tensorflow/models · error · ValueError

`TargetGather` does not support `labels` with rank larger th

Error message

`TargetGather` does not support `labels` with rank larger than 3, got {}

What it means

Error "`TargetGather` does not support `labels` with rank larger than 3, got {}" thrown in tensorflow/models.

Source

Thrown at official/vision/ops/target_gather.py:48

      labels: An integer tensor with shape [N, dims] or [B, N, ...] representing
        groundtruth labels.
      match_indices: An integer tensor with shape [M] or [B, M] representing
        match label index.
      mask: An boolean tensor with shape [M, dims] or [B, M,...] representing
        match labels.
      mask_val: An integer to fill in for mask.

    Returns:
      target: An integer Tensor with shape [M] or [B, M]
    Raises:
      ValueError: If `labels` is higher than rank 3.
    """
    if len(labels.shape) <= 2:
      return self._gather_unbatched(labels, match_indices, mask, mask_val)
    elif len(labels.shape) == 3:
      return self._gather_batched(labels, match_indices, mask, mask_val)
    else:
      raise ValueError("`TargetGather` does not support `labels` with rank "
                       "larger than 3, got {}".format(len(labels.shape)))

  def _gather_unbatched(self, labels, match_indices, mask, mask_val):
    """Gather based on unbatched labels and boxes."""
    num_gt_boxes = tf.shape(labels)[0]

    def _assign_when_rows_empty():
      if len(labels.shape) > 1:
        mask_shape = [match_indices.shape[0], labels.shape[-1]]
      else:
        mask_shape = [match_indices.shape[0]]
      return tf.cast(mask_val, labels.dtype) * tf.ones(
          mask_shape, dtype=labels.dtype)

    def _assign_when_rows_not_empty():
      targets = tf.gather(labels, match_indices)
      if mask is None:
        return targets

View on GitHub (pinned to e006f5f0d5)

Solutions

1. Pass labels with rank <= 3 to TargetGather.
2. Reduce the labels rank (merge extra leading axes) before gathering.

When it happens

Trigger: Thrown at official/vision/ops/target_gather.py:48 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/08e6a3a34fd81cdf. Report an issue: GitHub.