# tf.keras.layers.subtract

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v2.13.1/keras/layers/merging/subtract.py#L67-L93) |

Functional interface to the `Subtract` layer.

#### View aliases


**Compat aliases for migration**

See
[Migration guide](https://www.tensorflow.org/guide/migrate) for
more details.

\`tf.compat.v1.keras.layers.subtract\`

<br />

    tf.keras.layers.subtract(
        inputs, **kwargs
    )

<br />

<br />

<br />

| ## Args ||
|---|---|
| `inputs` | A list of input tensors (exactly 2). |
| `**kwargs` | Standard layer keyword arguments. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| A tensor, the difference of the inputs. ||

<br />

#### Examples:

        import keras.src as keras

        input1 = keras.layers.Input(shape=(16,))
        x1 = keras.layers.Dense(8, activation='relu')(input1)
        input2 = keras.layers.Input(shape=(32,))
        x2 = keras.layers.Dense(8, activation='relu')(input2)
        subtracted = keras.layers.subtract([x1, x2])

        out = keras.layers.Dense(4)(subtracted)
        model = keras.models.Model(inputs=[input1, input2], outputs=out)