Closed Tavish9 closed 11 months ago
Thanks for your interest.
I think there is no issue here.
For example, under the ScanRefer settings, the point_instance_label
will set the labels of the point clouds associated with the target object to 0, and the remaining points will be set to -1.
Then, in the compute_points_obj_cls_loss_hard_topk()
function, operation L179 will obtain labels for 1024 seed points, which are either 0 or -1. Operation L180 will set the labels of all seed points with a label of -1 to 131. Operation L181 will convert the labels into one-hot vectors.
Additionally, a label of 0
won't cause logical errors. Its corresponding one-hot label is 10000...
Thank you for your gracious reply. Your answer was indeed correct, and I apologize for my previous misunderstanding. I truly appreciate your support.
Hi, thanks for you great work.
But I have a question about "point_instance_label" when reading the code.
In
src/joint_det_dataset.py
, function_get_target_boxes
:Is there any problem with setting the label of the point to the sequence index
t
?In my opinion, the code should be modified as follows:
In this way, all points in the same scene can be correctly classified into the corresponding object IDs.
If we set the
point_instance_label
tot
, the label of the point can only be 0 on the scanrefer dataset whenjoint_det
is false, which leads to logic errors.