keras-team/keras · error · ValueError

A `Concatenate` layer should be called on a list of at least

Error message

A `Concatenate` layer should be called on a list of at least 1 input. Received: input_shape={input_shape}

What it means

Concatenate.build validates that input_shape is a list containing at least one shape (each itself a tuple/list). This catches calls where the layer got a single tensor's shape or an empty list, which are invalid for concatenation.

Source

Thrown at keras/src/layers/merging/concatenate.py:47

        axis: Axis along which to concatenate.
        **kwargs: Standard layer keyword arguments.

    Returns:
        A tensor, the concatenation of the inputs alongside axis `axis`.
    """

    def __init__(self, axis=-1, **kwargs):
        super().__init__(**kwargs)
        self.axis = axis
        self.supports_masking = True
        self._reshape_required = False

    def build(self, input_shape):
        # Used purely for shape validation.
        if len(input_shape) < 1 or not isinstance(
            input_shape[0], (tuple, list)
        ):
            raise ValueError(
                "A `Concatenate` layer should be called on a list of "
                f"at least 1 input. Received: input_shape={input_shape}"
            )
        if all(shape is None for shape in input_shape):
            return

        reduced_inputs_shapes = [list(shape) for shape in input_shape]
        reduced_inputs_shapes_copy = copy.copy(reduced_inputs_shapes)
        shape_set = set()
        for i in range(len(reduced_inputs_shapes_copy)):
            # Convert self.axis to positive axis for each input
            # in case self.axis is a negative number
            concat_axis = self.axis % len(reduced_inputs_shapes_copy[i])
            #  Skip batch axis.
            for axis, axis_value in enumerate(
                reduced_inputs_shapes_copy, start=1
            ):
                # Remove squeezable axes (axes with value of 1)

View on GitHub (pinned to 7a34a03db6)

Solutions

1. Pass a list of two or more tensors: Concatenate()([a, b])
2. Ensure all code paths deliver at least two tensors to the concat layer
3. Check that upstream conditionals/filters do not reduce the input list to one element

Example fix

# before
out = layers.Concatenate()(x)

# after
out = layers.Concatenate()([x, y])

assert isinstance(inputs, (list, tuple)) and len(inputs) >= 2, 'Concatenate needs a list of >= 2 tensors'

def is_concat_input(inputs) -> bool:
    return isinstance(inputs, (list, tuple)) and len(inputs) >= 2

When it happens

Trigger: Calling Concatenate()(x) with one tensor; Concatenate()([]); a Functional node wiring only one branch into the concat layer.

Common situations: Conditionally adding branches so that sometimes only one reaches the concat; incorrect list nesting.

Related errors

• A `Concatenate` layer should be called on a list of inputs.
• `inputs` should be a list. Received: inputs={inputs}
• A merge layer should be called on a list of inputs. Received
• A merge layer should be called on a list of inputs. Received
• `inputs` should be a list. Received: inputs={inputs}

AI-assisted analysis of keras-team/keras@7a34a03db6 (2026-08-25). Data as JSON: /api/errors/c1d14e06de0748c4. Report an issue: GitHub.