PyTorch .atanh()

Khomotso_Ntuli's avatar
Khomotso_Ntuli's avatar
Khomotso_Ntuli
Published Mar 28, 2025
Contribute to Docs

The .atanh() function in PyTorch calculates the inverse hyperbolic tangent for each value in a tensor.

  • Career path

    Data Scientist: Machine Learning Specialist

    Machine Learning Data Scientists solve problems at scale, make predictions, find patterns, and more! They use Python, SQL, and algorithms.
    • Includes 27 Courses
    • With Professional Certification
    • Beginner Friendly.
      95 hours
  • Free course

    Intro to PyTorch and Neural Networks

    Learn how to use PyTorch to build, train, and test artificial neural networks in this course.
    • Intermediate.
      3 hours

Syntax

torch.atanh(input, *, out=None)

Parameters:

  • input (Tensor): A tensor containing values strictly between -1 and 1 (exclusive).
  • out (Tensor, optional): The output tensor to store the result. If not provided, a new tensor is created.

Return Value:

Returns a new tensor where each value is the inverse hyperbolic tangent of the corresponding value in input.

Example

The following example demonstrates the usage of the .atanh() function:

import torch


# Create a tensor
x = torch.tensor([0.5, -0.3, 0.0])


# Calculate the inverse hyperbolic tangent
y = torch.atanh(x)


# Print the result
print(y)

The above code produces the following output:

tensor([ 0.5493, -0.3095,  0.0000])

All contributors

Contribute to Docs

Learn PyTorch on Codecademy

  • Career path

    Data Scientist: Machine Learning Specialist

    Machine Learning Data Scientists solve problems at scale, make predictions, find patterns, and more! They use Python, SQL, and algorithms.
    • Includes 27 Courses
    • With Professional Certification
    • Beginner Friendly.
      95 hours
  • Free course

    Intro to PyTorch and Neural Networks

    Learn how to use PyTorch to build, train, and test artificial neural networks in this course.
    • Intermediate.
      3 hours