Installation and Setup of PyTorch

PyTorch is a popular open-source machine learning library for Python which provides a flexible framework for building and training deep learning models. In this article, we will walk you through the process of installing and setting up PyTorch on your machine.

Step 1: Python Installation

Before installing PyTorch, ensure that Python is installed on your system. PyTorch supports Python versions 3.6 or higher. If Python is not installed, visit the Python website at and download the latest version for your operating system.

Step 2: Installing PyTorch

There are different ways to install PyTorch, depending on your platform and requirements. The recommended approach is to install PyTorch via Anaconda, a popular package manager for Python.

  1. Visit the Anaconda website at and download the Anaconda installer compatible with your operating system.

  2. Follow the installation instructions provided by Anaconda for your OS, and make sure to add Anaconda to your system PATH during the installation process.

  3. Once Anaconda is installed, open the Anaconda Navigator or Anaconda Prompt (terminal/command line) and create a new environment for PyTorch. You can create a new environment named "pytorch_env" by running the following command in your terminal:

conda create -n pytorch_env python=3.8
  1. Activate the newly created environment by running the following command:
conda activate pytorch_env
  1. Now, you can install PyTorch by executing the following command:
conda install pytorch torchvision torchaudio cudatoolkit=XX.X -c pytorch

Replace "XX.X" with the version of CUDA Toolkit installed on your system. If you don't have CUDA, you can omit the "cudatoolkit" flag. Also, if you want to install PyTorch without GPU acceleration, remove the "cudatoolkit" flag.

  1. After the installation is complete, test your PyTorch installation by running the following Python code:
import torch


If the output shows the PyTorch version installed, congratulations! PyTorch is successfully installed on your system.

Option 2: Installing PyTorch via pip

If you prefer using pip, you can install PyTorch by running the following command in your terminal:

pip install torch torchvision

Note that pip installs the CPU-only version of PyTorch. If you want GPU support, you'll need to have CUDA installed on your system and follow the appropriate steps provided by PyTorch.


In this article, we have covered the installation and setup process for PyTorch. By following the outlined steps, you should now have a working PyTorch environment on your machine. With PyTorch installed, you can start exploring the vast array of deep learning capabilities and build your own machine learning models. Happy coding!

noob to master © copyleft