keras-team/keras · error · ValueError

Invalid start_points shape: expected (4,2) for a single imag

Error message

Invalid start_points shape: expected (4,2) for a single image or (N,4,2) for a batch. Received shape: {start_points.shape}

What it means

Error "Invalid start_points shape: expected (4,2) for a single image or (N,4,2) for a batch. Received shape: {start_points.shape}" thrown in keras-team/keras.

Source

Thrown at keras/src/backend/openvino/image.py:986

        )

    images = convert_to_tensor(images)
    start_points = convert_to_tensor(start_points)
    end_points = convert_to_tensor(end_points)
    images_ov = get_ov_output(images)
    sp_ov = get_ov_output(start_points)
    ep_ov = get_ov_output(end_points)

    if len(images.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={images.shape}"
        )
    if len(start_points.shape) not in (2, 3) or tuple(start_points.shape)[
        -2:
    ] != (4, 2):
        raise ValueError(
            "Invalid start_points shape: expected (4,2) for a single image"
            f" or (N,4,2) for a batch. Received shape: {start_points.shape}"
        )
    if len(end_points.shape) not in (2, 3) or tuple(end_points.shape)[-2:] != (
        4,
        2,
    ):
        raise ValueError(
            "Invalid end_points shape: expected (4,2) for a single image"
            f" or (N,4,2) for a batch. Received shape: {end_points.shape}"
        )

    ov_type = images_ov.get_element_type()
    compute_type = Type.f32

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

View on GitHub (pinned to 7a34a03db6)

When it happens

Trigger: Thrown at keras/src/backend/openvino/image.py:986 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/eed68432e5e62d7a. Report an issue: GitHub.