tf.keras.backend.cast_to_floatx

TensorFlow 1 version View source on GitHub

Cast a Numpy array to the default Keras float type.

x Numpy array or TensorFlow tensor.

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')