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 with shape: images.shape={images.get_partial_shape()}

What it means

Error "Invalid images rank: expected rank 3 (single image) or rank 4 (batch of images). Received input with shape: images.shape={images.get_partial_shape()}" thrown in keras-team/keras.

Source

Thrown at keras/src/backend/openvino/image.py:294

            "Invalid value for argument `fill_mode`. Only `'constant'` "
            f"is supported. Received: fill_mode={fill_mode}"
        )
    if pad_to_aspect_ratio and crop_to_aspect_ratio:
        raise ValueError(
            "Only one of `pad_to_aspect_ratio` & `crop_to_aspect_ratio` "
            "can be `True`."
        )
    if not len(size) == 2:
        raise ValueError(
            "Argument `size` must be a tuple of two elements "
            f"(height, width). Received: size={size}"
        )

    target_height, target_width = tuple(size)
    images = get_ov_output(images)
    rank = len(images.get_partial_shape())
    if rank not in (3, 4):
        raise ValueError(
            "Invalid images rank: expected rank 3 (single image) "
            "or rank 4 (batch of images). Received input with shape: "
            f"images.shape={images.get_partial_shape()}"
        )

    if data_format == "channels_last":
        height_axis, width_axis = (-3, -2)
    else:
        height_axis, width_axis = (-2, -1)

    def _gather_dim(shape_tensor, axis):
        axis_node = ov_opset.constant([axis], Type.i32).output(0)
        axis0 = ov_opset.constant(0, Type.i32).output(0)
        return ov_opset.gather(shape_tensor, axis_node, axis0).output(0)

    def _floor_div_int(numerator, denominator):
        numerator_f = ov_opset.convert(numerator, Type.f32).output(0)
        denominator_f = ov_opset.convert(denominator, Type.f32).output(0)

View on GitHub (pinned to 7a34a03db6)

When it happens

Trigger: Thrown at keras/src/backend/openvino/image.py:294 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/1cbe95cb54d7c131. Report an issue: GitHub.