Compute element-wise logical AND, OR and NOT of tensors in PyTorch

In this article, we are going to see how to compute element-wise logical AND, OR, and NOT of given tensors in PyTorch. We can compute this by using the torch.logical_and(), torch.logical_or(), and torch.logical_not() methods. Let’s discuss all of them one by one.

Compute element-wise with logical AND

torch.logical_and() – This method is used to compute the element-wise logical AND of the given tensor. This method treated the non-zero values as True and zero values as False. The following syntax is used to compute logical AND.

Syntax: torch.logical_and(input, other)

Parameters

• input –  This is our input tensor
• other – This tensor is to compute AND with input tensor.

Return : This method returns a tensor with values we get after computing the logical AND.

Example 1:

The following program is to compute element-wise logical AND on two 1D tensors having boolean values.

Python3

# Import the required library
import torch

# create two tensors having boolean values
tens_1 = torch.tensor([True, True, False, False])
tens_2 = torch.tensor([True, False, True, False])

# display the above created tensors
print("Input Tensor 1: ", tens_1)
print("Input Tensor 2: ", tens_2)

# compute the logical AND of input1 and input2
tens = torch.logical_and(tens_1, tens_2)

# print result
print("\nAfter Compute Logical AND: ", tens)

Output:

Example 2:

The following program is to understand how to compute element-wise logical AND on two 2D tensors.

Python3

# Import the required library
import torch

# create two tensors
tens_1 = torch.tensor([[10, 0], [0, 20]])
tens_2 = torch.tensor([[0, 30], [0, 40]])

# display the tensors
print("Input Tensor 1: \n", tens_1)
print("Input Tensor 2: \n", tens_2)

# compute the logical AND
tens = torch.logical_and(tens_1, tens_2)

# print result
print("After Compute Logical AND: \n", tens)

Output:

Compute element-wise with logical OR

torch.logical_or() – This method is used to compute the element-wise logical OR of the given tensor. This method also treated the non-zero values as True and zero values as False. The following syntax is used to compute logical OR.

Syntax: torch.logical_or(input, other)

Parameters

• input –  This is our input tensor
• other – This tensor is to compute OR with input tensor.

Return –returns a tensor with values we get after computing the logical OR.

Example 1:

The following program is to know how to compute element-wise logical OR on two 1D tensors.

Python3

# Import the required library
import torch

# create two tensors
tens_1 = torch.tensor([[10, 0, 20, 0]])
tens_2 = torch.tensor([[0, 30, 40, 0]])

# display the tensors
print("\n Input Tensor 1: ", tens_1)
print("\n Input Tensor 2: ", tens_2)

# compute the logical OR
tens = torch.logical_or(tens_1, tens_2)

# print result
print("\n After Compute Logical OR: ", tens)

Output:

Example 2:

The following program is to understand how to compute element-wise logical OR on two 2D tensors.

Python3

# Import the required library
import torch

# create two tensors
tens_1 = torch.tensor([[11, 0], [0, 12]])
tens_2 = torch.tensor([[0, 13], [0, 14]])

# display the tensors
print("\n Input Tensor 1: \n", tens_1)
print("\n Input Tensor 2: \n", tens_2)

# compute the logical OR
tens = torch.logical_or(tens_1, tens_2)

# print result
print("\n After Compute Logical OR: \n", tens)

Output:

Compute element-wise with logical NOT

torch.logical_not() – This method is used to compute the element-wise logical NOT of the given input tensor. This method also treated the non-zero values as True and zero values as False.  The following syntax is used to compute logical NOT.

Syntax – torch.logical_not(input)

Parameter – 

• input – This is our input tensor

Return –This method returns a tensor with values we get after computing the logical NOT.

The following program is to understand how to compute element-wise logical NOT of tensor.

Python3

# import required library
import torch

# create two tensors
tens_1 = torch.tensor([11, 0])


# display the tensors
print("\n Input Tensor 1: \n", tens_1)

# compute the logical NOT
tens = torch.logical_not(tens_1)

# display result
print("\n After Compute Logical NOT: \n", tens)

Output: