tensorflow/models · error · ValueError

`class_agnostic_bbox_pred` needs to be True if multiple dete

Error message

`class_agnostic_bbox_pred` needs to be True if multiple detection heads are specified.

What it means

Error "`class_agnostic_bbox_pred` needs to be True if multiple detection heads are specified." thrown in tensorflow/models.

Source

Thrown at official/vision/modeling/maskrcnn_model.py:120

        'max_level': max_level,
        'num_scales': num_scales,
        'aspect_ratios': aspect_ratios,
        'anchor_size': anchor_size,
    }
    self.backbone = backbone
    self.decoder = decoder
    self.rpn_head = rpn_head
    if not isinstance(detection_head, (list, tuple)):
      self.detection_head = [detection_head]
    else:
      self.detection_head = detection_head
    self.roi_generator = roi_generator
    if not isinstance(roi_sampler, (list, tuple)):
      self.roi_sampler = [roi_sampler]
    else:
      self.roi_sampler = roi_sampler
    if len(self.roi_sampler) > 1 and not class_agnostic_bbox_pred:
      raise ValueError(
          '`class_agnostic_bbox_pred` needs to be True if multiple detection heads are specified.'
      )
    self.roi_aligner = roi_aligner
    self.detection_generator = detection_generator
    self._include_mask = mask_head is not None
    if outer_boxes_scale < 1.0:
      raise ValueError('`outer_boxes_scale` should be a value >= 1.0.')
    self.outer_boxes_scale = outer_boxes_scale
    self.mask_head = mask_head
    if self._include_mask and mask_sampler is None:
      raise ValueError('`mask_sampler` is not provided in Mask R-CNN.')
    self.mask_sampler = mask_sampler
    if self._include_mask and mask_roi_aligner is None:
      raise ValueError('`mask_roi_aligner` is not provided in Mask R-CNN.')
    self.mask_roi_aligner = mask_roi_aligner
    # Weights for the regression losses for each FRCNN layer.
    # TODO(jiageng): Make the weights configurable.
    self._cascade_layer_to_weights = [

View on GitHub (pinned to e006f5f0d5)

Solutions

1. Set class_agnostic_bbox_pred to True when multiple detection heads are configured.
2. Reduce to a single detection head if you need per-class box prediction.

When it happens

Trigger: Thrown at official/vision/modeling/maskrcnn_model.py:120 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/52e945258add302e. Report an issue: GitHub.