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.

Sign up for GitHub

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

Jump to bottom

Always got nan result. #71

Open
EEWenbinWu opened this issue Jun 8, 2023 · 2 comments
Open

Always got nan result. #71

EEWenbinWu opened this issue Jun 8, 2023 · 2 comments
Assignees
@zerollzeng

Comments

@EEWenbinWu
Copy link

EEWenbinWu commented Jun 8, 2023 •
edited
Loading

the model is resnet50 from TensorRT8 folder. onnx can produce the correct result, but tinytrt can't.
image
the onnx result
image
the tinytrt result
image
@EEWenbinWu EEWenbinWu reopened this Jun 8, 2023
@zerollzeng
Copy link
Owner

Could you please share the reproduce script then I can debug it. Thanks!

@zerollzeng
Copy link
Owner

I have to say I didn't put much effort on the python api and I didn't add accuracy test for it. So it might have bugs.

Source code in https://github.com/zerollzeng/tiny-tensorrt/blob/master/src/PyTrt.cpp

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@zerollzeng zerollzeng

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@EEWenbinWu @zerollzeng