tf.math.erf

Computes the Gauss error function of x element-wise. In statistics, for non-negative values of \(x\), the error function has the following interpretation: for a random variable \(Y\) that is normally distributed with mean 0 and variance \(1/\sqrt{2}\), \(erf(x)\) is the probability that \(Y\) falls in the range \([−x, x]\).

tf.math.erf(
    x: _atypes.TensorFuzzingAnnotation[TV_Erf_T], name=None
) -> _atypes.TensorFuzzingAnnotation[TV_Erf_T]

For example:

tf.math.erf([[1.0, 2.0, 3.0], [0.0, -1.0, -2.0]])
<tf.Tensor: shape=(2, 3), dtype=float32, numpy=
array([[ 0.8427007,  0.9953223,  0.999978 ],
       [ 0.       , -0.8427007, -0.9953223]], dtype=float32)>

x A Tensor. Must be one of the following types: bfloat16, half, float32, float64.
name A name for the operation (optional).

A Tensor. Has the same type as x.

If x is a SparseTensor, returns SparseTensor(x.indices, tf.math.erf(x.values, ...), x.dense_shape)