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={input_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={input_shape}" thrown in keras-team/keras.

Source

Thrown at keras/src/backend/openvino/image.py:1492

            ).output(0)

            # kernel1d_y has kW elements -> column vector [kW, 1]
            kernel1d_y = ov_opset.reshape(
                kernel1d_y,
                ov_opset.constant([int(size[1]), 1], Type.i32).output(0),
                False,
            ).output(0)
            return ov_opset.multiply(kernel1d_y, kernel1d_x).output(0)

        return _get_gaussian_kernel2d(kernel_size, sigma)

    data_format = backend.standardize_data_format(data_format)
    images = convert_to_tensor(images)
    input_shape = images.shape
    ov_type = get_ov_output(images).get_element_type()

    if len(input_shape) 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={input_shape}"
        )

    # bfloat16 is not supported by all OV ops used here; promote to f32.
    # f16 constants in range() would mismatch with the f32 arithmetic
    # constants in the kernel builder, so promote f16 to f32 as well.
    compute_type = Type.f32 if ov_type in (Type.bf16, Type.f16) else ov_type
    images = get_ov_output(images)
    if compute_type != ov_type:
        images = ov_opset.convert(images, compute_type).output(0)

    need_squeeze = False
    if len(input_shape) == 3:
        images = ov_opset.unsqueeze(images, axes=[0]).output(0)
        need_squeeze = True

View on GitHub (pinned to 7a34a03db6)

When it happens

Trigger: Thrown at keras/src/backend/openvino/image.py:1492 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/600b9adf40dbfe0c. Report an issue: GitHub.