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

SOME USEFUL PYTORCH FUNCTIONS

An short introduction about PyTorch and about the chosen functions.

  • torch.linspace
  • torch.eye
  • torch.full
  • torch.cat
  • torch.Tensor.clone

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 - torch.linspace

torch.linspace is used to create a 1D equally spaced tensor between the values start and end . We can specify the size of the tensor with the steps parameters. The default is steps=100

# Example 1 
torch.linspace(1, 10)
tensor([ 1.0000,  1.0909,  1.1818,  1.2727,  1.3636,  1.4545,  1.5455,  1.6364,
         1.7273,  1.8182,  1.9091,  2.0000,  2.0909,  2.1818,  2.2727,  2.3636,
         2.4545,  2.5455,  2.6364,  2.7273,  2.8182,  2.9091,  3.0000,  3.0909,
         3.1818,  3.2727,  3.3636,  3.4545,  3.5455,  3.6364,  3.7273,  3.8182,
         3.9091,  4.0000,  4.0909,  4.1818,  4.2727,  4.3636,  4.4545,  4.5455,
         4.6364,  4.7273,  4.8182,  4.9091,  5.0000,  5.0909,  5.1818,  5.2727,
         5.3636,  5.4545,  5.5455,  5.6364,  5.7273,  5.8182,  5.9091,  6.0000,
         6.0909,  6.1818,  6.2727,  6.3636,  6.4545,  6.5455,  6.6364,  6.7273,
         6.8182,  6.9091,  7.0000,  7.0909,  7.1818,  7.2727,  7.3636,  7.4545,
         7.5455,  7.6364,  7.7273,  7.8182,  7.9091,  8.0000,  8.0909,  8.1818,
         8.2727,  8.3636,  8.4545,  8.5455,  8.6364,  8.7273,  8.8182,  8.9091,
         9.0000,  9.0909,  9.1818,  9.2727,  9.3636,  9.4545,  9.5455,  9.6364,
         9.7273,  9.8182,  9.9091, 10.0000])