b68db1aaf6abe4d2cea8321cc6f1564228dd60f5,deepchem/models/tensorgraph/models/seqtoseq.py,SeqToSeq,predict_from_sequences,#SeqToSeq#Any#Any#,226

Before Change

    result = []
    with self._get_tf("Graph").as_default():
      for batch in self._batch_elements(sequences):
        feed_dict = {}
        feed_dict[self._features] = self._create_input_array(batch)
        feed_dict[self._gather_indices] = [(i, len(batch[i])
                                            if i < len(batch) else 0)
                                           for i in range(self.batch_size)]
        feed_dict[self._training_placeholder] = 0.0
        for initial, zero in zip(self.rnn_initial_states, self.rnn_zero_states):
          feed_dict[initial] = zero
        probs = self.session.run(self.output, feed_dict=feed_dict)
        for i in range(len(batch)):
          result.append(self._beam_search(probs[i], beam_width))
    return result

After Change

    result = []
    for batch in self._batch_elements(sequences):
      features = self._create_input_array(batch)
      indices = np.array([(i, len(batch[i]) if i < len(batch) else 0)
                          for i in range(self.batch_size)])
      probs = self.predict_on_generator([[(features, indices,
                                           self.get_global_step()), None,
                                          None]])
      for i in range(len(batch)):
        result.append(self._beam_search(probs[i], beam_width))

Instances