tensorflow/models · error · ValueError

Image rank 4 is not supported

Error message

Image rank 4 is not supported

What it means

Error "Image rank 4 is not supported" thrown in tensorflow/models.

Source

Thrown at official/vision/ops/augment.py:1262

    aug_func: Augmentation function that will be applied to the
      subsections of image indicated by the bbox values in bboxes.
    func_changes_bbox: Boolean. Does augmentation_func return bbox in addition
      to image.
    *args: Additional parameters that will be passed into augmentation_func
      when it is called.

  Returns:
    A modified version of image, where each bbox location in the image will
    have augmentation_func applied to it if it is chosen to be called with
    probability prob independently across all bboxes. Also the final
    bboxes are returned that will be unchanged if func_changes_bbox is set to
    false and if true, the new altered ones will be returned.

  Raises:
    ValueError if applied to video.
  """
  if image.shape.rank == 4:
    raise ValueError('Image rank 4 is not supported')

  # Will keep track of the new altered bboxes after aug_func is repeatedly
  # applied. The -1 values are a dummy value and this first Tensor will be
  # removed upon appending the first real bbox.
  new_bboxes = tf.constant(_INVALID_BOX)

  # If the bboxes are empty, then just give it _INVALID_BOX. The result
  # will be thrown away.
  bboxes = tf.cond(tf.equal(tf.size(bboxes), 0),
                   lambda: tf.constant(_INVALID_BOX),
                   lambda: bboxes)

  bboxes = tf.ensure_shape(bboxes, (None, 4))

  # pylint:disable=g-long-lambda
  wrapped_aug_func = (
      lambda _image, bbox, _new_bboxes: _apply_bbox_augmentation_wrapper(
          _image, bbox, _new_bboxes, prob, aug_func, func_changes_bbox, *args))

View on GitHub (pinned to e006f5f0d5)

Solutions

1. Process images one at a time (rank 3); this op does not accept a batched rank-4 image.
2. Loop over the batch or use a batched-compatible augmentation op.

When it happens

Trigger: Thrown at official/vision/ops/augment.py:1262 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/7a467bd964ed0c63. Report an issue: GitHub.