keras-team/keras · error · ValueError

The `value_range` argument should be a list of two numbers.

Error message

The `value_range` argument should be a list of two numbers. Received: value_range={value_range}

What it means

The value_range argument of AutoContrast must contain exactly two numbers (the minimum and maximum pixel values of the input). After confirming it is a tuple/list, the layer checks len(value_range) == 2 and raises this ValueError for lists of any other length; the accepted pair is stored sorted.

Source

Thrown at keras/src/layers/preprocessing/image_preprocessing/auto_contrast.py:51

        "The `value_range` argument should be a list of two numbers. "
    )

    def __init__(
        self,
        value_range=(0, 255),
        **kwargs,
    ):
        super().__init__(**kwargs)
        self._set_value_range(value_range)

    def _set_value_range(self, value_range):
        if not isinstance(value_range, (tuple, list)):
            raise ValueError(
                self._VALUE_RANGE_VALIDATION_ERROR
                + f"Received: value_range={value_range}"
            )
        if len(value_range) != 2:
            raise ValueError(
                self._VALUE_RANGE_VALIDATION_ERROR
                + f"Received: value_range={value_range}"
            )
        self.value_range = sorted(value_range)

    def transform_images(self, images, transformation=None, training=True):
        original_images = images
        images = self._transform_value_range(
            images,
            original_range=self.value_range,
            target_range=(0, 255),
            dtype=self.compute_dtype,
        )

        images = self.backend.cast(images, self.compute_dtype)
        low = self.backend.numpy.min(images, axis=(1, 2), keepdims=True)
        high = self.backend.numpy.max(images, axis=(1, 2), keepdims=True)
        scale = 255.0 / (high - low)

View on GitHub (pinned to 7a34a03db6)

Solutions

1. Pass exactly two numbers, e.g. (0, 255).
2. If you computed per-channel ranges, reduce them to a single global (min, max) pair before passing them in.

Example fix

# before
layer = keras.layers.AutoContrast(value_range=[0, 128, 255])
# after
layer = keras.layers.AutoContrast(value_range=(0, 255))

assert len(value_range) == 2, f"value_range must have 2 elements, got {len(value_range)}"

def is_valid_value_range(v):
    return isinstance(v, (tuple, list)) and len(v) == 2 and all(isinstance(x, (int, float)) for x in v)

When it happens

Trigger: Passing value_range=(0,), value_range=[0, 128, 255], or an empty list.

Common situations: Building value_range dynamically (e.g. from per-channel normalization statistics that yield three values) and passing it straight to the layer.

Related errors

• {self._VALUE_RANGE_VALIDATION_ERROR}Received: value_range={v
• Layer {self.__class__.__name__} does not take a `factor` arg
• The `factor` argument should be a number (or a list of two n
• Invalid quantization mode. Expected one of {dtype_policies.Q
• Invalid value for argument `output_mode`. Expected one of {a

AI-assisted analysis of keras-team/keras@7a34a03db6 (2026-08-25). Data as JSON: /api/errors/e598375c3a72d4ce. Report an issue: GitHub.