daveredrum / Pointnet2.ScanNet

PointNet++ Semantic Segmentation on ScanNet in PyTorch with CUDA acceleration
MIT License
130 stars 30 forks source link

What are the results reported? #3

Closed ghost closed 3 years ago

ghost commented 4 years ago

What are the reported results? Mean IoU or accuracy?

daveredrum commented 4 years ago

Hey @clavichord93, the reported results are the Mean IoU for the 20 ScanNet benchmark classes. We don't report the per point accuracy here, unfortunately.