tensorflow/models · error · ValueError

Groundtruth mask must have only 1 layer if using categorical

Error message

Groundtruth mask must have only 1 layer if using categoricalcross entropy, but got {} layers.

What it means

Error "Groundtruth mask must have only 1 layer if using categoricalcross entropy, but got {} layers." thrown in tensorflow/models.

Source

Thrown at official/vision/losses/segmentation_losses.py:80

    """Computes `SegmentationLoss`.

    Args:
      logits: A float tensor in shape (batch_size, height, width, num_classes)
        which is the output of the network.
      labels: A tensor in shape (batch_size, height, width, num_layers), which
        is the label masks of the ground truth. The num_layers can be > 1 if the
        pixels are labeled as multiple classes.
      **kwargs: additional keyword arguments.

    Returns:
       A 0-D float which stores the overall loss of the batch.
    """
    _, height, width, num_classes = logits.get_shape().as_list()
    output_dtype = logits.dtype
    num_layers = labels.get_shape().as_list()[-1]
    if not self._use_binary_cross_entropy:
      if num_layers > 1:
        raise ValueError(
            'Groundtruth mask must have only 1 layer if using categorical'
            'cross entropy, but got {} layers.'.format(num_layers))
    if self._gt_is_matting_map:
      if num_classes != 2:
        raise ValueError(
            'Groundtruth matting map only supports 2 classes, but got {} '
            'classes.'.format(num_classes))
      if num_layers > 1:
        raise ValueError(
            'Groundtruth matting map must have only 1 layer, but got {} '
            'layers.'.format(num_layers))

    class_weights = (
        self._class_weights if self._class_weights else [1] * num_classes)
    if num_classes != len(class_weights):
      raise ValueError(
          'Length of class_weights should be {}'.format(num_classes))
    class_weights = tf.constant(class_weights, dtype=output_dtype)

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/vision/losses/segmentation_losses.py:80 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/9c93a48adec984f5. Report an issue: GitHub.