|---| | [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.21.0/tensorflow/python/ops/math_ops.py#L662-L685) | Computes elementwise softplus: `softplus(x) = log(exp(x) + 1)`. #### View aliases **Main aliases** [`tf.nn.softplus`](https://www.tensorflow.org/api_docs/python/tf/math/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](https://www.tensorflow.org/guide/autodiff) | - [TFP Probabilistic Layers: Regression](https://www.tensorflow.org/probability/examples/Probabilistic_Layers_Regression) - [Gaussian Process Latent Variable Models](https://www.tensorflow.org/probability/examples/Gaussian_Process_Latent_Variable_Model) - [Bayesian Modeling with Joint Distribution](https://www.tensorflow.org/probability/examples/Modeling_with_JointDistribution) | `softplus` is a smooth approximation of `relu`. Like `relu`, `softplus` always takes on positive values. ![](https://www.tensorflow.org/images/softplus.png) #### 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` ||