Python | PyTorch cos () method

The torch.cos () function provides support for the cosine function in PyTorch. It expects input in radians, and output is in the range [-1, 1]. Input type — tensor, and if the input contains more than one element, the element-wise cosine is calculated.

Syntax : torch.cos (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:

Exit :

 1.0000 -0.5000 3.4000 -2.1000 0.0000 -6.5000 [torch.FloatTensor of size 6] 0.5403 0.8776 -0.9668 -0.5048 1.0000 0.9766 [torch.FloatTensor of size 6] 

  Code # 2: Rendering

# 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 cos function and
# saving the result to & # 39; b & # 39;

b = torch.cos (a)

print (b)

# Import PyTorch library

import torch

  
# Importing the 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 , < / code> 5 , 15 )

 
# Applying the cosine function and
# save result to & # 39; b & # 39;

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

  

print (b)

  
# Plotting

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

plt.title ( " torch.cos "

plt.xlabel ( "X"

plt.ylabel ( "Y"

 
plt.show ()

Output:

 0.2837 -0.4138 -0.9090 -0.9598 -0.5414 0.1417 0.7556 1.0000 0.7556 0.1417 -0.5414 -0.9598 -0.9090 -0.4138 0.2837 [torch.FloatTensor of size 15]