Closed thomas-enxuli closed 1 year ago
Hi @zhijian-liu , thanks for the amazing work! Quick question regarding the coordinates here. I see that in https://github.com/mit-han-lab/spvnas/blob/master/core/datasets/semantic_kitti.py#L198
pc_ -= pc_.min(0, keepdims=1)
The coordinates are made to be non-negative. Is there a constraint that voxel indices for sparse tensor or point tensor to be non-negative? Thanks
It's a common practice to normalize the coordinates to be non-negative. This is because some sparse convolution libraries do not support negative indices.
Hi @zhijian-liu , thanks for the amazing work! Quick question regarding the coordinates here. I see that in https://github.com/mit-han-lab/spvnas/blob/master/core/datasets/semantic_kitti.py#L198
The coordinates are made to be non-negative. Is there a constraint that voxel indices for sparse tensor or point tensor to be non-negative? Thanks