Closed ChenxMa closed 6 months ago
Hi, it seems a pytorch version problem, I changed the pytorch from 1.9.1+cu111 to 1.6.0+cu101 by pip install torch==1.6.0+cu101 torchvision==0.7.0+cu101 -f https://download.pytorch.org/whl/torch_stable.html and then recompiled pointnet2, finally it worked!
Hi, thank you for your work, I'm trying to reproduce it, but when I try this:
CUDA_VISIBLE_DEVICES=0 python network/test.py --config handtracknet_test_SimGrasp.yml --num_worker 0
I encountered: 0%| | 0/120 [00:00<?, ?it/s]CUDA kernel failed : no kernel image is available for execution on the device
I googled this error, it said pytorch or CUDA is not consistent with GPU Compute Capability, however, when I run code to test it, it passed.
My GPU is 1660s, and the Compute Capability is 7.5
Is there any chance you can help me solve this error? Thank you!