chrischoy / SpatioTemporalSegmentation

4D Spatio-Temporal Semantic Segmentation on a 3D video (a sequence of 3D scans)
MIT License
288 stars 51 forks source link

a problem with scannet about training #53

Closed zouyanmei closed 3 years ago

zouyanmei commented 3 years ago

thanks for your share. when I tried to training in ScanNet, I got a problem like this "File "/home/zou/anaconda3/envs/sparse/lib/python3.8/site-packages/MinkowskiEngine-0.4.3-py3.8-linux-x86_64.egg/MinkowskiEngine/Common.py", line 272, in convert_region_type region_offset = torch.IntTensor(region_offset) TypeError: only integer tensors of a single element can be converted to an index".