RSVP for your your local TensorFlow Everywhere event today!

tf.keras.activations.softsign

TensorFlow 1 version View source on GitHub

Softsign activation function, softsign(x) = x / (abs(x) + 1).

Example Usage:

a = tf.constant([-1.0, 0.0, 1.0], dtype = tf.float32)
b = tf.keras.activations.softsign(a)
b.numpy()
array([-0.5,  0. ,  0.5], dtype=float32)

x Input tensor.

The softsign activation: x / (abs(x) + 1).