tf.keras.activations.hard_sigmoid

TensorFlow 1 version View source on GitHub

Hard sigmoid activation function.

Faster to compute than sigmoid activation.

For example:

a = tf.constant([-3.0,-1.0, 0.0,1.0,3.0], dtype = tf.float32)
b = tf.keras.activations.hard_sigmoid(a)
b.numpy()
array([0. , 0.3, 0.5, 0.7, 1. ], dtype=float32)

x Input tensor.

The hard sigmoid activation:

  • 0 if x < -2.5
  • 1 if x > 2.5
  • 0.2 * x + 0.5 if -2.5 <= x <= 2.5.