How to compare two tensors in PyTorch?

In this article, we are going to see how we can compare two tensors in Pytorch. 

We can compare two tensors by using the torch.eq() method. This method compares the corresponding elements of tensors. It has to return rue at each location where both tensors have equal value else it will return false.

torch.eq() function:

Syntax: torch.eq( First_tensor, Second_tensor, out=None )

Parameters: torch.eq() accept tensors that are we want to compare as parameters.

Return: It return a boolean value. true if tensors are equals else it will return false.

Example 1:

In this example, we are comparing two 1-D tensors using the torch.eq() function in the python programming language .

Python3

# import library
import torch

# Create first tensor
first = torch.Tensor([4.4, 2.4, -9.1,
                      -5.31, 5.3])

# Create second tensor
second = torch.Tensor([4.4, 5.5, -9.1,
                       -5.31, 43])

# print first tensors
print("First Tensor:", first)

# print first tensors
print("Second Tensor:", second)

# Compare element wise tensors
# first and second
print(torch.eq(first, second))

Output:

Example 2:

Under this example, we are comparing 2D tensors PyTorch using the torch.eq() function.

Python3

# import library
import torch

# create two 2D tensors
first = torch.Tensor([[7, -2, 3],
                      [29, 9, -5],
                      [2, -8, 34],
                      [24, 62, 98]])

second = torch.Tensor([[7, -5, 3],
                       [26, 9, -4],
                       [3, -8, 43],
                       [23, -62, 98]])

# print first tensors
print("First Tensor:", first)

# print second tensors
print("Second Tensor:\n", second)


print("After Comparing Both Tensors")

# Compare element wise tensors first
# and second
print(torch.eq(first, second))

Output: