Skip to content

Instantly share code, notes, and snippets.

@MSFTserver
Last active February 27, 2022 08:03
Show Gist options
  • Save MSFTserver/1b863cc4e8246f6e2bf39ee8f7161e89 to your computer and use it in GitHub Desktop.
Save MSFTserver/1b863cc4e8246f6e2bf39ee8f7161e89 to your computer and use it in GitHub Desktop.
Local environment setup to run most GANs for image generators

##***WORK-IN-PROGRESS***##

































How to setup your Local Environment for GANs 🦾

This will walk you through getting your environment setup to run most of the GANs with Anaconda as a Virtual Python Environment.


Tutorial Index

  1. Windows Local
  2. Windows Subsystem for Linux
  3. Linux

System Requirements:

OS: Windows (11/10/8/7), Ubuntu(19,20)

GPU: Nvidia (AMD hasn't been tested)

VRAM: 6gb+


1. Download Tools!






1. Enable subsystem for linux on windows!

  • Option A (control panel)
    • open control panel and click "Programs" from here select "Turn windows feature on or off"
    • this should have opened a new window with a list of features, scroll all the way to the bottom and select "Windows Subsystem for Linux", restart your pc after installing
    • now you actually need a linux distribution
  • Option B (PowerShell)
    • Enable-WindowsOptionalFeature -Online -FeatureName Microsoft-Windows-Subsystem-Linux
    • Optional: Enable-WindowsOptionalFeature -Online -FeatureName VirtualMachinePlatform

2. Download & Prepare linux Distro

  • open the microsoft store app and search "Linux", i went with Ubuntu 20.04
  • setup username and password for linux distribution
  • run the following command to update some things sudo apt update && sudo apt upgrade -y

3. Download & Prepare Anaconda

  • download anaconda with wget https://repo.anaconda.com/archive/Anaconda3-2021.11-Linux-x86_64.sh
  • install the library with bash Anaconda3-2021.11-Linux-x86_64.sh
  • run source bachrc to make use of install
  • install pytorch in conda with conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch






Coming Soon!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment