This repo contains files for Deepfake Detection Project
Deepfakes are synthetic media in which a person in an existing image or video is replaced with someone else's likeness. They are deceiving and with the use of a good algorithm, a deepfake video becomes harder to differ from actual recorded footage or clicked images. The main machine learning methods used to create deepfakes are based on deep learning and involve training generative neural network architectures, such as autoencoders or generative adversarial networks (GANs).
This project aims at building a model which can differentiate between a deepfake and an originally recorded video or image.
- Dataset
- Code
- Suggestions
- Python
- Machine Learning
- Deep learning
- Docker
- AWS
In order to contribute to this repository, you can drop your suggestions,links,code etc. in the file 'suggestions.md' in suggestions folder, regarding other techniques or improvements you think can help this project achieve it's goal.
PS - Add your name at the end of your suggestion. So that your contribution has a name to it. If we use your suggestion, we'll mention you! Cheers!
You can also contribute to improve or increase the dataset. We're collecting deepfakes/manipulated/faceswapped images and their real counterpart images. In order to contribute to dataset, you can add your images to the dataset/images folder.