ssd_tensorflow
                                
                                
                                
                                    ssd_tensorflow copied to clipboard
                            
                            
                            
                        Absolute difference instead of Normalized difference?
For the loc_loss calculation, absolute difference between ground truth and anchor have been taken instead of normalized difference between ground truth and anchor. Why is it so? Am I missing something? Because paper have suggested this in equation (2) in page num. 5.
https://github.com/seann999/ssd_tensorflow/blob/f381dba71029a329a2b23763b804289eb8069b4b/model.py#L82