keras-team/keras · error · ValueError

Invalid images rank: expected rank 3 (single image) or rank

Error message

Invalid images rank: expected rank 3 (single image) or rank 4 (batch of images). Received: input_shape={input_shape}

What it means

RandomColorDegeneration.compute_output_shape requires the input shape to have rank 3 (single image) or 4 (batch). Called during model building, it rejects shapes of other lengths, e.g. rank 2 or rank 5 input specifications.

Source

Thrown at keras/src/layers/preprocessing/image_preprocessing/random_color_degeneration.py:143

    def transform_bounding_boxes(
        self, bounding_boxes, transformation, training=True
    ):
        return bounding_boxes

    def get_config(self):
        config = super().get_config()
        config.update(
            {
                "factor": self.factor,
                "value_range": self.value_range,
                "seed": self.seed,
            }
        )
        return config

    def compute_output_shape(self, input_shape):
        if len(input_shape) not in (3, 4):
            raise ValueError(
                "Invalid images rank: expected rank 3 (single image) "
                "or rank 4 (batch of images). "
                f"Received: input_shape={input_shape}"
            )
        channels_axis = -1 if self.data_format == "channels_last" else -3
        channels = input_shape[channels_axis]
        if channels is not None and channels != 3:
            raise ValueError(
                "Input images must have 3 channels, but received images with "
                f"{channels} channels."
            )
        return input_shape


if RandomColorDegeneration.__doc__ is not None:
    RandomColorDegeneration.__doc__ = RandomColorDegeneration.__doc__.replace(
        "{{base_image_preprocessing_color_example}}",
        base_image_preprocessing_color_example.replace(

View on GitHub (pinned to 7a34a03db6)

Solutions

1. Reshape inputs to (H, W, C) / (batch, H, W, C) before this layer
2. For video, apply the layer per frame instead of a rank-5 tensor
3. Check keras.Input(shape=...) has exactly 3 dims

Example fix

# before
x = keras.Input(shape=(1, 224, 224, 3))  # rank 4 unbatched -> 5 with batch
# after
x = keras.Input(shape=(224, 224, 3))

assert len(input_shape) in (3, 4), input_shape

def is_img_shape3or4(s):
    return len(s) in (3, 4)

When it happens

Trigger: keras.Input(shape=(1, 224, 224, 3)) making a rank-5 batched shape passed through this layer; any input spec whose batched rank is not 3 or 4.

Common situations: Multi-frame/video inputs (T, H, W, C); extra leading axes from data loaders; constructing Input with unnecessary batch-and-time axes.

Related errors

• Expected the input image to be rank 3 or 4. Received inputs.
• Input images must have 3 channels, but received images with
• Found bounding_boxes['boxes'].shape={boxes_shape} and expect
• Found bounding_boxes['boxes'].shape={boxes_shape} and expect
• Expected `bounding_boxes['boxes']` to have rank 2 or 3, with

AI-assisted analysis of keras-team/keras@7a34a03db6 (2026-08-25). Data as JSON: /api/errors/4bcb71a667390c05. Report an issue: GitHub.