RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. about cornernet-lite HOT 8 OPEN

Hi, Thanks for trying out CornerNet-Lite! Were you able to resolve this?
Note that the code in this repo as-is requires CUDA 10. Perhaps you can check if your conda environment contains the correct PyTorch installation for your local setup. Otherwise, upgrading your CUDA should resolve this.
Yun

from cornernet-lite.

I met the same problem. Have you solved it? My CUDA is 10.0.

from cornernet-lite.

@yangqing-yq
Hi，how do you solve this problem?? I made this mistake, too.
Thank you!

from cornernet-lite.

I met the same problem. Have you solved it? My CUDA is 10.0.

@yghcats @Tension001 Sorry, My CUDA is 9.2, I still not try 10.0 version yet. I will let you know my result as soon as I tried it out.

from cornernet-lite.

@yangqing-yq
I have a problem with the driver to correct it.
Thank you

from cornernet-lite.

I have solved this problem by upgrading my NVIDIA driver. My former driver is 384, which does not match CUDA 10.0. CUDA 10.0 needs 410 or 418.

from cornernet-lite.

my cuda is CUDA Version 8.0.61 .solve this problem by using pytorch 1.0.0 py3.7_cuda9.0.176_cudnn7.4.1_1

from cornernet-lite.

@KeeaattJj Does this mean there is a way to get around needing CUDA 10?

from cornernet-lite.