Albhox

@AndrewJSong did it work? When I am trying to run the train I got this ``` File "pointnet2/train.py", line 31, in main model = hydra.utils.instantiate(cfg.task_model, hydra_params_to_dotdict(cfg)) File "/home/alberto/anaconda3/envs/pointnet++/lib/python3.8/site-packages/hydra/utils.py", line 70,...

Dear @tchaton does your implementation take in consideration the different architecture in the segmentation part from the original one in Tensorflow? see reference here https://github.com/erikwijmans/Pointnet2_PyTorch/issues/66 ?

Hand tracking would be great, also in having exposed the generic-hand-joints' it would be helpful: https://vimeo.com/user58338277. So I would be finally able to easily place the ring of my wife's...

Hi @Wuziyi616 and @hua-wu-que , is it possible to extrapolate from the demo or the trained model the category for inference? I can only see the mesh as output, where...

@Hippogriff did yo try the sampling operation from Pytorch3D? maybe that can help you. they have detailed explanations about how their works

``` iou iou_voxels kl loss rec_error class name airplane,aeroplane,plane 0.598022 0.474756 0.0 24.711739 24.711739 bench 0.497740 0.522154 0.0 69.006543 69.006543 cabinet 0.751526 0.747332 0.0 226.335480 226.335480 car,auto,automobile,machine,motorcar 0.748585 0.784312 0.0...

 also why in the unconditional KL goes to 16?

I am in USA, and it is taking days as well.

It seems that two days after this conversation they added support for pytorch https://github.com/microsoft/O-CNN/tree/master/pytorch pretty efficient

They also confirmed that it is still under development.