tensorflow/models · error · ValueError

The multi-level feature model

Error message

The multi-level feature model `{}` is not supported.

What it means

Dispatch guard in multilevel_features_generator: params.architecture.multilevel_features (filled into {}) is not a supported FPN style (e.g. 'fpn'), so no multi-level feature extractor function could be returned. The input at fault is the multilevel_features field of the architecture params.

Solutions

  1. Set architecture.multilevel_features to a supported value such as 'fpn'
  2. Verify the architecture section of the config for typos
Defensive patterns

Strategy: validation

When it happens

Trigger: Thrown at official/legaacy/detection/modeling/architecture/factory.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/37f5fd89e6a8c463. Report an issue: GitHub.

Appendix: source

Thrown at official/legacy/detection/modeling/architecture/factory.py:72:72

  else:
    raise ValueError('The multi-level feature model `{}` is not supported.'
                     .format(params.architecture.multilevel_features))
  return fpn_fn

View on GitHub (pinned to e006f5f0d5)