# tf.keras.backend.cast_to_floatx

<br />

|---|---|
| [![](https://www.tensorflow.org/images/tf_logo_32px.png) TensorFlow 2 version](https://www.tensorflow.org/api_docs/python/tf/keras/backend/cast_to_floatx) | [![](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#L150-L175) |

Cast a Numpy array to the default Keras float type.

#### View aliases


**Compat aliases for migration**

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

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

<br />

    tf.keras.backend.cast_to_floatx(
        x
    )

<br />

<br />

<br />

| ## Arguments ||
|---|---|
| `x` | Numpy array. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| The same Numpy array, cast to its new type. ||

<br />

#### Example:

        from tensorflow.keras import backend as K
        K.floatx()
            'float32'
        arr = numpy.array([1.0, 2.0], dtype='float64')
        arr.dtype
            dtype('float64')
        new_arr = K.cast_to_floatx(arr)
        new_arr
            array([ 1.,  2.], dtype=float32)
        new_arr.dtype
            dtype('float32')