tf.keras.ops.selu

Scaled Exponential Linear Unit (SELU) activation function.

Main aliases

tf.keras.ops.nn.selu

tf.keras.ops.selu(
    x
)

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

Args
`x`	Input tensor.

Returns
A tensor with the same shape as `x`.

x = np.array([-1., 0., 1.])
x_selu = keras.ops.selu(x)
print(x_selu)
array([-1.11133055, 0., 1.05070098], shape=(3,), dtype=float64)

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. Some content is licensed under the numpy license.

Last updated 2024-06-07 UTC.

Args