The torch.atan () function provides support for the inverse tangent function in PyTorch. This gives the output in radians. Input type — tensor, and if the input contains more than one element, the inverse tangent is calculated for each element.

Syntax : torch.atan (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 reverse tanning function and # saving the result to & # 39; b & # 39; b = torch.atan (a) print (b)

Exit:

 tensor ([1.0000, -0.5000, 3.4000, 0.2000, 0.0000, -2.0000]) tensor ([0.7854, -0.4636, 1.2847, 0.1974, 0.0000, -1.1071]) 

Code # 2: Vi rendering

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

Exit:

 tensor ([- 1.3734, -1.3416, -1.2978, -1.2341, -1.1342, -0.9601, -0.6202, 0.0000, 0.6202, 0.9601, 1.1342, 1.2341, 1.2978, 1.3416, 1.3734])