Learn practical skills, build real-world projects, and advance your career

PyTorch package - some basic methods nice to know about

I picked the following 5 basic functions, where torch.randn is to create a sample tensor, torch.cat and torch.split to manipulate the created tensor, torch.numel and torch.is_nonzero to evaluate the resulting tensors.

  • function 1: torch.is_nonzero
  • function 2: torch.numel
  • function 3: torch.randn
  • function 4: torch.cat
  • function 5: torch.split

Before we begin, let's install and import PyTorch

import torch

Function 1 - torch.is_nonzero(input) -> bool

  • torch.is_nonzero(input) -> (bool): Returns True if the input is a single element tensor which is not equal to zero after type conversions. i.e. not equal to torch.tensor([0.]) or torch.tensor([0]) or torch.tensor([False]). Throws a RuntimeError if torch.numel() != 1 (even in case of sparse tensors).
# Example 1 - working and returns True
x = torch.Tensor([3.]) # tensor with a single non-zero element
torch.is_nonzero(x)
True

An example of a tensor with a single non-zero element, which returns True.