tensorflow/models · error · ValueError

Only 'all' or 'backbone' can be used to initialize the model

Error message

Only 'all' or 'backbone' can be used to initialize the model.

What it means

Error "Only 'all' or 'backbone' can be used to initialize the model." thrown in tensorflow/models.

Source

Thrown at official/projects/centernet/tasks/centernet.py:168

    if not self.task_config.init_checkpoint:
      return

    ckpt_dir_or_file = self.task_config.init_checkpoint

    # Restoring checkpoint.
    if tf.io.gfile.isdir(ckpt_dir_or_file):
      ckpt_dir_or_file = tf.train.latest_checkpoint(ckpt_dir_or_file)

    if self.task_config.init_checkpoint_modules == 'all':
      ckpt = tf.train.Checkpoint(**model.checkpoint_items)
      status = ckpt.restore(ckpt_dir_or_file)
      status.assert_consumed()
    elif self.task_config.init_checkpoint_modules == 'backbone':
      ckpt = tf.train.Checkpoint(backbone=model.backbone)
      status = ckpt.restore(ckpt_dir_or_file)
      status.expect_partial().assert_existing_objects_matched()
    else:
      raise ValueError(
          "Only 'all' or 'backbone' can be used to initialize the model.")

    logging.info('Finished loading pretrained checkpoint from %s',
                 ckpt_dir_or_file)

  def build_losses(self,
                   outputs,
                   labels,
                   aux_losses=None):
    """Build losses."""
    input_size = self.task_config.model.input_size[0:2]
    output_size = outputs['ct_heatmaps'][0].get_shape().as_list()[1:3]

    gt_label = tf.map_fn(
        # pylint: disable=g-long-lambda
        fn=lambda x: target_assigner.assign_centernet_targets(
            labels=x,
            input_size=input_size,

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/centernet/tasks/centernet.py:168 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/8c173f29de8dfb40. Report an issue: GitHub.