tf.compat.v1.math.erfcinv

Computes the inverse of complementary error function.

Given x, compute the inverse complementary error function of x. This function is the inverse of tf.math.erfc, and is defined on [0, 2].

tf.math.erfcinv([0., 0.2, 1., 1.5, 2.])
<tf.Tensor: shape=(5,), dtype=float32, numpy=
array([       inf,  0.9061935, -0.       , -0.4769363,       -inf],
      dtype=float32)>

x Tensor with type float or double.
name A name for the operation (optional).

Inverse complementary error function of x.

numpy compatibility

Equivalent to scipy.special.erfcinv