search

prs-eth / OverlapPredator

[CVPR 2021, Oral] PREDATOR: Registration of 3D Point Clouds with Low Overlap.
https://shengyuh.github.io/predator/index.html
MIT License
512 stars 73 forks source link

When training ModelNet, there is an error, 'tensors used as indices must be long, byte or bool tensors'. #48

Closed ChaunceyQ closed 2 years ago

ChaunceyQ commented 2 years ago

After downloading the datasets and run 'python main.py configs/train/modelnet.yaml', it always reminds that 'tensors used as indices must be long, byte or bool tensors'. I wonder what went wrong.

ShengyuH commented 2 years ago

please comment try ... except here, then try to locate your bug. I didn't encounter this.

Cindy-my commented 1 year ago

After downloading the datasets and run 'python main.py configs/train/modelnet.yaml', it always reminds that 'tensors used as indices must be long, byte or bool tensors'. I wonder what went wrong.

Hey, when I run 'python main.py configs/train/indoor.yaml', I also had this problem. How did you solve the problem? Can you please share?