tensorflow/models · error · ValueError

Export module not implemented for {} task.

Error message

Export module not implemented for {} task.

What it means

Error "Export module not implemented for {} task." thrown in tensorflow/models.

Source

Thrown at official/vision/serving/export_module_factory.py:87

                                           model=model,
                                           input_signature=input_signature,
                                           preprocessor=preprocess_fn,
                                           postprocessor=postprocess_fn)
  return export_module


def get_export_module(params: cfg.ExperimentConfig,
                      input_type: str,
                      batch_size: Optional[int],
                      input_image_size: List[int],
                      num_channels: int = 3) -> export_base.ExportModule:
  """Factory for export modules."""
  if isinstance(params.task,
                configs.image_classification.ImageClassificationTask):
    export_module = create_classification_export_module(
        params, input_type, batch_size, input_image_size, num_channels)
  else:
    raise ValueError('Export module not implemented for {} task.'.format(
        type(params.task)))
  return export_module

View on GitHub (pinned to e006f5f0d5)

Solutions

1. Use a supported task for export (e.g. 'classification', 'detection', 'segmentation').
2. Register an export module for your custom task in the factory.

When it happens

Trigger: Thrown at official/vision/serving/export_module_factory.py:87 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/b62ac776d6a58040. Report an issue: GitHub.