tensorflow/models · error · ValueError

Unrecognized `input_type`

Error message

Unrecognized `input_type`

What it means

Error "Unrecognized `input_type`" thrown in tensorflow/models.

Source

Thrown at official/vision/serving/video_classification.py:186

                dtype=tf.uint8,
                name='INPUT_FRAMES'),
            tf.TensorSpec(
                shape=[self._batch_size] +
                self.params.task.train_data.audio_feature_shape,
                dtype=tf.float32,
                name='INPUT_AUDIO')
        ]
        signatures[
            def_name] = self.inference_from_image_audio_tensors.get_concrete_function(
                input_signature)
      elif key == 'serve_examples' or key == 'tf_example':
        input_signature = tf.TensorSpec(
            shape=[self._batch_size], dtype=tf.string)
        signatures[
            def_name] = self.inference_from_tf_example.get_concrete_function(
                input_signature)
      else:
        raise ValueError('Unrecognized `input_type`')
    return signatures

View on GitHub (pinned to e006f5f0d5)

Solutions

1. Set input_type to 'image_tensor' or 'tf_example' as supported by video classification serving.
2. Check the serving input_type config for typos.

When it happens

Trigger: Thrown at official/vision/serving/video_classification.py:186 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/61556f9371b28a39. Report an issue: GitHub.