Line 278: losses['loss_point'] = loss_bbox.sum() / num_points
Line 335: weight_dict = {'loss_ce': 1, 'loss_points': args.point_loss_coef}
one is "loss_points" and another is "loss_point" (an "s" is different) ! This would cause that the point loss is actually not used, which is fully wrong!
In
models/p2pnet.py
:Line 278:
losses['loss_point'] = loss_bbox.sum() / num_points
Line 335:weight_dict = {'loss_ce': 1, 'loss_points': args.point_loss_coef}
one is "loss_points" and another is "loss_point" (an "s" is different) ! This would cause that the point loss is actually not used, which is fully wrong!