W3cubDocs

/TensorFlow 2.3

tf.keras.activations.swish

Swish activation function, swish(x) = x * sigmoid(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)
Arguments
x Input tensor.
Returns
The swish activation applied to x (see reference paper for details).

Reference:

© 2020 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/versions/r2.3/api_docs/python/tf/keras/activations/swish