PyTorch .erfinv()

In PyTorch, the .erfinv() function returns the inverse error function of each element in the input tensor. The inverse error function in the range (−1,1) is: $$erfinv(erf(x))=x$$.

Syntax

torch.erfinv(input, *, out=None) → Tensor

Or,

torch.special.erfinv(input, *, out=None) → Tensor

Parameters:

• input: A tensor containing values in the range (-1, 1).
• out (Optional): A tensor to store the output. If provided, the result is written to this tensor.

Return value:

It returns a new tensor of the same shape as the input, containing the computed inverse error function values for each corresponding element.

Example

In this example, the inverse error function values of each tensor is computed using .erfinv():

import torch

# Define a tensor
x = torch.tensor([0, 0.5, -1.])

result = torch.erfinv(torch.tensor(x))

print(result)

Copy to clipboard
Copy to clipboard

Here is the output:

tensor([ 0.0000,  0.4769,    -inf])

Copy to clipboard
Copy to clipboard