tensorflow/models · error · ValueError

Augmentation policy {} not supported.

Error message

Augmentation policy {} not supported.

What it means

Error "Augmentation policy {} not supported." thrown in tensorflow/models.

Source

Thrown at official/projects/maskconver/dataloaders/multiscale_maskconver_input.py:176

    self._aug_scale_max = aug_scale_max
    self._segmentation_ignore_label = segmentation_ignore_label
    self._panoptic_ignore_label = panoptic_ignore_label
    self.level = level
    self._mask_target_level = mask_target_level
    self._num_panoptic_categories = num_panoptic_categories
    self._num_thing_categories = num_thing_categories
    self._gaussian_iou = gaussian_iou
    self.fpn_low_range = fpn_low_range
    self.fpn_high_range = fpn_high_range

    if aug_type and aug_type.type:
      if aug_type.type == 'autoaug':
        self._augmenter = augment.AutoAugment(
            augmentation_name=aug_type.autoaug.augmentation_name,
            cutout_const=aug_type.autoaug.cutout_const,
            translate_const=aug_type.autoaug.translate_const)
      else:
        raise ValueError('Augmentation policy {} not supported.'.format(
            aug_type.type))
    else:
      self._augmenter = None

  def _parse_train_data(self, data):
    """Parses data for training.

    Args:
      data: the decoded tensor dictionary from TfExampleDecoder.

    Returns:
      image: image tensor that is preproessed to have normalized value and
        dimension [output_size[0], output_size[1], 3]
      labels: a dictionary of tensors used for training. The following describes
        {key: value} pairs in the dictionary.
    """
    # Flips image randomly during training.
    if self.aug_rand_hflip:

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/maskconver/dataloaders/multiscale_maskconver_input.py:176 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/9647b06933fb5bbc. Report an issue: GitHub.