The torch.acos () function provides support for the inverse cosine 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 inverse cosine is calculated for each element.

Syntax : torch.acos (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)   # Applying the inverse cos and # saving the result to & # 39; b & # 39; b = torch.acos (a) print (b)

Exit:

 tensor ([1.0000, -0.5000, 3.4000, 0.2000, 0.0000, -2.0000]) tensor ([0.0000, 2.0944, nan, 1.3694, 1.5708, nan]) 

Code # 2: Visualization

# Import PyTorch library import torch   # Import NumPy library import numpy as np    # Import of the 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 cosine function and # saving the result to & # 39; b & # 39; b = torch. acos (torch.FloatTensor (a))   print (b)   # Plotting plt.plot (a, b.numpy (), color = `red` , marker = "o" )  plt.title ( " torch.acos " )  plt.xlabel ( "X" )  plt.ylabel ( "Y" )    plt.show ()

Exit:

 tensor ([3.1416, 2.6005, 2.3664, 2.1790, 2.0137, 1.8605, 1.7141, 1.5708, 1.4274, 1.2810, 1.1279, 0.9626, 0.7752, 0.5411, 0.0000])