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/vision/tasks/video_classification.py:101

    """Loads pretrained checkpoint."""
    if not self.task_config.init_checkpoint:
      return

    ckpt_dir_or_file = self.task_config.init_checkpoint
    if tf.io.gfile.isdir(ckpt_dir_or_file):
      ckpt_dir_or_file = tf.train.latest_checkpoint(ckpt_dir_or_file)

    # Restoring checkpoint.
    if self.task_config.init_checkpoint_modules == 'all':
      ckpt = tf.train.Checkpoint(model=model)
      status = ckpt.read(ckpt_dir_or_file)
      status.expect_partial().assert_existing_objects_matched()
    elif self.task_config.init_checkpoint_modules == 'backbone':
      ckpt = tf.train.Checkpoint(backbone=model.backbone)
      status = ckpt.read(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 _get_dataset_fn(self, params):
    if params.file_type == 'tfrecord':
      return tf.data.TFRecordDataset
    else:
      raise ValueError('Unknown input file type {!r}'.format(params.file_type))

  def _get_decoder_fn(self, params):
    if params.tfds_name:
      decoder = video_input.VideoTfdsDecoder(
          image_key=params.image_field_key, label_key=params.label_field_key)
    else:
      decoder = video_input.Decoder(
          image_key=params.image_field_key, label_key=params.label_field_key)

View on GitHub (pinned to e006f5f0d5)

Solutions

1. Set the initialization mode to 'all' or 'backbone' when loading video classification weights.
2. Check the init_checkpoint_modules config value.

When it happens

Trigger: Thrown at official/vision/tasks/video_classification.py:101 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/99154c76f911f4f5. Report an issue: GitHub.