Python | PyTorch asin () method

The torch.asin () function provides support for the inverse sine function in PyTorch. The input is assumed to be in the range [-1, 1] and outputs the output in radians. Returns nan, if the input is not in the range [-1, 1]. Input type — tensor, and if the input contains more than one element, the elementwise inverse sine is calculated.

Syntax : torch.asin (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 , 0.2 , 0.0 , - 2 ])

print (a)

 
# Usage reverse sin functions and
# save the result to & # 39; b & # 39;

b = torch.asin (a)

print (b)

Exit:

 tensor ([1.0000, -0.5000, 3.4000, 0.2000, 0.0000, -2.0000]) tensor ([1.5708, -0.5236, nan, 0.2014, 0.0000, nan]) 

Code # 2: Visualization

< / p>

Exit:

 tensor ([- 1.5708, -1.0297, -0.7956, -0.6082, -0.4429 , -0.2898, -0.1433, 0.0000, 0.1433, 0.2898, 0.4429, 0.6082, 0.7956, 1.0297, 1.5708]) 


# PyTorch library import

import torch

 
# Import NumPy library

import numpy as np

 
# Import matplotlib.pylot function

import matplotlib.pyplot as plt

 
# Vector size 15 with values ​​from -1 to 1

a = np.linspace ( - 1 , 1 , 15 )

  
# Applying the inverse sine function and
# saving the result to & # 39; b & # 39;

b = torch.asin (torch .FloatTensor (a))

 

print (b)

 
# Building

plt.plot (a, b.numpy (), color = `red` , marker = " o "

plt.title ( " torch.asin "

plt.xlabel ( "X"

plt.ylabel ( "Y"

 
plt.show ()