What causes "Detection with center point is only available " in tensorflow/models?

Detection with center point is only available

Error message

Detection with center point is only available

What it means

Error "Detection with center point is only available " thrown in tensorflow/models.

Source

Thrown at official/projects/centernet/configs/centernet.py:180

  losses: Losses = dataclasses.field(default_factory=Losses)
  gradient_clip_norm: float = 10.0
  per_category_metrics: bool = False
  weight_decay: float = 5e-4
  # Load checkpoints
  init_checkpoint: Optional[str] = None
  init_checkpoint_modules: str = 'all'
  annotation_file: Optional[str] = None

  def get_output_length_dict(self):
    task_outputs = {}
    if self.subtasks.detection and self.subtasks.detection.use_centers:
      task_outputs.update({
          'ct_heatmaps': self.model.num_classes,
          'ct_offset': 2,
          'ct_size': 2
      })
    else:
      raise ValueError('Detection with center point is only available ')
    return task_outputs


COCO_INPUT_PATH_BASE = 'coco'
COCO_TRAIN_EXAMPLES = 118287
COCO_VAL_EXAMPLES = 5000


@exp_factory.register_config_factory('centernet_hourglass_coco')
def centernet_hourglass_coco() -> cfg.ExperimentConfig:
  """COCO object detection with CenterNet."""
  train_batch_size = 128
  eval_batch_size = 8
  steps_per_epoch = COCO_TRAIN_EXAMPLES // train_batch_size

  config = cfg.ExperimentConfig(
      task=CenterNetTask(
          annotation_file=os.path.join(COCO_INPUT_PATH_BASE,

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/centernet/configs/centernet.py:180 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/887b68450d00048a. Report an issue: GitHub.