kleinlee / DH_live

每个人都能用的数字人
669 stars 147 forks source link

这个错误怎么解决呢 #22

Closed peano2 closed 1 month ago

peano2 commented 1 month ago

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.

kleinlee commented 1 month ago

maybe you installed pytorch with cpu version? Run the followings to verify your pytorch version. import torch print(torch.cuda.is_available())