Improving your data

There are no silver bullets to magically make your data better, but there are some ways that you can tweak your data to improve the training of the AI.

Linear color

When you’re filming you may film in logarithmic scale (log) color, where the scale represents an exponential change. This is great for storing a large color range while filming but does not work well for training a deepfake. To get the best results from your training, you’ll want to convert your video into a linear color space (where a change of some number is consistently represented). It doesn’t really matter which one, but all your data and converted videos should be the same. Since most content is Rec.709, we recommend that you use that unless you have a good reason to pick a different color space.

Author’s note

Color science is a very robust field, and a full examination is outside the scope of this book. However, a basic understanding can help. Rec.709 is...