keras-team/keras · error · AttributeError

Sequential model '{self.name}' has no defined input shape ye

Error message

Sequential model '{self.name}' has no defined input shape yet.

What it means

The input_shape property only exists once the Sequential has a functional graph, i.e. after build() or after an InputLayer was supplied. Before that there is no input shape to report, so an AttributeError is raised.

Source

Thrown at keras/src/models/sequential.py:302

                **kwargs,
            )  # Ignore mask
            inputs = outputs
        return outputs

    def compute_output_shape(self, input_shape):
        if self._functional:
            return self._functional.compute_output_shape(input_shape)
        # Direct application
        for layer in self.layers:
            output_shape = layer.compute_output_shape(input_shape)
            input_shape = output_shape
        return output_shape

    @property
    def input_shape(self):
        if self._functional:
            return self._functional.input_shape
        raise AttributeError(
            f"Sequential model '{self.name}' has no defined input shape yet."
        )

    @property
    def output_shape(self):
        if self._functional:
            return self._functional.output_shape
        raise AttributeError(
            f"Sequential model '{self.name}' has no defined output shape yet."
        )

    @property
    def inputs(self):
        if self._functional:
            return self._functional.inputs
        raise AttributeError(
            f"Sequential model '{self.name}' has no defined inputs yet."
        )

View on GitHub (pinned to 7a34a03db6)

Solutions

1. Call model.build(input_shape) first
2. Construct with keras.Sequential([keras.Input(...), ...])
3. Pass input_shape= to the Sequential constructor

Example fix

# before
shape = model.input_shape

# after
model.build((None, 28, 28))
shape = model.input_shape

has_input = bool(model._functional) or (
    model._layers and isinstance(model._layers[0], keras.layers.InputLayer))

try:
    shape = model.input_shape
except AttributeError:
    model.build(input_shape)
    shape = model.input_shape

When it happens

Trigger: model = keras.Sequential([Dense(10)]); print(model.input_shape) before build or calling on data

Common situations: Introspection utilities, TensorBoard callbacks, or shape-logging code run before any data passes through the model

Related errors

• Sequential model '{self.name}' has already been configured t
• Sequential model '{self.name}' has no defined output shape y
• Sequential model '{self.name}' has no defined inputs yet.
• Sequential model '{self.name}' has no defined outputs yet.
• You must build the layer before accessing `kernel`.

AI-assisted analysis of keras-team/keras@7a34a03db6 (2026-08-25). Data as JSON: /api/errors/3900311fadb39307. Report an issue: GitHub.