tf.keras.ops.celu

Continuously-differentiable exponential linear unit.

View aliases

Main aliases

tf.keras.ops.nn.celu

tf.keras.ops.celu(
    x, alpha=1.0
)

It is defined as:

f(x) = alpha * (exp(x / alpha) - 1) for x < 0, f(x) = x for x >= 0.

Args
x	Input tensor.
alpha	the α value for the CELU formulation. Defaults to 1.0.

Returns
A tensor with the same shape as x.

Example:

x = np.array([-1., 0., 1.])
x_celu = keras.ops.celu(x)
print(x_celu)
array([-0.63212056, 0. , 1. ], shape=(3,), dtype=float64)