When I trained my net ,this strange error happened. Though I reboot my computer, it is still there!!!
somebody help me,please.
Environment: Win10,Pytorch1.1
CUDA out of memory. Tried to allocate 352.00 MiB (GPU 0; 8.00 GiB total capacity; 5.71 GiB already allocated; 239.85 MiB free; 85.67 MiB cached)