tensorflow/models · error · ValueError

Unsupported head type: {}

Error message

Unsupported head type: {}

What it means

Error "Unsupported head type: {}" thrown in tensorflow/models.

Source

Thrown at official/projects/pointpillars/modeling/heads.py:119

        kernel_regularizer=self._config_dict['kernel_regularizer'],
        bias_initializer=tf.constant_initializer(-np.log((1 - 0.01) / 0.01)))
    self._box_regressor = tf_keras.layers.Conv2D(
        filters=(self._config_dict['num_params_per_anchor'] *
                 self._config_dict['num_anchors_per_location']),
        kernel_size=3,
        strides=1,
        padding='same',
        kernel_initializer=tf_keras.initializers.RandomNormal(stddev=1e-5),
        kernel_regularizer=self._config_dict['kernel_regularizer'],
        bias_initializer=tf.zeros_initializer())
    if self._config_dict['attribute_heads']:
      self._att_predictors = {}
      for att_config in self._config_dict['attribute_heads']:
        att_name = att_config['name']
        att_type = att_config['type']
        att_size = att_config['size']
        if att_type != 'regression':
          raise ValueError('Unsupported head type: {}'.format(att_type))
        self._att_predictors[att_name] = tf_keras.layers.Conv2D(
            filters=(att_size * self._config_dict['num_anchors_per_location']),
            kernel_size=3,
            strides=1,
            padding='same',
            kernel_initializer=tf_keras.initializers.RandomNormal(stddev=1e-5),
            kernel_regularizer=self._config_dict['kernel_regularizer'],
            bias_initializer=tf.zeros_initializer())

    super(SSDHead, self).build(input_specs)

  def call(
      self, inputs: Mapping[str, tf.Tensor]
  ) -> Tuple[Dict[str, Any], Dict[str, Any], Dict[Any, Dict[str, Any]]]:
    # Build multi level features.
    feats = {}
    for level in range(self._decoder_output_level,
                       self._config_dict['max_level'] + 1):

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/pointpillars/modeling/heads.py:119 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/ecf913361e6e7a94. Report an issue: GitHub.