tensorflow/models · error · ValueError

You must specify a temporary directory, either in params.inp

Error message

You must specify a temporary directory, either in params.input_preprocessed_data_path or logging_dir to store intermediate evaluation TFRecord data.

What it means

Error "You must specify a temporary directory, either in params.input_preprocessed_data_path or logging_dir to store intermediate evaluation TFRecord data." thrown in tensorflow/models.

Source

Thrown at official/nlp/tasks/question_answering.py:140

    start_loss = tf_keras.losses.sparse_categorical_crossentropy(
        start_positions,
        tf.cast(start_logits, dtype=tf.float32),
        from_logits=True)
    end_loss = tf_keras.losses.sparse_categorical_crossentropy(
        end_positions, tf.cast(end_logits, dtype=tf.float32), from_logits=True)

    loss = (tf.reduce_mean(start_loss) + tf.reduce_mean(end_loss)) / 2
    return loss

  def _preprocess_eval_data(self, params):
    eval_examples = self.squad_lib.read_squad_examples(
        input_file=params.input_path,
        is_training=False,
        version_2_with_negative=params.version_2_with_negative)

    temp_file_path = params.input_preprocessed_data_path or self.logging_dir
    if not temp_file_path:
      raise ValueError('You must specify a temporary directory, either in '
                       'params.input_preprocessed_data_path or logging_dir to '
                       'store intermediate evaluation TFRecord data.')
    eval_writer = self.squad_lib.FeatureWriter(
        filename=os.path.join(temp_file_path, 'eval.tf_record'),
        is_training=False)
    eval_features = []

    def _append_feature(feature, is_padding):
      if not is_padding:
        eval_features.append(feature)
      eval_writer.process_feature(feature)

    # XLNet preprocesses SQuAD examples in a P, Q, class order whereas
    # BERT preprocesses in a class, Q, P order.
    xlnet_ordering = self.task_config.model.encoder.type == 'xlnet'
    kwargs = dict(
        examples=eval_examples,
        max_seq_length=params.seq_length,

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/nlp/tasks/question_answering.py:140 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of tensorflow/models@e006f5f0d5 (2026-08-24). Data as JSON: /api/errors/9a61216c4e0c4f59. Report an issue: GitHub.