Open gordonyfg opened 3 years ago
In tensorflow implementation and your 3DSSD-pytorch implementation, I can see there is a vote_loss. https://github.com/qiqihaer/3DSSD-pytorch/blob/d0c856e4c1b6cb69810fc0b0562ebc9a42e5bace/lib/builder/loss_builder.py#L190
_Is it still available in this repo? If not, should I add voteloss to improve the performance?
_And I am not sure how to get end_points[maps_dict.PL_LABEL_BOXES_3D] from forward_retdict. Could you give me some hints please?
vote_offset = self.forward_ret_dict['ctr_offsets'] vote_base = self.forward_ret_dict['centers_origin'] bs, pts_num, _ = vote_offset.shape gt_boxes_3d = end_points[maps_dict.PL_LABEL_BOXES_3D]
Appreciate your efforts and thank you for your time
In tensorflow implementation and your 3DSSD-pytorch implementation, I can see there is a vote_loss. https://github.com/qiqihaer/3DSSD-pytorch/blob/d0c856e4c1b6cb69810fc0b0562ebc9a42e5bace/lib/builder/loss_builder.py#L190
_Is it still available in this repo? If not, should I add voteloss to improve the performance?
_And I am not sure how to get end_points[maps_dict.PL_LABEL_BOXES_3D] from forward_retdict. Could you give me some hints please?
Appreciate your efforts and thank you for your time