Python eval_classification.eval_nested_kfold方法代碼示例

本文整理匯總了Python中skipthoughts.eval_classification.eval_nested_kfold方法的典型用法代碼示例。如果您正苦於以下問題：Python eval_classification.eval_nested_kfold方法的具體用法？Python eval_classification.eval_nested_kfold怎麽用？Python eval_classification.eval_nested_kfold使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類skipthoughts.eval_classification的用法示例。

在下文中一共展示了eval_classification.eval_nested_kfold方法的2個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。

示例1: main

# 需要導入模塊: from skipthoughts import eval_classification [as 別名]
# 或者: from skipthoughts.eval_classification import eval_nested_kfold [as 別名]
def main(unused_argv):
  if not FLAGS.data_dir:
    raise ValueError("--data_dir is required.")

  encoder = encoder_manager.EncoderManager()

  # Maybe load unidirectional encoder.
  if FLAGS.uni_checkpoint_path:
    print("Loading unidirectional model...")
    uni_config = configuration.model_config()
    encoder.load_model(uni_config, FLAGS.uni_vocab_file,
                       FLAGS.uni_embeddings_file, FLAGS.uni_checkpoint_path)

  # Maybe load bidirectional encoder.
  if FLAGS.bi_checkpoint_path:
    print("Loading bidirectional model...")
    bi_config = configuration.model_config(bidirectional_encoder=True)
    encoder.load_model(bi_config, FLAGS.bi_vocab_file, FLAGS.bi_embeddings_file,
                       FLAGS.bi_checkpoint_path)

  if FLAGS.eval_task in ["MR", "CR", "SUBJ", "MPQA"]:
    eval_classification.eval_nested_kfold(
        encoder, FLAGS.eval_task, FLAGS.data_dir, use_nb=False)
  elif FLAGS.eval_task == "SICK":
    eval_sick.evaluate(encoder, evaltest=True, loc=FLAGS.data_dir)
  elif FLAGS.eval_task == "MSRP":
    eval_msrp.evaluate(
        encoder, evalcv=True, evaltest=True, use_feats=True, loc=FLAGS.data_dir)
  elif FLAGS.eval_task == "TREC":
    eval_trec.evaluate(encoder, evalcv=True, evaltest=True, loc=FLAGS.data_dir)
  else:
    raise ValueError("Unrecognized eval_task: %s" % FLAGS.eval_task)

  encoder.close()

開發者ID:ringringyi，項目名稱:DOTA_models，代碼行數:36，代碼來源:evaluate.py

示例2: main

# 需要導入模塊: from skipthoughts import eval_classification [as 別名]
# 或者: from skipthoughts.eval_classification import eval_nested_kfold [as 別名]
def main(unused_argv):
    if not FLAGS.data_dir:
        raise ValueError("--data_dir is required.")

    encoder = encoder_manager.EncoderManager()

    # Maybe load unidirectional encoder.
    if FLAGS.uni_checkpoint_path:
        print("Loading unidirectional model...")
        uni_config = configuration.model_config()
        encoder.load_model(uni_config, FLAGS.uni_vocab_file,
                           FLAGS.uni_embeddings_file, FLAGS.uni_checkpoint_path)

    # Maybe load bidirectional encoder.
    if FLAGS.bi_checkpoint_path:
        print("Loading bidirectional model...")
        bi_config = configuration.model_config(bidirectional_encoder=True)
        encoder.load_model(bi_config, FLAGS.bi_vocab_file,
                           FLAGS.bi_embeddings_file,
                           FLAGS.bi_checkpoint_path)

    if FLAGS.eval_task in ["MR", "CR", "SUBJ", "MPQA"]:
        eval_classification.eval_nested_kfold(
            encoder, FLAGS.eval_task, FLAGS.data_dir, use_nb=False)
    elif FLAGS.eval_task == "SICK":
        eval_sick.evaluate(encoder, evaltest=True, loc=FLAGS.data_dir)
    elif FLAGS.eval_task == "MSRP":
        eval_msrp.evaluate(
            encoder, evalcv=True, evaltest=True, use_feats=True,
            loc=FLAGS.data_dir)
    elif FLAGS.eval_task == "TREC":
        eval_trec.evaluate(encoder, evalcv=True, evaltest=True,
                           loc=FLAGS.data_dir)
    else:
        raise ValueError("Unrecognized eval_task: %s" % FLAGS.eval_task)

    encoder.close()

開發者ID:snuspl，項目名稱:parallax，代碼行數:39，代碼來源:evaluate.py

注：本文中的skipthoughts.eval_classification.eval_nested_kfold方法示例由純淨天空整理自Github/MSDocs等開源代碼及文檔管理平台，相關代碼片段篩選自各路編程大神貢獻的開源項目，源碼版權歸原作者所有，傳播和使用請參考對應項目的License；未經允許，請勿轉載。