Trying to predict emotions in real time

[DisplayFace]

I trained the classifier as explained in your post, and got a trained model. I'm now trying to put together a script that can take a grayscale image from the RPi Camera V2, then return a value from 0-6 depending on the emotion it detected using the trained model. However, I don't know how to feed the landmarks I extracted from the image to the model. I tried replicating some snippets of your code in order to get the desired results, but always ended up feeding incompatible data to the "predict()" function. How could this be done?