Machine learning essentially involves a ton of trial and error. You're letting a program try millions of different settings to land on an algorithm that sort of does what you want it to do. This process is really really slow unless you have the hardware required to speed this up.
The type of computations that the process does are well suited for graphics cards, rather than regular processors. **It is pretty much required that you run the training process on a desktop or server capable GPU.** Running this on your CPU means it can take weeks to train your model, compared to several hours on a GPU.
## Hardware Requirements
**TL;DR: you need at least one of the following:**
- **A powerful CPU**
- Laptop CPUs can often run the software, but will not be fast enough to train at reasonable speeds
Windows 7 and 8 might work. Your mileage may vary. Windows has an installer which will set up everything you need. See: https://github.com/deepfakes/faceswap/releases
Most Ubuntu/Debian or CentOS based Linux distributions will work. There is a Linux install script that will install and set up everything you need. See: https://github.com/deepfakes/faceswap/releases
Experimental support for GPU-accelerated, native Apple Silicon processing (e.g. Apple M1 chips). Installation instructions can be found [further down this page](#macos-apple-silicon-install-guide).
Intel based macOS systems should work, but you will need to follow the [Manual Install](#manual-install) instructions.
**In its current iteration, the project relies heavily on the use of the command line, although a gui is available. if you are unfamiliar with command line tools, you may have difficulty setting up the environment and should perhaps not attempt any of the steps described in this guide.** This guide assumes you have intermediate knowledge of the command line.
Windows and Linux now both have an installer which installs everything for you and creates a desktop shortcut to launch straight into the GUI. You can download the installer from https://github.com/deepfakes/faceswap/releases.
Setting up faceswap can seem a little intimidating to new users, but it isn't that complicated, although a little time consuming. It is recommended to use Linux where possible as Windows will hog about 20% of your GPU Memory, making faceswap run a little slower, however using Windows is perfectly fine and 100% supported.
Download and install the latest Python 3 Anaconda from: https://www.anaconda.com/download/. Unless you know what you are doing, you can leave all the options at default.
### Git
Download and install Git for Windows: https://git-scm.com/download/win. Unless you know what you are doing, you can leave all the options at default.
## Setup
Reboot your PC, so that everything you have just installed gets registered.
- If using the GUI you can go to the Help menu and select "Check for Updates...". If updates are available go to the Help menu and select "Update Faceswap". Restart Faceswap to complete the update.
The recommended install method is to use a Conda3 Environment as this will handle the installation of Nvidia's CUDA and cuDNN straight into your Conda Environment. This is by far the easiest and most reliable way to setup the project.
- MiniConda3 is recommended: [MiniConda3](https://docs.conda.io/en/latest/miniconda.html)
Alternatively you can install Python (>= 3.7-3.9 64-bit) for your distribution (links below.) If you go down this route and are using an Nvidia GPU you should install CUDA (https://developer.nvidia.com/cuda-zone) and cuDNN (https://developer.nvidia.com/cudnn). for your system. If you do not plan to build Tensorflow yourself, make sure you install the correct Cuda and cuDNN package for the currently installed version of Tensorflow (Current release: Tensorflow 2.8. Release v1.0: Tensorflow 1.15). You can check for the compatible versions here: (https://www.tensorflow.org/install/source#gpu).
It is highly recommended that you setup faceswap inside a virtual environment. In fact we will not generally support installations that are not within a virtual environment as troubleshooting package conflicts can be next to impossible.
If using Conda3 then setting up virtual environments is relatively straight forward. More information can be found at [Conda Docs](https://docs.conda.io/projects/conda/en/latest/user-guide/tasks/manage-environments.html)
If using a default Python distribution then [virtualenv](https://github.com/pypa/virtualenv) and [virtualenvwrapper](https://virtualenvwrapper.readthedocs.io) may help when you are not using docker.
It is recommended to clone the repo with git instead of downloading the code from http://github.com/deepfakes/faceswap and extracting it as this will make it far easier to get the latest code (which can be done from the GUI). To clone a repo you can either use the Git GUI for your distribution or open up a command prompt, enter the folder where you want to store faceswap and enter:
If you are experiencing issues, please raise them in the [faceswap Forum](https://faceswap.dev/forum) instead of the main repo. Usage questions raised in the issues within this repo are liable to be closed without response.
