Learn practical skills, build real-world projects, and advance your career
Updated 3 years ago
5 Powerful Interesting Pytorch functions For Data Science Beginners
WHAT IS PYTORCH?
It’s a Python-based scientific computing package targeted at two sets of audiences:
A replacement for NumPy to use the power of GPUs
a deep learning research platform that provides maximum flexibility and speed
What are Tensors?
Tensors are similar to NumPy’s ndarrays, with the addition being that Tensors can also be used on a GPU to accelerate computing.
The following are the 5 powerful functions
- torch.from_numpy()
- torch.split()
- torch.transpose()
- torch.unbind()
- torch.randint()
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.from_numpy
A numpy array can be easily converted to a tensor using the functioin above
# Example 1 - Given a numpy array below
import numpy as np
x = np.array([[10., 20.], [30., 40.]])
# this can be change to tensor as follows
y = torch.from_numpy(x)
x, y
(array([[10., 20.],
[30., 40.]]),
tensor([[10., 20.],
[30., 40.]], dtype=torch.float64))