# Python | PyTorch tanh () method

One of the many activation functions is the hyperbolic tangent function (also known as tanh), which is defined as ,

The hyperbolic tangent function outputs in the range (-1, 1), thus mapping strongly negative inputs to negative values. Unlike the sigmoidal function, only near-zero values ​​are mapped to near-zero outputs, and this solves the "vanishing gradients" problem to some extent. The hyperbolic tangent function is differentiable at every point, and its derivative turns out to be Since the expression includes the tanh function, its value can be reused to speed up backpropagation.

Although the network is less likely to get stuck compared to the sigmoid function, the hyperbolic tangent function still suffers from "vanishing gradients." A rectified linear unit (ReLU) can be used to overcome this problem.

The ` torch.tanh () ` function provides support for the hyperbolic tangent in PyTorch. It expects input in radians, and output is in the range [-∞, ∞]. Input type — tensor, and if the input contains more than one element, the element-wise hyperbolic tangent is calculated.

Syntax : torch.tanh (x, out = None)

Parameters :
x : Input tensor
name (optional): Output tensor

Return type : A tensor with the same type as that of x.

Code # 1:

` `

` # PyTorch library import import torch   # Constant tensor of size 6 a = torch.FloatTensor ([ 1.0 , - 0 .5 , 3.4 , - 2.1 , 0.0 , - 6.5 ]) print (a)    # Using the tanh function and # saving the result to & # 39; b & # 39; b = torch.tanh (a ) print (b) `

` `

Exit:

` 1.0000 -0.5000 3.4000 -2.1000 0.0000 -6.5000 [ torch.FloatTensor of size 6] 0.7616 -0.4621 0.9978 -0.9705 0.0000 -1.0000 [torch.FloatTensor of s ize 6] `

Code # 2: Visualization

` `

` # Import PyTorch library import torch    # Importing the NumPy library import numpy as np    # Import matplotlib.pylot import matplotlib.pyplot as plt   # Vector size 15 with values ​​from -5 to 5 a = np.linspace ( - 5 , 5 , 15 )   # Applying hyperbolic tangent function and # save the result to & # 39; b & # 39; b = torch.tanh (torch.FloatTensor (a))   print (b)   # Build plt. plot (a, b.numpy (), color = ’red’ , marker = "o" )  plt.title ( "torch.tanh" )  plt.xlabel ( "X" )  plt.ylabel ( "Y" )    plt.show () `

` `

Exit:

` -0.9999 -0.9996 -0.9984 -0.9934 -0.9728 -0.8914 -0.6134 0.0000 0.6134 0.8914 0.9728 0.9934 0.9984 0.9996 0.9999 [torch.FloatTensor of size 15] `

## Shop Learn programming in R: courses

\$FREE Best Python online courses for 2022

\$FREE Best laptop for Fortnite

\$399+ Best laptop for Excel

\$ Best laptop for Solidworks

\$399+ Best laptop for Roblox

\$399+ Best computer for crypto mining

\$499+ Best laptop for Sims 4

\$

Latest questions

PythonStackOverflow

Common xlabel/ylabel for matplotlib subplots

PythonStackOverflow

Check if one list is a subset of another in Python

PythonStackOverflow

How to specify multiple return types using type-hints

PythonStackOverflow

Printing words vertically in Python

PythonStackOverflow

Python Extract words from a given string

PythonStackOverflow

Why do I get "Pickle - EOFError: Ran out of input" reading an empty file?

PythonStackOverflow

Python os.path.join () method

PythonStackOverflow

Flake8: Ignore specific warning for entire file

## Wiki

Python | How to copy data from one Excel sheet to another

Common xlabel/ylabel for matplotlib subplots

Check if one list is a subset of another in Python

How to specify multiple return types using type-hints

Printing words vertically in Python

Python Extract words from a given string

Cyclic redundancy check in Python

Finding mean, median, mode in Python without libraries