# tf.keras.backend.floatx

<br />

|---|---|
| [![](https://www.tensorflow.org/images/tf_logo_32px.png) TensorFlow 2 version](https://www.tensorflow.org/api_docs/python/tf/keras/backend/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_config.py#L60-L74) |

Returns the default float type, as a string.

#### View aliases


**Compat aliases for migration**

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

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

<br />

    tf.keras.backend.floatx()

E.g. 'float16', 'float32', 'float64'.

<br />

<br />

<br />

| ## Returns ||
|---|---|
| String, the current default float type. ||

<br />

#### Example:

    keras.backend.floatx() >>> 'float32'