tensorflow/models · error · ValueError

Results do not correspond to the current dataset!

Error message

Results do not correspond to the current dataset!

What it means

Consistency guard in the COCO loadRes path: the prediction results contain image ids that are not present in the ground-truth dataset's image set, so the predictions cannot correspond to the loaded annotations. It fires when predictions come from a different dataset/ split than the annotation file or gt_dataset used for evaluation.

Solutions

  1. Regenerate predictions on the same dataset/ split as the ground-truth annotations
  2. Verify image id mapping and that no predictions reference excluded images
Defensive patterns

Strategy: validation

When it happens

Trigger: Thrown at official/legacy/detection/evaluation/coco_utils.py:93 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/4275819049633bfa. Report an issue: GitHub.

Appendix: source

Thrown at official/legacy/detection/evaluation/coco_utils.py:93

    Args:
      predictions: a list of dictionary each representing an annotation in COCO
        format. The required fields are `image_id`, `category_id`, `score`,
        `bbox`, `segmentation`.

    Returns:
      res: result COCO api object.

    Raises:
      ValueError: if the set of image id from predctions is not the subset of
        the set of image id of the groundtruth dataset.
    """
    res = coco.COCO()
    res.dataset['images'] = copy.deepcopy(self.dataset['images'])
    res.dataset['categories'] = copy.deepcopy(self.dataset['categories'])

    image_ids = [ann['image_id'] for ann in predictions]
    if set(image_ids) != (set(image_ids) & set(self.getImgIds())):
      raise ValueError('Results do not correspond to the current dataset!')
    for ann in predictions:
      x1, x2, y1, y2 = [ann['bbox'][0], ann['bbox'][0] + ann['bbox'][2],
                        ann['bbox'][1], ann['bbox'][1] + ann['bbox'][3]]
      if self._eval_type == 'box':
        ann['area'] = ann['bbox'][2] * ann['bbox'][3]
        ann['segmentation'] = [
            [x1, y1, x1, y2, x2, y2, x2, y1]]
      elif self._eval_type == 'mask':
        ann['area'] = mask_api.area(ann['segmentation'])

    res.dataset['annotations'] = copy.deepcopy(predictions)
    res.createIndex()
    return res


def convert_predictions_to_coco_annotations(predictions):
  """Converts a batch of predictions to annotations in COCO format.

View on GitHub (pinned to e006f5f0d5)