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。
*** RuntimeError: CUDA error: out of memory.
原文:https://www.cnblogs.com/leifzhang/p/15269683.html