- 版本、环境信息:
1)PaddlePaddle版本:1.3.1
2)CPU:
3)GPU:gpu Tesla P40, cuda9.0 cudnn7
4)系统环境:centos python2.7
- 问题描述:
使用paddle版本enrie模型预测一段时间后就会报如下错误,看不出来是哪一行的问题,请问是为什么?
terminate called after throwing an instance of 'paddle::platform::EnforceNotMet'
what(): unspecified launch failure at [/paddle/paddle/fluid/framework/details/op_handle_base.cc:37]
PaddlePaddle Call Stacks:
0 0x7feba39b7405p void paddle::platform::EnforceNotMet::Init<char const*>(char const*, char const*, int) + 357
1 0x7feba39b7789p paddle::platform::EnforceNotMet::EnforceNotMet(std::__exception_ptr::exception_ptr, char const*, int) + 137
2 0x7feba523bfe1p paddle::framework::details::OpHandleBase::~OpHandleBase() + 337
3 0x7feba5229e91p paddle::framework::details::FetchOpHandle::~FetchOpHandle() + 17
4 0x7feba3a68489p paddle::framework::ir::Node::~Node() + 73
5 0x7feba3a68631p paddle::framework::ir::Node::~Node() + 17
6 0x7feba522b9cbp paddle::framework::details::ClearFetchOp(paddle::framework::ir::Graph*, std::vector<paddle::framework::details::FetchOpHandle*, std::allocator<paddle::framework::details::FetchOpHandle*> >*) + 1995
7 0x7feba51d7254p paddle::framework::details::ThreadedSSAGraphExecutor::Run(std::vector<std::string, std::allocator<std::string> > const&) + 4660
8 0x7feba51cd9bap paddle::framework::details::ScopeBufferedSSAGraphExecutor::Run(std::vector<std::string, std::allocator<std::string> > const&) + 394
9 0x7feba3af57a2p paddle::framework::ParallelExecutor::Run(std::vector<std::string, std::allocator<std::string> > const&, std::string const&) + 562
10 0x7feba39a7d9ep
11 0x7feba39e2d0ep
12 0x7fec08c9b577p PyEval_EvalFrameEx + 28695
13 0x7fec08c9da99p PyEval_EvalCodeEx + 2025
14 0x7fec08c9af68p PyEval_EvalFrameEx + 27144
15 0x7fec08c9c54ep PyEval_EvalFrameEx + 32750
16 0x7fec08c9c54ep PyEval_EvalFrameEx + 32750
17 0x7fec08c9da99p PyEval_EvalCodeEx + 2025
18 0x7fec08c9dcbap PyEval_EvalCode + 26
19 0x7fec08cb701dp
20 0x7fec08cb81c8p PyRun_FileExFlags + 120
21 0x7fec08cb93e8p PyRun_SimpleFileExFlags + 232
22 0x7fec08ccb67cp Py_Main + 2988
23 0x7fec07eb4b45p __libc_start_main + 245
24 0x7fec08d9d07fp
***Aborted at 1564038910 (unix time) try "date -d @1564038910" if you are using GNU date***
PC: @ 0x0 (unknown)
***SIGABRT (@0x1f600006f1e) received by PID 28446 (TID 0x7fec08b9d740) from PID 28446; stack trace:***
@ 0x7fec0896c130 (unknown)
@ 0x7fec07ec89d9 __GI_raise
@ 0x7fec07eca0e8 __GI_abort
@ 0x7febfe07d3df __gnu_cxx::__verbose_terminate_handler()
@ 0x7febfe07bb16 __cxxabiv1::__terminate()
@ 0x7febfe07af91 __cxa_call_terminate
@ 0x7febfe07b79d __gxx_personality_v0
@ 0x7febfe349f56 _Unwind_RaiseException_Phase2
@ 0x7febfe34a244 _Unwind_RaiseException
@ 0x7febfe07bd1b __cxa_throw
@ 0x7feba523bfff paddle::framework::details::OpHandleBase::~OpHandleBase()
@ 0x7feba5229e91 paddle::framework::details::FetchOpHandle::~FetchOpHandle()
@ 0x7feba3a68489 paddle::framework::ir::Node::~Node()
@ 0x7feba3a68631 paddle::framework::ir::Node::~Node()
@ 0x7feba522b9cb paddle::framework::details::ClearFetchOp()
@ 0x7feba51d7254 paddle::framework::details::ThreadedSSAGraphExecutor::Run()
@ 0x7feba51cd9ba paddle::framework::details::ScopeBufferedSSAGraphExecutor::Run()
@ 0x7feba3af57a2 paddle::framework::ParallelExecutor::Run()
@ 0x7feba39a7d9e _ZZN8pybind1112cpp_function10initializeIZN6paddle6pybindL18pybind11_init_coreERNS_6moduleEEUlRNS2_9framework16ParallelExecutorERKSt6vectorISsSaISsEERKSsE152_vIS8_SD_SF_EINS_4nameENS_9is_methodENS_7siblingEEEEvOT_PFT0_DpT1_EDpRKT2_ENUlRNS_6detail13function_callEE1_4_FUNESX_
@ 0x7feba39e2d0e pybind11::cpp_function::dispatcher()
@ 0x7fec08c9b577 PyEval_EvalFrameEx
@ 0x7fec08c9da99 PyEval_EvalCodeEx
@ 0x7fec08c9af68 PyEval_EvalFrameEx
@ 0x7fec08c9c54e PyEval_EvalFrameEx
@ 0x7fec08c9c54e PyEval_EvalFrameEx
@ 0x7fec08c9da99 PyEval_EvalCodeEx
@ 0x7fec08c9dcba PyEval_EvalCode
@ 0x7fec08cb701d run_mod
@ 0x7fec08cb81c8 PyRun_FileExFlags
@ 0x7fec08cb93e8 PyRun_SimpleFileExFlags
@ 0x7fec08ccb67c Py_Main
@ 0x7fec07eb4b45 __libc_start_main
2条答案
按热度按时间efzxgjgh1#
请问 run 哪个脚本报这个错误?
mznpcxlj2#
我自己重写了一下预测的脚本,主要是想询问下这种错误会不会是显卡的问题?因为我换一张卡同样的代码就可以。