# tfdf.keras.build_default_feature_signature

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/decision-forests/blob/main/tensorflow_decision_forests/tensorflow/core_inference.py#L591-L630) |

Gets an example of feature values for the default model signature.

    tfdf.keras.build_default_feature_signature(
        feature_name: str, dataspec_column: data_spec_pb2.Column
    ) -> Any

When a model is trained without having tensor examples (e.g. the model is
build manually or converted from the Yggdrasil format), the output of this
function is used to instantiate the tf graph of the model. The feature value
should represent 2 or more examples.

Follow "InputModelSignatureFn".

<br />

<br />

<br />

| ## Args ||
|---|---|
| `feature_name` | Name of the feature. |
| `dataspec_column` | Yggdrasil column dataspec for the feature. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| An example of tensor value. ||

<br />