keras-team/keras · error · ValueError

Argument `input_tensors` must contain a single tensor.

Error message

Argument `input_tensors` must contain a single tensor.

What it means

When cloning a Sequential model onto new inputs, input_tensors must reduce to exactly one tensor because a Sequential model has a single input. A list/tuple with zero or two-plus tensors raises this ValueError.

Source

Thrown at keras/src/models/cloning.py:308

    new_layers = [clone_function(layer) for layer in model.layers]

    if isinstance(model._layers[0], InputLayer):
        ref_input_layer = model._layers[0]
        input_name = ref_input_layer.name
        input_batch_shape = ref_input_layer.batch_shape
        input_dtype = ref_input_layer._dtype
        input_optional = ref_input_layer.optional
    else:
        input_name = None
        input_dtype = None
        input_batch_shape = None
        input_optional = False

    if input_tensors is not None:
        if isinstance(input_tensors, (list, tuple)):
            if len(input_tensors) != 1:
                raise ValueError(
                    "Argument `input_tensors` must contain a single tensor."
                )
            input_tensors = input_tensors[0]
        if not isinstance(input_tensors, backend.KerasTensor):
            raise ValueError(
                "Argument `input_tensors` must be a KerasTensor. "
                f"Received invalid value: input_tensors={input_tensors}"
            )
        inputs = Input(
            tensor=input_tensors,
            name=input_name,
            optional=input_optional,
        )
        new_layers = [inputs] + new_layers
    else:
        if input_batch_shape is not None:
            inputs = Input(
                batch_shape=input_batch_shape,

View on GitHub (pinned to 7a34a03db6)

Solutions

1. Pass the single tensor directly (no list), or a one-element list: input_tensors=[t].
2. For genuinely multi-input models, use a Functional model instead of Sequential.

Example fix

# before
clone = keras.models.clone_model(seq_model, input_tensors=[t1, t2])

# after
clone = keras.models.clone_model(seq_model, input_tensors=t1)

if isinstance(input_tensors, (list, tuple)):
    assert len(input_tensors) == 1, 'Sequential clone takes exactly one input tensor'
    input_tensors = input_tensors[0]

When it happens

Trigger: clone_model(seq_model, input_tensors=[]) or input_tensors=[t1, t2] - a list whose length is not 1.

Common situations: Generic cloning code that always wraps inputs in a list; adapting multi-input Functional examples to Sequential.

Related errors

• `call_function` argument is not supported with Sequential mo
• Expected `model` argument to be a `Sequential` model instanc
• Unexpected keyword argument(s): {tuple(kwargs.keys())}
• Arguments `clone_function` and `input_tensors` are only supp
• Argument `call_function` is only supported for Functional mo

AI-assisted analysis of keras-team/keras@7a34a03db6 (2026-08-25). Data as JSON: /api/errors/d87f87ab8a137f22. Report an issue: GitHub.