keras-team/keras · error · NotImplementedError

Unsupported data type: {type(data)}

Error message

Unsupported data type: {type(data)}

What it means

Error "Unsupported data type: {type(data)}" thrown in keras-team/keras.

Source

Thrown at keras/src/layers/preprocessing/normalization.py:409

                batch_weight = float(batch_count) / total_count
                existing_weight = 1.0 - batch_weight
                new_total_mean = (
                    total_mean * existing_weight + batch_mean * batch_weight
                )
                # The variance is computed using the lack-of-fit sum of squares
                # formula (see
                # https://en.wikipedia.org/wiki/Lack-of-fit_sum_of_squares).
                total_var = (
                    total_var + (total_mean - new_total_mean) ** 2
                ) * existing_weight + (
                    batch_var + (batch_mean - new_total_mean) ** 2
                ) * batch_weight
                total_mean = new_total_mean
                progbar.update(i + 1)

            progbar.update(steps if steps is not None else i + 1, finalize=True)
        else:
            raise NotImplementedError(f"Unsupported data type: {type(data)}")

        self.adapt_mean.assign(total_mean)
        self.adapt_variance.assign(total_var)
        self.finalize_state()

    def finalize_state(self):
        if self.input_mean is not None or not self.built:
            return

        # In the adapt case, we make constant tensors for mean and variance with
        # proper broadcast shape and dtype each time `finalize_state` is called.
        self.mean = ops.reshape(self.adapt_mean, self._broadcast_shape)
        self.mean = ops.cast(self.mean, self.compute_dtype)
        self.variance = ops.reshape(self.adapt_variance, self._broadcast_shape)
        self.variance = ops.cast(self.variance, self.compute_dtype)

    def call(self, inputs):
        # This layer can be called in tf.data

View on GitHub (pinned to 7a34a03db6)

When it happens

Trigger: Thrown at keras/src/layers/preprocessing/normalization.py:409 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/18f41b2894e2dde9. Report an issue: GitHub.