Giter Site home page Giter Site logo

johndpope / deepfakes Goto Github PK

View Code? Open in Web Editor NEW

This project forked from sergiovirahonda/deepfakes

0.0 1.0 0.0 67.43 MB

This repository is part of a project which seeks to build DIY deep fakes' models from scratch. Also it's part of an article that explains how to achieve such task.

Dockerfile 0.01% Python 0.14% Jupyter Notebook 99.85%

deepfakes's Introduction

DeepFakes

This repository is part of a project which seeks to build DIY deep fakes' models from scratch. Also it's part of an article that explains how to achieve such task. In this repo you'll contain the files required to preprocess videos for deep fakes generation, models training and swap faces in the final frames. Also, it shows you how to rebuild the original video with the transformed frames to finally get the deep fake. Finally, I show you how to use DeepFaceLab on Google Colab as an alternative to your DIY solution.

The repository contains several folders that contain the necessary files to achieve every stage of the project:

  • Deep faces dataset contains the raw videos that I'll be using along this project but also has the workspace folder ready to be fed into DeepFaceLab.
  • Deep fakes - Docker files contains the required files to build a Docker container to train your DIY solution on Google AI Platorm
  • Notebooks contains all the Notebooks in .ipynb format used in this project: within DFL folder you'll find the resulting notebook that I used to obtain the Deep fake video with DeepFaceLab and within Kaggle folder you'll find all notebooks used for my DIY solution: data preprocessing, models training and face swapping / building the deep fake video.
  • Deep fakes - Final videos contains the deep fake videos obtain with the DIY solution as well as with DeepFaceLab.

Find the fully interactive notebooks here, here, here and here.

Find the final models here and here

Find the transformed images and final video frames here

I hope this was helpful for you!

deepfakes's People

Contributors

sergiovirahonda avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.