tf.keras.backend.cast_to_floatx
Stay organized with collections
Save and categorize content based on your preferences.
Cast a Numpy array to the default Keras float type.
tf.keras.backend.cast_to_floatx(
x
)
Arguments |
|---|
x
|
Numpy array or TensorFlow tensor.
|
Returns |
|---|
The same array (Numpy array if x was a Numpy array, or TensorFlow tensor
if x was a tensor), cast to its new type.
|
Example:
tf.keras.backend.floatx()
'float32'
arr = np.array([1.0, 2.0], dtype='float64')
arr.dtype
dtype('float64')
new_arr = cast_to_floatx(arr)
new_arr
array([1., 2.], dtype=float32)
new_arr.dtype
dtype('float32')
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2020-10-01 UTC.
[null,null,["Last updated 2020-10-01 UTC."],[],[],null,["# tf.keras.backend.cast_to_floatx\n\n\u003cbr /\u003e\n\n|-----------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------|\n| [TensorFlow 1 version](/versions/r1.15/api_docs/python/tf/keras/backend/cast_to_floatx) | [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.2.0/tensorflow/python/keras/backend.py#L169-L198) |\n\nCast a Numpy array to the default Keras float type.\n\n#### View aliases\n\n\n**Compat aliases for migration**\n\nSee\n[Migration guide](https://www.tensorflow.org/guide/migrate) for\nmore details.\n\n[`tf.compat.v1.keras.backend.cast_to_floatx`](/api_docs/python/tf/keras/backend/cast_to_floatx)\n\n\u003cbr /\u003e\n\n tf.keras.backend.cast_to_floatx(\n x\n )\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Arguments --------- ||\n|-----|-----------------------------------|\n| `x` | Numpy array or TensorFlow tensor. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| The same array (Numpy array if `x` was a Numpy array, or TensorFlow tensor if `x` was a tensor), cast to its new type. ||\n\n\u003cbr /\u003e\n\n#### Example:\n\n tf.keras.backend.floatx()\n 'float32'\n arr = np.array([1.0, 2.0], dtype='float64')\n arr.dtype\n dtype('float64')\n new_arr = cast_to_floatx(arr)\n new_arr\n array([1., 2.], dtype=float32)\n new_arr.dtype\n dtype('float32')"]]
TensorFlow 1 version
View source on GitHub