PyTorch – How to compute element-wise logical XOR of tensors?

torch.logical_xor() computes the element-wise logical XOR of the given two input tensors. In a tensor, the elements with zero values are treated as False and non-zero elements are treated as True. It takes two tensors as input parameters and returns a tensor with values after computing the logical XOR.

Syntax

torch.logical_xor(tensor1, tensor2)

where tensor1 and tensor2 are the two input tensors.

Steps

To compute element-wise logical XOR of given input tensors, one could follow the steps given below −

• Import the torch library. Make sure you have it already installed.

• Create two tensors, tensor1 and tensor2, and print the tensors.

• Compute torch.logical_xor(tesnor1, tesnor2) and assign the value to a variable.

• Print the final result after performing the element-wise logical XOR operation.

Example 1

# import torch library
import torch

# define two Boolean tensors
tensor1 = torch.tensor([True, True, True, False, False])
tensor2 = torch.tensor([True, False, False, True, True])

# display the defined tensors
print("Tensor 1:<br>", tensor1)
print("Tensor 2:<br>", tensor2)

# compute XOR of tensor1 and tensor2 and display
tensor_xor = torch.logical_xor(tensor1, tensor2)
print("XOR result:<br>", tensor_xor)

Output

Tensor 1:
 tensor([ True, True, True, False, False])
Tensor 2:
 tensor([ True, False, False, True, True])
XOR result:
 tensor([False, True, True, True, True])

Example 2

# import torch library
import torch

# define two tensors
tensor1 = torch.tensor([True, True, True, False, False])
tensor2 = torch.tensor([1, 0, 123, 23, -12])

# display the defined tensors
print("Tensor 1:<br>", tensor1)
print("Tensor 2:<br>", tensor2)

# compute XOR of tensor1 and tensor2 and display
tensor_xor = torch.logical_xor(tensor1, tensor2)
print("XOR result:<br>", tensor_xor)

Output

Tensor 1:
 tensor([ True, True, True, False, False])
Tensor 2:
 tensor([ 1, 0, 123, 23, -12])
XOR result:
 tensor([False, True, False, True, True])

Example 3

# import torch library
import torch

# define two tensors
tensor1 = torch.tensor([12, 3, 11, 21, -12])
tensor2 = torch.tensor([1, 0, 123, 0, -2])

# display the defined tensors
print("Tensor 1:<br>", tensor1)
print("Tensor 2:<br>", tensor2)

# compute XOR of tensor1 and tensor2 and display
tensor_xor = torch.logical_xor(tensor1, tensor2)
print("XOR result:<br>", tensor_xor)

Output

Tensor 1:
 tensor([ 12, 3, 11, 21, -12])
Tensor 2:
 tensor([ 1, 0, 123, 0, -2])
XOR result:
 tensor([False, True, False, True, False])