Wonders of 5 Pytorch tensors

Pytorch is a library for processing tensors. A Tensor is a number, vector , matrix or any n-dimentional array.

  • function 1 : zeros_like
  • function 2 : eye
  • function 3 : conj
  • function 4 : chunk
  • function 5 : narrow

Before we begin, let's install and import PyTorch

# Uncomment and run the appropriate command for your operating system, if required

# Linux / Binder
# !pip install numpy torch==1.7.0+cpu torchvision==0.8.1+cpu torchaudio==0.7.0 -f https://download.pytorch.org/whl/torch_stable.html

# Windows
# !pip install numpy torch==1.7.0+cpu torchvision==0.8.1+cpu torchaudio==0.7.0 -f https://download.pytorch.org/whl/torch_stable.html

# MacOS
# !pip install numpy torch torchvision torchaudio
# Import torch and other required modules
import torch

Function 1 - zeros_like

zeros_like tensor returns a tensor filled with '0', with the same size as input.

# Example 1 - working 
x = torch.tensor([[1, 2], [3, 4.]])
x
tensor([[1., 2.],
        [3., 4.]])