tensorflow/models · error · ValueError

Mobile SpineNet-{} is not a valid architecture.

Error message

Mobile SpineNet-{} is not a valid architecture.

What it means

Error "Mobile SpineNet-{} is not a valid architecture." thrown in tensorflow/models.

Source

Thrown at official/vision/modeling/backbones/spinenet_mobile.py:526

    """A dict of {level: TensorShape} pairs for the model output."""
    return self._output_specs


@factory.register_backbone_builder('spinenet_mobile')
def build_spinenet_mobile(
    input_specs: tf_keras.layers.InputSpec,
    backbone_config: hyperparams.Config,
    norm_activation_config: hyperparams.Config,
    l2_regularizer: tf_keras.regularizers.Regularizer = None) -> tf_keras.Model:
  """Builds Mobile SpineNet backbone from a config."""
  backbone_type = backbone_config.type
  backbone_cfg = backbone_config.get()
  assert backbone_type == 'spinenet_mobile', (f'Inconsistent backbone type '
                                              f'{backbone_type}')

  model_id = backbone_cfg.model_id
  if model_id not in SCALING_MAP:
    raise ValueError(
        'Mobile SpineNet-{} is not a valid architecture.'.format(model_id))
  scaling_params = SCALING_MAP[model_id]

  return SpineNetMobile(
      input_specs=input_specs,
      min_level=backbone_cfg.min_level,
      max_level=backbone_cfg.max_level,
      endpoints_num_filters=scaling_params['endpoints_num_filters'],
      block_repeats=scaling_params['block_repeats'],
      filter_size_scale=scaling_params['filter_size_scale'],
      se_ratio=backbone_cfg.se_ratio,
      expand_ratio=backbone_cfg.expand_ratio,
      init_stochastic_depth_rate=backbone_cfg.stochastic_depth_drop_rate,
      kernel_regularizer=l2_regularizer,
      activation=norm_activation_config.activation,
      use_sync_bn=norm_activation_config.use_sync_bn,
      norm_momentum=norm_activation_config.norm_momentum,
      norm_epsilon=norm_activation_config.norm_epsilon,

View on GitHub (pinned to e006f5f0d5)

Solutions

1. Use a valid mobile SpineNet architecture id such as '49' or '49S' (mobile variants).
2. Check the model_id in the SpineNetMobile backbone config for typos.

When it happens

Trigger: Thrown at official/vision/modeling/backbones/spinenet_mobile.py:526 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/1948322e4fbab85d. Report an issue: GitHub.