keras-team/keras · error · ValueError

If using `weights="imagenet"` as true, `classes` should be 1

Error message

If using `weights="imagenet"` as true, `classes` should be 1000

What it means

Width-axis cropping check: left_cropping (explicit or inferred as width - target_width - right_cropping) must be >= 0; negative means the horizontal crop configuration is impossible.

Source

Thrown at keras/src/applications/efficientnet_v2.py:905

    Returns:
        A model instance.
    """

    if blocks_args == "default":
        blocks_args = DEFAULT_BLOCKS_ARGS[name]

    if not (weights in {"imagenet", None} or file_utils.exists(weights)):
        raise ValueError(
            "The `weights` argument should be either "
            "`None` (random initialization), `imagenet` "
            "(pre-training on ImageNet), "
            "or the path to the weights file to be loaded."
            f"Received: weights={weights}"
        )

    if weights == "imagenet" and include_top and classes != 1000:
        raise ValueError(
            'If using `weights="imagenet"` with `include_top`'
            " as true, `classes` should be 1000"
        )

    # Determine proper input shape
    input_shape = imagenet_utils.obtain_input_shape(
        input_shape,
        default_size=default_size,
        min_size=32,
        data_format=backend.image_data_format(),
        require_flatten=include_top,
        weights=weights,
    )

    if input_tensor is None:
        img_input = layers.Input(shape=input_shape)
    else:
        if not backend.is_keras_tensor(input_tensor):

View on GitHub (pinned to 7a34a03db6)

Solutions

1. Ensure target_width + left + right cropping <= width
2. Use pad_images to enlarge
3. Double-check which axis is width under your data_format

Example fix

# before
out = ops.image.crop_images(img, target_width=(64, 64))  # img width 32
# after
out = ops.image.pad_images(img, target_width=(64, 64))

left = left_cropping or 0
right = right_cropping or 0
if width is not None and left + right + target_width > width:
    raise ValueError('horizontal crop exceeds width')

When it happens

Trigger: Negative left_cropping argument, or None with right_cropping + target_width > width.

Common situations: Center-crop math going negative on narrow images; aspect-ratio-preserving pipelines; swapped width/height.

Related errors

• If using `weights="imagenet"` as true, `classes` should be 1
• The number of repeats in `EfficientNet` must be > 0. Receive
• The number of repeats in `EfficientNetV2` must be > 0. Recei
• weights_path undefined
• The `weights` argument should be either `None` (random initi

AI-assisted analysis of keras-team/keras@7a34a03db6 (2026-08-25). Data as JSON: /api/errors/bd5d31cd16c99f5e. Report an issue: GitHub.