Preprocessing a Dataset for Deep Fakes

Preprocessing a Dataset for Deep Fakes

Preprocessing a Dataset for Deep Fakes

“Deep fakes – the use of deep learning to swap one person’s face into another in video – are one of the most interesting and frightening ways that AI is being used today.

While deep fakes can be used for legitimate purposes, they can also be used in disinformation. With the ability to easily swap someone’s face into any video, can we really trust what our eyes are telling us? A real-looking video of a politician or actor doing or saying something shocking might not be real at all.

In this article series, we’re going to show how deep fakes work, and show how to implement them from scratch. We’ll then take a look at DeepFaceLab, which is the all-in-one Tensorflow-powered tool often used for creating convincing deep fakes.

In the previous articles we’ve been going through tons of theory but now it’s time to get into the actual code to make this project work! In this article, I’ll guide you through what’s required to convert the source (src) and destination (dst) videos into actual images ready to be fed into our autoencoders. If you’re not familiar with these terms, I encourage you to quickly read over previous articles to get some context…”

Source: www.codeproject.com/Articles/5298023/Preprocessing-a-Dataset-for-Deep-Fakes