Issue on running test.py

Question

Issue on running test.py

guohaoxiang opened this issue 4 years ago · comments

When I download all the dataset and pretrained models and run 'python test.py 0 3999', the following error occur:

Expected tensor for argument #1 'input' to have the same device as tensor for argument #2 'weight'; but device 0 does not equal 1 (while checking arguments for cudnn_convolution)

Could you please give me some suggestions on how to fix this?

Gopal Sharma · Answer 1 · Thu Feb 25 2021 07:50:00 GMT+0800 (China Standard Time)

Can you try single gpu instead of multi gpu? It seems tensors in some operation are on different gpu devices.

Haoxiang Guo · Answer 2 · Thu Feb 25 2021 11:14:17 GMT+0800 (China Standard Time)

It works now! Thanks a lot for your suggestion. If I want to forward my own point cloud data (already stored in h5 format) to ParSeNet to get the segmentation label, which command should I use?

zizichong · Answer 3 · Mon Oct 30 2023 13:15:26 GMT+0800 (China Standard Time)

hello, when i run "bash download_dataset.sh" according to readme, i can't found the file "predictions.h5", I also can't download the file on the website. I'm guessing you might still have that dataset, and if so, can you send me a copy, thank!