# tf.keras.backend.permute_dimensions

<br />

|---|---|
| [![](https://www.tensorflow.org/images/tf_logo_32px.png) TensorFlow 2 version](https://www.tensorflow.org/api_docs/python/tf/keras/backend/permute_dimensions) | [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/backend.py#L2626-L2654) |

Permutes axes in a tensor.

#### View aliases


**Compat aliases for migration**

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

[`tf.compat.v1.keras.backend.permute_dimensions`](https://www.tensorflow.org/api_docs/python/tf/keras/backend/permute_dimensions), \`tf.compat.v2.keras.backend.permute_dimensions\`

<br />

    tf.keras.backend.permute_dimensions(
        x, pattern
    )

<br />

<br />

<br />

| ## Arguments ||
|---|---|
| `x` | Tensor or variable. |
| `pattern` | A tuple of dimension indices, e.g. `(0, 2, 1)`. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| A tensor. ||

<br />

#### Example:

    a = tf.constant([[1, 2, 3], [4, 5, 6], [7, 8, 9], [10, 11, 12]])
    a
    <tf.Tensor: id=49, shape=(4, 3), dtype=int32, numpy=
    array([[ 1,  2,  3],
           [ 4,  5,  6],
           [ 7,  8,  9],
           [10, 11, 12]], dtype=int32)>
    tf.keras.backend.permute_dimensions(a, pattern=(1, 0))
    <tf.Tensor: id=52, shape=(3, 4), dtype=int32, numpy=
    array([[ 1,  4,  7, 10],
           [ 2,  5,  8, 11],
           [ 3,  6,  9, 12]], dtype=int32)>