Open In App

How to Compute Pairwise Distance Between Two Vectors in PyTorch

Last Updated : 21 Apr, 2022
Improve
Improve
Like Article
Like
Save
Share
Report

In this article, we will discuss how to compute the pairwise distance between two vectors in PyTorch

The vector size should be the same and we can use PairwiseDistance() method to compute the pairwise distance between two vectors.

PairwiseDistance() method

PairwiseDistance() method computes the pairwise distance between two vectors using the p-norm. This method is provided by the torch module. The below syntax is used to compute pairwise distance.

Syntax – torch.nn.PairwiseDistance(p=2)

Return – This method Returns the pairwise distance between two vectors.

Example 1:

The following program is to understand how to compute the pairwise distance between two vectors.

Python3




import torch
  
# define first vector
vec1 = torch.tensor([1., 2., 3., 4.])
  
# define second vector
vec2 = torch.tensor([5., 6., 7., 8.])
  
# display tensors
print("\n First Vector: ", vec1)
print("\n Second Vector: ", vec2)
  
# define an instance of the PairwiseDistance
pdist = torch.nn.PairwiseDistance(p=2)
  
# compute the pairwise distance
result = pdist(vec1, vec2)
  
# display result
print("\n Pairwise Distance:", result)


Output:

 

Example 2:

Python3




import torch
  
# define first vector
vec1 = torch.tensor([[0.2245, 0.2959, 0.3597, 0.6766],
                     [0.3685, 0.6469, 0.3765, 0.7898],
                     [0.4577, 0.3228, 0.4699, 0.2389]])
  
# define second vector
vec2 = torch.tensor([[0.2423, 0.4667, 0.4434, 0.3598],
                     [0.2956, 0.6932, 0.5387, 0.2245],
                     [0.8277, 0.2597, 0.9834, 0.9987]])
  
# display tensors
print("\n First Vector: \n", vec1)
print("\n Second Vector: \n", vec2)
  
# define an instance of the PairwiseDistance
pdist = torch.nn.PairwiseDistance(p=2)
  
# compute the pairwise distance
result = pdist(vec1, vec2)
  
# display result
print("\n Pairwise Distance: \n", result)


Output:

 



Like Article
Suggest improvement
Share your thoughts in the comments

Similar Reads