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/maskconver_segmentation_input.py:104

        aug_rand_hflip=aug_rand_hflip,
        preserve_aspect_ratio=preserve_aspect_ratio,
        aug_scale_min=aug_scale_min,
        aug_scale_max=aug_scale_max)

    self._num_classes = num_classes
    self.level = level
    self._gaussian_iou = gaussian_iou
    self._max_num_stuff_centers = max_num_stuff_centers
    self._max_num_instances = max_num_instances

    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 _prepare_image_and_label(self, data, use_augment=False):
    """Prepare normalized image and label."""
    image = tf.io.decode_image(data['image/encoded'], channels=3)
    label = tf.io.decode_image(data['image/segmentation/class/encoded'],
                               channels=1)
    height = data['image/height']
    width = data['image/width']
    image = tf.reshape(image, (height, width, 3))

    label = tf.reshape(label, (1, height, width))
    label = tf.cast(label, tf.float32)

    if use_augment and self._augmenter is not None:
      image = self._augmenter.distort(image)

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/maskconver/dataloaders/maskconver_segmentation_input.py:104 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/a038445169c20e2c. Report an issue: GitHub.