mindspore.ops.Erfc

class mindspore.ops.Erfc[源代码]

Computes the complementary error function of x element-wise.

\[erfc(x) = 1 - \frac{2} {\sqrt{\pi}} \int\limits_0^{x} e^{-t^{2}} dt\]
Inputs:
  • x (Tensor) - The input tensor. The data type must be float16 or float32. \((N,*)\) where \(*\) means, any number of additional dimensions, its rank should be less than 8.

Outputs:

Tensor, has the same shap dtype as the x.

Raises
  • TypeError – If x is not a Tensor.

  • TypeError – If dtype of x is not float16 or float32.

Supported Platforms:

Ascend GPU

Examples

>>> x = Tensor(np.array([-1, 0, 1, 2, 3]), mindspore.float32)
>>> erfc = ops.Erfc()
>>> output = erfc(x)
>>> print(output)
[1.8427168e+00 1.0000000e+00 1.5728319e-01 4.6912432e-03 2.2351742e-05]