keras-team/keras · error · ValueError

You need to either pass the `bin_boundaries` argument at con

Error message

You need to either pass the `bin_boundaries` argument at construction time or call `adapt(dataset)` before you can start using the `Discretization` layer.

What it means

Error "You need to either pass the `bin_boundaries` argument at construction time or call `adapt(dataset)` before you can start using the `Discretization` layer." thrown in keras-team/keras.

Source

Thrown at keras/src/layers/preprocessing/discretization.py:281

                    (input_shape[0],) + tuple(input_shape[2:]) + (depth,)
                )
                return out_shape
            else:
                return (depth,)

    def compute_output_spec(self, inputs):
        output_shape = self.compute_output_shape(inputs.shape)
        return backend.KerasTensor(shape=output_shape, dtype=self.output_dtype)

    def load_own_variables(self, store):
        if len(store) == 1:
            # Legacy format case
            self.summary = store["0"]
        return

    def call(self, inputs):
        if self.bin_boundaries is None:
            raise ValueError(
                "You need to either pass the `bin_boundaries` argument at "
                "construction time or call `adapt(dataset)` before you can "
                "start using the `Discretization` layer."
            )

        indices = self.backend.numpy.digitize(inputs, self.bin_boundaries)
        return numerical_utils.encode_categorical_inputs(
            indices,
            output_mode=self.output_mode,
            depth=len(self.bin_boundaries) + 1,
            dtype=self.output_dtype,
            sparse=self.sparse,
            backend_module=self.backend,
        )

    def get_config(self):
        return {
            "bin_boundaries": self.bin_boundaries,

View on GitHub (pinned to 7a34a03db6)

When it happens

Trigger: Thrown at keras/src/layers/preprocessing/discretization.py:281 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/3334a52a53fd5486. Report an issue: GitHub.