TensorFlow 2.0 Beta is available Learn more

tf.math.sigmoid

Computes sigmoid of x element-wise.

Aliases:

  • tf.compat.v1.math.sigmoid
  • tf.compat.v1.nn.sigmoid
  • tf.compat.v1.sigmoid
  • tf.compat.v2.math.sigmoid
  • tf.compat.v2.nn.sigmoid
  • tf.compat.v2.sigmoid
  • tf.math.sigmoid
  • tf.nn.sigmoid
  • tf.sigmoid
tf.math.sigmoid(
    x,
    name=None
)
View source on GitHub

Specifically, y = 1 / (1 + exp(-x)).

Args:

  • x: A Tensor with type float16, float32, float64, complex64, or complex128.
  • name: A name for the operation (optional).

Returns:

A Tensor with the same type as x.

Scipy Compatibility

Equivalent to scipy.special.expit