*** RuntimeError: CUDA error: out of memory.

CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1.

这个error 的原因是，当期指定的GPU的显存不足，可以关闭现有的process，或者重指定显卡编号。

标签：显存,RuntimeError,error,指定,CUDA,memory,device,might,out
来源： https://www.cnblogs.com/leifzhang/p/15269683.html