<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/ops/numpy.py#L258-L287) |

Add arguments element-wise.

#### View aliases


**Main aliases**

[`tf.keras.ops.numpy.add`](https://www.tensorflow.org/api_docs/python/tf/keras/ops/add)

<br />

    tf.keras.ops.add(
        x1, x2
    )

<br />

<br />

<br />

| ## Args ||
|---|---|
| `x1` | First input tensor. |
| `x2` | Second input tensor. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| The tensor containing the element-wise sum of `x1` and `x2`. ||

<br />

#### Examples:

    x1 = keras.ops.convert_to_tensor([1, 4])
    x2 = keras.ops.convert_to_tensor([5, 6])
    keras.ops.add(x1, x2)
    array([6, 10], dtype=int32)

[`keras.ops.add`](https://www.tensorflow.org/api_docs/python/tf/keras/ops/add) also broadcasts shapes:

    >>> x1 = keras.ops.convert_to_tensor(
    ...     [[5, 4],
    ...      [5, 6]]
    ... )
    >>> x2 = keras.ops.convert_to_tensor([5, 6])
    >>> keras.ops.add(x1, x2)
    array([[10 10]
           [10 12]], shape=(2, 2), dtype=int32)