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

Segmentation fault (core dumped) #8

Open
sissini opened this issue Nov 1, 2021 · 4 comments
Open

Segmentation fault (core dumped) #8

sissini opened this issue Nov 1, 2021 · 4 comments

Comments

@sissini
Copy link

sissini commented Nov 1, 2021

i follwed your instruction, and run 'python tools/create_data.py waymo_data_prep --root_path=data/Waymo --split train --nsweeps=1', but failed, shows 'Segmentation fault (core dumped)'
did u ever meet this problem? hope for help

@YoushaaMurhij
Copy link

I have the same problem while using ./centerpoint in the instructions

&&&& RUNNING TensorRT.sample_onnx_centerpoint # ./centerpoint
[11/01/2021-20:05:38] [I] Building and running a GPU inference engine for CenterPoint
[11/01/2021-20:05:43] [I] [TRT] ----------------------------------------------------------------
[11/01/2021-20:05:43] [I] [TRT] Input filename:   ../data/centerpoint/pointpillars_trt.onnx
[11/01/2021-20:05:43] [I] [TRT] ONNX IR version:  0.0.7
[11/01/2021-20:05:43] [I] [TRT] Opset version:    11
[11/01/2021-20:05:43] [I] [TRT] Producer name:    pytorch
[11/01/2021-20:05:43] [I] [TRT] Producer version: 1.10
[11/01/2021-20:05:43] [I] [TRT] Domain:
[11/01/2021-20:05:43] [I] [TRT] Model version:    0
[11/01/2021-20:05:43] [I] [TRT] Doc string:
[11/01/2021-20:05:43] [I] [TRT] ----------------------------------------------------------------
[11/01/2021-20:05:43] [W] [TRT] /home/jenkins/workspace/OSS/L0_MergeRequest/oss/parsers/onnx/onnx2trt_utils.cpp:226: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
[11/01/2021-20:05:43] [I] [TRT] No importer registered for op: ScatterND. Attempting to import as plugin.
[11/01/2021-20:05:43] [I] [TRT] Searching for plugin: ScatterND, plugin_version: 1, plugin_namespace:
[11/01/2021-20:05:43] [I] [TRT] Successfully created plugin: ScatterND
[11/01/2021-20:05:43] [W] [TRT] Tensor DataType is determined at build time for tensors not marked as input or output.
[11/01/2021-20:06:07] [I] [TRT] Some tactics do not have sufficient workspace memory to run. Increasing workspace size may increase performance, please check verbose output.
[11/01/2021-20:06:29] [I] [TRT] Detected 1 inputs and 6 output network tensors.
[11/01/2021-20:06:29] [I] getNbInputs: 2

[11/01/2021-20:06:29] [I] getNbOutputs: 6

[11/01/2021-20:06:29] [I] getNbOutputs Name: 315

[11/01/2021-20:06:29] [E] [TRT] INVALID_ARGUMENT: Cannot find binding of given name: input.1
filePath[idx]: ../data/centerpoint//points/0a0d6b8c2e884134a3b48df43d54c36a.bin
[11/01/2021-20:06:29] [I] [INFO] pointNum : 278272
Segmentation fault (core dumped)

@YoushaaMurhij
Copy link

YoushaaMurhij commented Nov 2, 2021

@CarkusL, I have tried your steps on pointpillars with Waymo config. But I faced the error above! Can you please tell me what I am missing!.
Thanks!

@CarkusL
Copy link
Owner

CarkusL commented Nov 7, 2021

@CarkusL, I have tried your steps on pointpillars with Waymo config. But I faced the error above! Can you please tell me what I am missing!. Thanks!

[11/01/2021-20:06:29] [E] [TRT] INVALID_ARGUMENT: Cannot find binding of given name: input.1

I think you should check the input name of your onnx model

@YoushaaMurhij
Copy link

Thanks, I have already solved this problem. Yeah, the input was not correct.

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

3 participants