tf.math.softplus

Computes elementwise softplus: softplus(x) = log(exp(x) + 1).

View aliases

Main aliases

tf.nn.softplus

tf.math.softplus(
    features, name=None
)

Used in the notebooks

Used in the guide	Used in the tutorials
Introduction to gradients and automatic differentiation	TFP Probabilistic Layers: Regression Gaussian Process Latent Variable Models Bayesian Modeling with Joint Distribution

softplus is a smooth approximation of relu. Like relu, softplus always takes on positive values.

Example:

import tensorflow as tf
tf.math.softplus(tf.range(0, 2, dtype=tf.float32)).numpy()
array([0.6931472, 1.3132616], dtype=float32)

Args
features	Tensor
name	Optional: name to associate with this operation.

Returns
Tensor