keras-team/keras · error · ValueError

Cannot adapt a Discretization layer that has been initialize

Error message

Cannot adapt a Discretization layer that has been initialized with `bin_boundaries`, use `num_bins` instead.

What it means

Error "Cannot adapt a Discretization layer that has been initialized with `bin_boundaries`, use `num_bins` instead." thrown in keras-team/keras.

Source

Thrown at keras/src/layers/preprocessing/discretization.py:187

        input dataset. The number of quantiles can be controlled via the
        `num_bins` argument, and the error tolerance for quantile boundaries can
        be controlled via the `epsilon` argument.

        Arguments:
            data: The data to train on. It can be passed either as a
                batched `tf.data.Dataset`, a Grain dataset, as a NumPy
                array, or as any iterable of batches (e.g. a list of
                arrays or a generator yielding batches).
            steps: Integer or `None`.
                Total number of steps (batches of samples) to process.
                If `data` is a `tf.data.Dataset`, and `steps` is `None`,
                `adapt()` will run until the input dataset is exhausted.
                When passing an infinitely
                repeating dataset, you must specify the `steps` argument. This
                argument is not supported with array inputs or list inputs.
        """
        if self.num_bins is None:
            raise ValueError(
                "Cannot adapt a Discretization layer that has been initialized "
                "with `bin_boundaries`, use `num_bins` instead."
            )
        self.reset_state()
        if isinstance(data, tf.data.Dataset):
            if steps is None and hasattr(data, "cardinality"):
                cardinality = data.cardinality()
                if cardinality.numpy() not in (
                    tf.data.UNKNOWN_CARDINALITY,
                    tf.data.INFINITE_CARDINALITY,
                ):
                    steps = int(cardinality.numpy())

            progbar = Progbar(target=steps, unit_name="step")
            if steps is not None:
                data = data.take(steps)
            for i, batch in enumerate(data):
                self.update_state(batch)

View on GitHub (pinned to 7a34a03db6)

When it happens

Trigger: Thrown at keras/src/layers/preprocessing/discretization.py:187 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of keras-team/keras@7a34a03db6 (2026-08-25). Data as JSON: /api/errors/c329936bea1f9410. Report an issue: GitHub.