tensorflow/models · error · ValueError

Only 'all', 'backbone', 'decoder', 'segmentation_backbone' a

Error message

Only 'all', 'backbone', 'decoder', 'segmentation_backbone' and/or 'segmentation_decoder' can be used to initialize the model, but got {}

What it means

Error "Only 'all', 'backbone', 'decoder', 'segmentation_backbone' and/or 'segmentation_decoder' can be used to initialize the model, but got {}" thrown in tensorflow/models.

Source

Thrown at official/projects/panoptic/tasks/panoptic_maskrcnn.py:139

      elif init_module == 'segmentation_backbone':
        checkpoint_path = _get_checkpoint_path(
            self.task_config.segmentation_init_checkpoint)
        ckpt = tf.train.Checkpoint(
            segmentation_backbone=model.segmentation_backbone)
        status = ckpt.read(checkpoint_path)
        status.expect_partial().assert_existing_objects_matched()

      elif init_module == 'segmentation_decoder':
        checkpoint_path = _get_checkpoint_path(
            self.task_config.segmentation_init_checkpoint)
        ckpt = tf.train.Checkpoint(
            segmentation_decoder=model.segmentation_decoder)
        status = ckpt.read(checkpoint_path)
        status.expect_partial().assert_existing_objects_matched()

      else:
        raise ValueError(
            "Only 'all', 'backbone', 'decoder', 'segmentation_backbone' and/or "
            "'segmentation_decoder' can be used to initialize the model, but "
            "got {}".format(init_module))
      logging.info('Finished loading pretrained checkpoint from %s for %s',
                   checkpoint_path, init_module)

  def build_inputs(
      self,
      params: exp_cfg.DataConfig,
      input_context: Optional[tf.distribute.InputContext] = None
  ) -> tf.data.Dataset:
    """Builds input dataset."""
    decoder_cfg = params.decoder.get()
    if params.decoder.type == 'simple_decoder':
      decoder = panoptic_maskrcnn_input.TfExampleDecoder(
          regenerate_source_id=decoder_cfg.regenerate_source_id,
          mask_binarize_threshold=decoder_cfg.mask_binarize_threshold,
          include_panoptic_masks=decoder_cfg.include_panoptic_masks,

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/panoptic/tasks/panoptic_maskrcnn.py:139 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/8afcd2cf14461998. Report an issue: GitHub.