Putting it all together

In order to run our app, we will need to execute the main function routine (chapter8.py) that loads the pre-trained cascade classifier and the pre-trained MLP and applies them to each frame of the webcam live stream.

However, this time, instead of collecting more training samples, we will start the program with a different option, shown here:

 $ python chapter8.py demo --classifier data/clf1

This will start the application with a new FacialExpressionRecognizerLayout layout, which is a subclass of BasicLayout without any extra UI elements. Let's go over the constructor first, as follows:

1. It reads and initializes all the data that was stored by the training script, like this:

class FacialExpressionRecognizerLayout(BaseLayout):
    def __init__(self, *args,
                 clf_path=None,
                 **kwargs):
        super().__init__(*args, **kwargs...