def _external_eval()

in nmt/train.py [0:0]

• 40 lines of code
• 8 McCabe index (conditional complexity)

def _external_eval(model, global_step, sess, hparams, iterator,
                   iterator_feed_dict, tgt_file, label, summary_writer,
                   save_on_best, avg_ckpts=False):
  """External evaluation such as BLEU and ROUGE scores."""
  out_dir = hparams.out_dir
  decode = global_step > 0

  if avg_ckpts:
    label = "avg_" + label

  if decode:
    utils.print_out("# External evaluation, global step %d" % global_step)

  sess.run(iterator.initializer, feed_dict=iterator_feed_dict)

  output = os.path.join(out_dir, "output_%s" % label)
  scores = nmt_utils.decode_and_evaluate(
      label,
      model,
      sess,
      output,
      ref_file=tgt_file,
      metrics=hparams.metrics,
      subword_option=hparams.subword_option,
      beam_width=hparams.beam_width,
      tgt_eos=hparams.eos,
      decode=decode,
      infer_mode=hparams.infer_mode)
  # Save on best metrics
  if decode:
    for metric in hparams.metrics:
      if avg_ckpts:
        best_metric_label = "avg_best_" + metric
      else:
        best_metric_label = "best_" + metric

      utils.add_summary(summary_writer, global_step, "%s_%s" % (label, metric),
                        scores[metric])
      # metric: larger is better
      if save_on_best and scores[metric] > getattr(hparams, best_metric_label):
        setattr(hparams, best_metric_label, scores[metric])
        model.saver.save(
            sess,
            os.path.join(
                getattr(hparams, best_metric_label + "_dir"), "translate.ckpt"),
            global_step=model.global_step)
    utils.save_hparams(out_dir, hparams)
  return scores