cuda 10.2,cudnn 8.0.4,paddle:2.2.
安装完后跑推理代码出错，老是出错，难道paddle不能一次安装成功推理？环境依赖有那么苛刻？搞的XXX
C++ Traceback (most recent call last):
No stack trace in paddle, may be caused by external reasons.
Error Message Summary:
FatalError: Segmentation fault is detected by the operating system.
[TimeInfo:Aborted at 1637680470 (unix time) try "date -d @1637680470" if you are using GNU date]
[SignalInfo:SIGSEGV (@0x0) received by PID 4303 (TID 0x7f9e26ade740) from PID 0]
段错误 (核心已转储)
5条答案
按热度按时间zxlwwiss1#
您好，我们已经收到了您的问题，会安排技术人员尽快解答您的问题，请耐心等待。请您再次检查是否提供了清晰的问题描述、复现代码、环境&版本、报错信息等。同时，您也可以通过查看官网API文档、常见问题、历史Issue、AI社区来寻求解答。祝您生活愉快～
Hi! We've received your issue and please be patient to get responded. We will arrange technicians to answer your questions as soon as possible. Please make sure that you have posted enough message to demo your request. You may also check out the API，FAQ，Github Issue and AI community to get the answer.Have a nice day!
q35jwt9p2#
@LielinJiang@jzhang533@wanglun@lileding self.predictor.run() 运行直接挂掉，
C++ Traceback (most recent call last):
No stack trace in paddle, may be caused by external reasons.
Error Message Summary:
FatalError: Segmentation fault is detected by the operating system.
[TimeInfo:Aborted at 1637680470 (unix time) try "date -d @1637680470" if you are using GNU date]
[SignalInfo:SIGSEGV (@0x0) received by PID 4303 (TID 0x7f9e26ade740) from PID 0]
voase2hg3#
麻烦贴一下具体的代码 self.predictor.run()，看不出是啥
mwyxok5s4#
cuda 10.2,和cudnn 8.0.4是不是两个版本不匹配？官网的安装解释：CUDA 工具包10.1/10.2配合cuDNN 7 (cuDNN版本>=7.6.5, 如需多卡支持，需配合NCCL2.7及更高)，不能超过8吧，我换成7.6.5没有问题
@LielinJiang
t98cgbkg5#
可以先 export GLOG_v=3 并且 删掉 py脚本中的config.disable_glog_info()，然后运行查看打屏日志，会有更详细报错，如果没有请提供下模型和脚本。或者可以加下QQ群：959308808