_loss(self):
    Create the loss function.
    prob = layers.ReduceSum(self.output * self._labels, axis=2)

After Change

    for i in range(n_layers):
      if dropout > 0.0:
        prev_layer = Dropout(dropout)(prev_layer)
      prev_layer = GRU(
          self._embedding_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_loss(self):
    Create the loss function.

Instances