keras-team/keras · error · ValueError

The `weights` argument should be either `None` (random initi

Error message

The `weights` argument should be either `None` (random initialization), `imagenet` (pre-training on ImageNet), or the path to the weights file to be loaded.

What it means

Width-axis counterpart: the input width dim is None and target_width was not specified, so the cropping op cannot determine its output width in the symbolic shape.

Source

Thrown at keras/src/applications/efficientnet.py:275

              last convolutional layer, and thus
              the output of the model will be a 2D tensor.
          - `max` means that global max pooling will
              be applied.
      classes: optional number of classes to classify images
          into, only to be specified if `include_top` is True, and
          if no `weights` argument is specified.
      classifier_activation: A `str` or callable. The activation function to use
          on the "top" layer. Ignored unless `include_top=True`. Set
          `classifier_activation=None` to return the logits of the "top" layer.

    Returns:
        A model instance.
    """
    if blocks_args == "default":
        blocks_args = DEFAULT_BLOCKS_ARGS

    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."
        )

    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(),

View on GitHub (pinned to 7a34a03db6)

Solutions

1. Specify target_width on the operation
2. Fix the input width in keras.Input
3. Handle fully-dynamic crops with raw slicing outside the layer

Example fix

# before
inputs = keras.Input(shape=(224, None, 3))
x = Cropping2D(2)(inputs)
# after
inputs = keras.Input(shape=(224, 224, 3))
x = Cropping2D(2)(inputs)

if images.shape[-2] is None and target_width is None:
    raise ValueError('fixed input width or target_width required')

def has_static_width(images) -> bool:
    return images.shape[-2] is not None

When it happens

Trigger: Variable-width inputs (Input(shape=(H, None, 3))) with a cropping layer lacking target_width.

Common situations: Variable-resolution models; Keras 3 symbolic tracing where TF1-style code assumed lazy shapes.

Related errors

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

AI-assisted analysis of keras-team/keras@7a34a03db6 (2026-08-25). Data as JSON: /api/errors/39c1a56bea686866. Report an issue: GitHub.