The RPN and RCNN layers have methods for their respective losses (each has a classification_loss and a regression_loss). We should refactor the methods into functions and move them into the keras_rcnn.losses module to replicate the Keras interface.
In addition, they should, wherever necessary, be refactored to conform to the Keras loss API:
The RPN and RCNN layers have methods for their respective losses (each has a classification_loss and a regression_loss). We should refactor the methods into functions and move them into the keras_rcnn.losses module to replicate the Keras interface.
In addition, they should, wherever necessary, be refactored to conform to the Keras loss API:
and expose the useful Keras alias interface: