tensorflow/models · error · ValueError

Unknown `output` value "%s". `output` can be either "logits"

Error message

Unknown `output` value "%s". `output` can be either "logits" or "predictions"

What it means

Error "Unknown `output` value "%s". `output` can be either "logits" or "predictions"" thrown in tensorflow/models.

Source

Thrown at official/nlp/modeling/networks/span_labeling.py:73

    intermediate_logits = tf_keras.layers.Dense(
        2,  # This layer predicts start location and end location.
        activation=activation,
        kernel_initializer=initializer,
        name='predictions/transform/logits')(
            sequence_data)
    start_logits, end_logits = self._split_output_tensor(intermediate_logits)

    start_predictions = tf_keras.layers.Activation(tf.nn.log_softmax)(
        start_logits)
    end_predictions = tf_keras.layers.Activation(tf.nn.log_softmax)(end_logits)

    if output == 'logits':
      output_tensors = [start_logits, end_logits]
    elif output == 'predictions':
      output_tensors = [start_predictions, end_predictions]
    else:
      raise ValueError(
          ('Unknown `output` value "%s". `output` can be either "logits" or '
           '"predictions"') % output)

    # b/164516224
    # Once we've created the network using the Functional API, we call
    # super().__init__ as though we were invoking the Functional API Model
    # constructor, resulting in this object having all the properties of a model
    # created using the Functional API. Once super().__init__ is called, we
    # can assign attributes to `self` - note that all `self` assignments are
    # below this line.
    super().__init__(
        inputs=[sequence_data], outputs=output_tensors, **kwargs)
    config_dict = {
        'input_width': input_width,
        'activation': activation,
        'initializer': initializer,
        'output': output,
    }

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/nlp/modeling/networks/span_labeling.py:73 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/4e21c44af0f2f61d. Report an issue: GitHub.