tensorflow/models · error · ValueError

The min_level must be >= 1, but {} found.

Error message

The min_level must be >= 1, but {} found.

What it means

Error "The min_level must be >= 1, but {} found." thrown in tensorflow/models.

Source

Thrown at official/projects/pointpillars/modeling/backbones.py:72

        Conv2D. Default to None.
      **kwargs: Additional keyword arguments to be passed.

    Returns:
      endpoints: A `dict` of {level: Tensor} pairs for the model output.
      output_specs: A dict of {level: TensorShape} pairs for the model output.
    """
    utils.assert_channels_last()

    self._config_dict = {
        'input_specs': input_specs,
        'min_level': min_level,
        'max_level': max_level,
        'num_convs': num_convs,
        'kernel_regularizer': kernel_regularizer,
    }
    # Onlly allow to output from level 1.
    if min_level < 1:
      raise ValueError(
          'The min_level must be >= 1, but {} found.'.format(min_level))

    input_channels = input_specs[-1]
    inputs = tf_keras.Input(shape=input_specs[1:])

    # build the net
    x = inputs
    net = {}
    scale = 1
    for level in range(1, max_level + 1):
      x = self._block_group(
          inputs=x,
          filters=input_channels * scale)
      scale *= 2
      net[level] = x

    # build endpoints
    endpoints = {}

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/pointpillars/modeling/backbones.py:72 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/709495eaeb3c67f1. Report an issue: GitHub.