tf.keras.activations.swish

Swish activation function, swish(x) = x * sigmoid(x).

tf.keras.activations.swish(
    x
)

Swish activation function which returns x*sigmoid(x). It is a smooth, non-monotonic function that consistently matches or outperforms ReLU on deep networks, it is unbounded above and bounded below.

Example Usage:

a = tf.constant([-20, -1.0, 0.0, 1.0, 20], dtype = tf.float32)
b = tf.keras.activations.swish(a)
b.numpy()
array([-4.1223075e-08, -2.6894143e-01,  0.0000000e+00,  7.3105860e-01,
          2.0000000e+01], dtype=float32)

Args
`x`	Input tensor.

Returns
The swish activation applied to `x` (see reference paper for details).

Reference
Ramachandran et al., 2017

Reference

Ramachandran et al., 2017

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 2023-10-06 UTC.

tf.keras.activations.swish

Example Usage:

Args

Returns

Reference