tensorflow/models · error · TypeError

`loss_fn` cannot be a Keras `Loss` object, pass a non-reduci

Error message

`loss_fn` cannot be a Keras `Loss` object, pass a non-reducing loss function or a metric instance instead.

What it means

Error "`loss_fn` cannot be a Keras `Loss` object, pass a non-reducing loss function or a metric instance instead." thrown in tensorflow/models.

Source

Thrown at official/recommendation/uplift/metrics/loss_metric.py:92

        `loss_fn` is a Keras metric.
      from_logits: When `y_pred` is of type `TwoTowerTrainingOutputs`, specifies
        whether the true logits or true predictions should be used to compute
        the loss (defaults to using the true logits). Othwerwise, this argument
        will be ignored if `y_pred` is of type `tf.Tensor`.
      slice_by_treatment: Specifies whether the loss should be sliced by the
        treatment indicator tensor. If `True`, `loss_fn` will be wrapped in a
        `TreatmentSlicedMetric` to report the loss values sliced by the
        treatment group.
      name: Optional name for the instance. If `loss_fn` is a Keras metric then
        its name will be used instead.
      dtype: Optional data type for the instance. If `loss_fn` is a Keras metric
        then its `dtype` will be used instead.
      **loss_fn_kwargs: The keyword arguments that are passed on to `loss_fn`.
        These arguments will be ignored if `loss_fn` is a Keras metric.
    """
    # Do not accept Loss objects as they reduce tensors before weighting.
    if isinstance(loss_fn, tf_keras.losses.Loss):
      raise TypeError(
          "`loss_fn` cannot be a Keras `Loss` object, pass a non-reducing loss"
          " function or a metric instance instead."
      )

    if isinstance(loss_fn, tf_keras.metrics.Metric):
      name = loss_fn.name
      dtype = loss_fn.dtype

    super().__init__(name=name, dtype=dtype)

    self._loss_fn = loss_fn
    self._from_logits = from_logits
    self._loss_fn_kwargs = loss_fn_kwargs
    self._slice_by_treatment = slice_by_treatment

    if isinstance(loss_fn, tf_keras.metrics.Metric):
      metric_from_logits = loss_fn.get_config().get("from_logits", from_logits)
      if from_logits != metric_from_logits:

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/recommendation/uplift/metrics/loss_metric.py:92 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/5ea6a19b97a205c7. Report an issue: GitHub.