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

#Some functions of Pytorch, the deep learning python library

An short introduction about PyTorch and about the chosen functions.

  • torch.narrow
  • torch.polar
  • torch.split
  • torch.reshape
  • torch.abs

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
import numpy as np  #will be useful in examples

Function 1 - torch.narrow

It returns a narrowed version of the given input tensor.

a = torch.tensor([[[1, 2, 3], [3, 4., 5]], [[6, 7, 9],[34, 5,8]],[[21, 67, 10], [34, 11,15]]]) 
a.shape 
#Now we pass this tensor to the narrow function 
torch.Size([3, 2, 3])