I’m training a model to predict an angle in the [0, 2*pi) interval and I want to use a loss function that understands that we’re working on a circumference.
I defined the loss function cos_loss, the idea of the penalty is to encourage the model to keep predictions in the desired interval.

I’ve been getting into Neural Networks recently and I understand a lot of the basics. As of recent I wrote a CNN with Keras that sorts images of cats and dogs into 37 different breeds. Making the model and getting the data was easy and I have now successfully trained the model to get about 60% accuracy according to Keras metrics. However I have no idea how to print the result when its making predictions.