tensorflow/models · error · ValueError

Backbone depth should be equal to 3D UNet decoder's depth.

Error message

Backbone depth should be equal to 3D UNet decoder's depth.

What it means

Error "Backbone depth should be equal to 3D UNet decoder's depth." thrown in tensorflow/models.

Source

Thrown at official/projects/volumetric_models/modeling/decoders/unet_3d_decoder.py:139

          kernel_regularizer=kernel_regularizer,
          activation=activation,
          use_sync_bn=use_sync_bn,
          norm_momentum=norm_momentum,
          norm_epsilon=norm_epsilon,
          use_batch_normalization=use_batch_normalization)(
              x)

    feats = {'1': x}
    self._output_specs = {l: feats[l].get_shape() for l in feats}

    super(UNet3DDecoder, self).__init__(inputs=inputs, outputs=feats, **kwargs)

  def _build_input_pyramid(self, input_specs: Dict[str, tf.TensorShape],
                           depth: int) -> Dict[str, tf.Tensor]:
    """Builds input pyramid features."""
    assert isinstance(input_specs, dict)
    if len(input_specs.keys()) > depth:
      raise ValueError(
          'Backbone depth should be equal to 3D UNet decoder\'s depth.')

    inputs = {}
    for level, spec in input_specs.items():
      inputs[level] = tf_keras.Input(shape=spec[1:])
    return inputs

  def get_config(self) -> Mapping[str, Any]:
    return self._config_dict

  @classmethod
  def from_config(cls, config: Mapping[str, Any], custom_objects=None):
    return cls(**config)

  @property
  def output_specs(self) -> Mapping[str, tf.TensorShape]:
    """A dict of {level: TensorShape} pairs for the model output."""
    return self._output_specs

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/volumetric_models/modeling/decoders/unet_3d_decoder.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/9278d097d8956d78. Report an issue: GitHub.