|---| | [ View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.21.0/tensorflow/python/ops/math_ops.py#L4203-L4245) | Computes log sigmoid of `x` element-wise. #### View aliases **Compat aliases for migration** See [Migration guide](https://www.tensorflow.org/guide/migrate) for more details. [`tf.compat.v1.log_sigmoid`](https://www.tensorflow.org/api_docs/python/tf/math/log_sigmoid)
tf.math.log_sigmoid( x, name=None ) Specifically, `y = log(1 / (1 + exp(-x)))`. For numerical stability, we use `y = -tf.nn.softplus(-x)`.


| ## Args || |---|---| | `x` | A Tensor with type `float32` or `float64`. | | `name` | A name for the operation (optional). |



| ## Returns || |---|---| | A Tensor with the same type as `x`. ||
#### Usage Example: If a positive number is large, then its log_sigmoid will approach to 0 since the formula will be `y = log( / (1 + ) )` which approximates to `log (1)` which is 0. x = tf.constant([0.0, 1.0, 50.0, 100.0]) tf.math.log_sigmoid(x) If a negative number is large, its log_sigmoid will approach to the number itself since the formula will be `y = log( 1 / (1 + ) )` which is `log (1) - log ( (1 + ) )` which approximates to `- ` that is the number itself. x = tf.constant([-100.0, -50.0, -1.0, 0.0]) tf.math.log_sigmoid(x)