Introduction to Torch package

The torch package contains data structures for multi-dimensional tensors and mathematical operations over these are defined. Additionally, it provides many utilities for efficient serializing of Tensors and arbitrary types, and other useful utilities.

We'll look into the below functions

torch.numel
torch.arange
torch.linspace
torch.logspace
torch.cat

# Import torch and other required modules
import torch

Function 1 - torch.numel(input) → int

Returns the total number of elements in the input tensor.

# Example 1
# https://pytorch.org/docs/stable/torch.html
a = torch.randn(1, 2, 3, 4, 5)
torch.numel(a)

The above example create a tensor of 120 elements