Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

进行pointpillars推理时c++和python推理均出现Segmentation fault (core dumped)这是什么原因啊 #456

Open
yunyu18 opened this issue Mar 11, 2024 · 2 comments
Assignees

Comments

@yunyu18
Copy link

yunyu18 commented Mar 11, 2024

“----------------------
Error Message Summary:

FatalError: Segmentation fault is detected by the operating system.
[TimeInfo: *** Aborted at 1710145517 (unix time) try "date -d @1710145517" if you are using GNU date ***]
[SignalInfo: *** SIGSEGV (@0x0) received by PID 7083 (TID 0x7f5478c6c200) from PID 0 ***]

Segmentation fault (core dumped)”
这是python推理报错

“WARNING: Logging before InitGoogleLogging() is written to STDERR
W0311 16:16:12.435428 6840 tensorrt.cc:56] You are using Paddle compiled with TensorRT, but TensorRT dynamic library is not found. Ignore this if TensorRT is not needed.
The TensorRT that Paddle depends on is not configured correctly.
Suggestions:

  1. Check if the TensorRT is installed correctly and its version is matched with paddlepaddle you installed.
  2. Configure environment variables as follows:
  • Linux: set LD_LIBRARY_PATH by export LD_LIBRARY_PATH=...
  • Windows: set PATH by set PATH=XXX;%PATH%
  • Mac: set DYLD_LIBRARY_PATH by export DYLD_LIBRARY_PATH=...
    Segmentation fault (core dumped)”
    这是c++推理报错
@will-jl944
Copy link
Collaborator

You are using Paddle compiled with TensorRT, but TensorRT dynamic library is not found. Ignore this if TensorRT is not needed. The TensorRT that Paddle depends on is not configured correctly. Suggestions:

  1. Check if the TensorRT is installed correctly and its version is matched with paddlepaddle you installed.
  2. Configure environment variables as follows:
  • Linux: set LD_LIBRARY_PATH by export LD_LIBRARY_PATH=...
  • Windows: set PATH by set PATH=XXX;%PATH%
  • Mac: set DYLD_LIBRARY_PATH by export DYLD_LIBRARY_PATH=...
    Segmentation fault (core dumped)”
    这是c++推理报错

按照报错信息中的提示,根据你所使用的系统,配置TRT路径即可。例如,假设你使用的是Linux系统,你的TensorRT路径位于path/to/TensorRT,执行如下指令:

export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:path/to/TensorRT/lib

@yunyu18
Copy link
Author

yunyu18 commented Mar 13, 2024

感谢已经解决,但是现在出现了一个新问题,我运行推理时python推理没有问题,但是c++推理报错了:错误信息见下:
[libprotobuf ERROR /paddle/build/third_party/protobuf/src/extern_protobuf/src/google/protobuf/message_lite.cc:119] Can't parse message of type "paddle.framework.proto.ProgramDesc" because it is missing required fields: blocks[0].ops[25].attrs[13].type, blocks[0].ops[34].attrs[13].type, blocks[2].ops[34].attrs[13].type, blocks[2].ops[40].attrs[13].type, blocks[2].ops[48].attrs[13].type, blocks[2].ops[67].attrs[13].type
--- Running analysis [ir_graph_build_pass]
[libprotobuf ERROR /paddle/build/third_party/protobuf/src/extern_protobuf/src/google/protobuf/message_lite.cc:119] Can't parse message of type "paddle.framework.proto.ProgramDesc" because it is missing required fields: blocks[0].ops[25].attrs[13].type, blocks[0].ops[34].attrs[13].type, blocks[2].ops[34].attrs[13].type, blocks[2].ops[40].attrs[13].type, blocks[2].ops[48].attrs[13].type, blocks[2].ops[67].attrs[13].type
terminate called after throwing an instance of 'phi::enforce::EnforceNotMet'
what():
这个该怎么解决啊

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants