tf.math.log_sigmoid

TensorFlow 1 version View source on GitHub

Computes log sigmoid of x element-wise.

Specifically, y = log(1 / (1 + exp(-x))). For numerical stability, we use y = -tf.nn.softplus(-x).

x A Tensor with type float32 or float64.
name A name for the operation (optional).

A Tensor with the same type as x.