search

hkchengrex / Cutie

[CVPR 2024 Highlight] Putting the Object Back Into Video Object Segmentation
https://hkchengrex.com/Cutie/
MIT License
579 stars 60 forks source link

Attempting to deserialize object on a CUDA #37

Closed cyq329191721 closed 5 months ago

cyq329191721 commented 6 months ago

I got a problem,yestorday,I test the project ,but it show the error : Attempting to deserialize object on a CUDA ' RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.What should id do?

hkchengrex commented 6 months ago

Are you trying to train? CPU-only training is not supported?

cyq329191721 commented 6 months ago

Are you trying to train? CPU-only training is not supported?

no,i'm not train,i have a model,but i only have cpu in my computer。

hkchengrex commented 6 months ago

Can you clarify what you are trying to do?

CuriousTank commented 6 months ago

torch.cuda.is_available() must be False if you don't have a GPU device