search

Pointcept / PointTransformerV3

[CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3)
MIT License
583 stars 30 forks source link

Question about Test mode of GridSample #47

Closed pycoco closed 1 month ago

pycoco commented 1 month ago

thanks for your great work. I'm confuse about why to use a for loop with the max points of the all voxels here. could you please tell me the reason? And the input data is a list which is different with train( a dict). https://github.com/Pointcept/Pointcept/blob/c759914eb3ab8255455c80c00472ab0bc664a20c/pointcept/datasets/transform.py#L855

Gofinge commented 1 month ago

Make sure each point belongs to a sub point cloud and is directly predicted by network.