tensorflow/models · error · ValueError

Invalid augmentation_name: {}

Error message

Invalid augmentation_name: {}

What it means

Error "Invalid augmentation_name: {}" thrown in tensorflow/models.

Source

Thrown at official/vision/ops/augment.py:1985

    self.augmentation_name = augmentation_name
    self.cutout_const = float(cutout_const)
    self.translate_const = float(translate_const)
    self.available_policies = {
        'detection_v0': self.detection_policy_v0(),
        'v0': self.policy_v0(),
        'test': self.policy_test(),
        'simple': self.policy_simple(),
        'reduced_cifar10': self.policy_reduced_cifar10(),
        'svhn': self.policy_svhn(),
        'reduced_imagenet': self.policy_reduced_imagenet(),
        'panoptic_deeplab_policy': self.panoptic_deeplab_policy(),
        'vit': self.vit(),
        'deit3_three_augment': self.deit3_three_augment(),
    }

    if not policies:
      if augmentation_name not in self.available_policies:
        raise ValueError(
            'Invalid augmentation_name: {}'.format(augmentation_name))

      self.policies = self.available_policies[augmentation_name]

    else:
      self._check_policy_shape(policies)
      self.policies = policies

  def _check_policy_shape(self, policies):
    """Checks dimension and shape of the custom policy.

    Args:
      policies: List of list of tuples in the form `(func, prob, level)`. Must
        have shape of `(:, :, 3)`.

    Raises:
      ValueError if the shape of `policies` is unexpected.
    """

View on GitHub (pinned to e006f5f0d5)

Solutions

  1. Use one of the supported augmentation names listed in the augmentation registry.
  2. Check the augmentation_name in the config for typos.

When it happens

Trigger: Thrown at official/vision/ops/augment.py:1985 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/9a6003d0e4812090. Report an issue: GitHub.