tf.keras.ops.float_power

Note: This API is new and only available via pip install tf-nightly.

First tensor elements raised to powers from second tensor, in floats.

View aliases

Main aliases

tf.keras.ops.numpy.float_power

tf.keras.ops.float_power(
    x1, x2
)

This is power with the operands promoted to a float dtype first, so a negative exponent has a well defined result for integer inputs, where power either raises an error or returns an integer.

Args
x1	The bases.
x2	The exponents.

Returns
Output tensor, the bases in x1 raised to the exponents in x2.

Example:

x1 = keras.ops.convert_to_tensor([2, 3, 4])
x2 = keras.ops.convert_to_tensor([-1, -2, 2])
keras.ops.float_power(x1, x2)
array([ 0.5       ,  0.11111111, 16.        ], dtype=float32)