387e650e16a5405691fb18ce05b34bd90239180e,deepchem/metalearning/maml.py,MAML,fit,#MAML#Any#Any#Any#Any#,202

Before Change

      // Do checkpointing.

      if i == steps - 1 or time.time() >= checkpoint_time + checkpoint_interval:
        with self._session.as_default():
          manager.save()
        checkpoint_time = time.time()

  def restore(self):
    Reload the model parameters from the most recent checkpoint file.

After Change

        if j == 0:
          summed_gradients = meta_gradients
        else:
          summed_gradients = [
              s + g for s, g in zip(summed_gradients, meta_gradients)
          ]
      self._tf_optimizer.apply_gradients(zip(summed_gradients, variables))

      // Do checkpointing.

Instances