tf.compat.v1.math.erfcinv

Computes the inverse of complementary error function.

tf.compat.v1.math.erfcinv(
    x, name=None
)

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)>

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

Returns
Inverse complementary error function of `x`.

numpy compatibility

Equivalent to scipy.special.erfcinv

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.

Last updated 2024-04-26 UTC.

tf.compat.v1.math.erfcinv

Args

Returns

numpy compatibility