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

Five Interesting Pytorch Functions

The torch package which seats on pytorch was created by the Facebook's AI research laboratory. The package contains multi-dimensional tensors and mathematical operations.An interesting fact about pytorch is that it has a CUDA counterpart that enables you to run your tensor computations on an NVIDIA GPU with compute capability >= 3.0

List of functions in view
  1. chunk
  2. transpose
  3. rand
  4. add
  5. inverse

Before we begin, let's install and import PyTorch

First, let's import the torch library

import torch

Next we create a tensor, in this case, i created a 7 by 5 tensor, that is 7 rows and 5 columns, it's a 2 dimensional tensor.

t1 = torch.tensor([[1,2,3,4,5],[1,2,3,4,5],[2,3,4,5,6],[3,4,5,6,7],[4,5,6,7,8],[3,4,5,6,7],[1,1,1,1,1]])
t1
tensor([[1, 2, 3, 4, 5],
        [1, 2, 3, 4, 5],
        [2, 3, 4, 5, 6],
        [3, 4, 5, 6, 7],
        [4, 5, 6, 7, 8],
        [3, 4, 5, 6, 7],
        [1, 1, 1, 1, 1]])