bitwise-not.md

Title	Description	Subjects	Tags	CatalogContent
.bitwise_not()	Performs element-wise bitwise NOT operation on the input tensor, flipping each bit (0 becomes 1 and 1 becomes 0). Applicable to integer and boolean tensors.	AI Data Science	AI Data Types Deep Learning Functions	intro-to-py-torch-and-neural-networks paths/data-science

In PyTorch, the .bitwise_not() function performs an element-wise bitwise NOT operation on the input tensor. This flips each bit of the tensor’s binary representation, turning 0 to 1 and 1 to 0. It works for integer tensors (signed or unsigned) and boolean tensors (where it acts as a logical NOT).

Syntax

torch.bitwise_not(input, *, out=None)

• input: A tensor of integer or boolean dtype.
• out (Optional): The output tensor to store the result.

Example

The following example demonstrates the usage of the .bitwise_not() function:

import torch

# Create a boolean tensor
tensor_in = torch.tensor([True, False, True])

# Apply bitwise NOT
result = torch.bitwise_not(tensor_in)

print(result)

The above code produces the following output:

tensor([False,  True, False])