corner loss misuse label info?

[windyrobin]

        heading = angle_decode(heading_res_norm, heading_class_label)
        size = size_decode(size_res_norm, mean_size_array, size_class_label)

        corners_loss, corner_gts = self.get_corner_loss(
            (center_preds, heading, size),
            (center_label, heading_label, size_label)
        )

heading use heading_class_label as the main part, should use heading_pred instead?

[zhixinwang]

Regularization Loss. Use the heading class label to avoid the accumulative error especially at the early stage.