b68db1aaf6abe4d2cea8321cc6f1564228dd60f5,deepchem/models/tensorgraph/models/seqtoseq.py,SeqToSeq,predict_from_embeddings,#SeqToSeq#Any#Any#,254

Before Change

        feed_dict = {}
        feed_dict[self.embedding] = embedding_array
        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

      for i, e in enumerate(batch):
        embedding_array[i] = e
      probs = self.decoder(embedding_array, training=False)
      if tf.executing_eagerly():
        probs = probs.numpy()
      else:
        probs = probs.eval(session=self.session)
      for i in range(len(batch)):
        result.append(self._beam_search(probs[i], beam_width))
    return result

Instances