tensorflow/models · error · ValueError

Missing the required key `{}` in predictions!

Error message

Missing the required key `{}` in predictions!

What it means

Error "Missing the required key `{}` in predictions!" thrown in tensorflow/models.

Source

Thrown at official/vision/evaluation/panoptic_quality_evaluator.py:155

          [y_scale, x_scale], [y_offset, x_offset]], where [desired_height,
          desired_width] is the actual scaled image size, and [y_scale, x_scale]
          is the scaling factor, which is the ratio of scaled dimension /
          original dimension.
      predictions: a dictionary of tensors including the fields below. See
        different parsers under `../dataloader` for more details.
        Required fields:
          - category_mask: a numpy array of uint16 of shape [batch_size, H, W].
          - instance_mask: a numpy array of uint16 of shape [batch_size, H, W].

    Raises:
      ValueError: if the required prediction or ground-truth fields are not
        present in the incoming `predictions` or `groundtruths`.
    """
    groundtruths, predictions = self._convert_to_numpy(groundtruths,
                                                       predictions)
    for k in self._required_prediction_fields:
      if k not in predictions:
        raise ValueError(
            'Missing the required key `{}` in predictions!'.format(k))

    for k in self._required_groundtruth_fields:
      if k not in groundtruths:
        raise ValueError(
            'Missing the required key `{}` in groundtruths!'.format(k))

    if self._rescale_predictions:
      for idx in range(len(groundtruths['category_mask'])):
        image_info = groundtruths['image_info'][idx]
        groundtruths_ = {
            'category_mask':
                _crop_padding(groundtruths['category_mask'][idx], image_info),
            'instance_mask':
                _crop_padding(groundtruths['instance_mask'][idx], image_info),
            }
        predictions_ = {
            'category_mask':

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/vision/evaluation/panoptic_quality_evaluator.py:155 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/96e4dda73668801f. Report an issue: GitHub.