且构网

分享程序员开发的那些事...
且构网 - 分享程序员编程开发的那些事

非法指令:运行任何Tensorflow程序时出现4错误

更新时间:2022-01-28 00:03:02

确定 如果您拥有的2.66 GHz版本在我看来是2010年发布的Arrendale架构,在这种情况下,绝对没有任何机会使用它,因为该组件没有最新的张量流二进制文件所需要的AVX指令.

OK If you have the 2.66 GHz version that seems to me to be the the Arrendale architecture released 2010 in which case there is absolutely no chance it's going to work since that thing doesn't have AVX instructions as needed by the latest binaries of tensor flow.

除非您的CPU是Sandy Bridge或更高版本(因此是AVX指令)

Unless your CPU is Sandy Bridge or newer (so AVX instructions)

您的选择是:

1)获得更新的CPU
2)安装较旧版本的张量流
3)从源头编译张量流

1) get a newer CPU
2) install an older version of tensor flow
3) compile tensor flow from source

有关降级版本,请参见.
非法指令(转储核心)tensorflow
在Python中导入张量流时的非法指令

for downgrade version see.
Illegal instruction(core dumped) tensorflow
Illegal instruction when import tensorflow in Python

编辑
看起来,尽管所有Core(i3,i5,i7)和Xeon CPU Sandy Bridge及更新版本都支持AVX,但截至2018年为止,对于Celron或Pentium CPU而言,情况并非如此.如果购买硬件,请检查计算机包含的内容.

EDIT
It seems that although all Core (i3, i5, i7) and Xeon CPU Sandy Bridge and newer support AVX, this is not true of Celron, nor Pentium CPU's to this day, as of 2018. Check what the machine contains if buying hardware.