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

[BUG]: abp_pcap_detection example should run in C++ mode #1675

Closed
2 tasks done
dagardner-nv opened this issue May 1, 2024 · 3 comments · Fixed by #1687
Closed
2 tasks done

[BUG]: abp_pcap_detection example should run in C++ mode #1675

dagardner-nv opened this issue May 1, 2024 · 3 comments · Fixed by #1687
Assignees
Labels
bug Something isn't working

Comments

@dagardner-nv
Copy link
Contributor

Version

24.06

Which installation method(s) does this occur on?

Source

Describe the bug.

This example runs in Python mode, however there is nothing about the pipeline which should prevent it from running in C++ mode.

With the changes in PR #1674 it is possible to run in C++ mode, however the results do not match those of Python mode.

Minimum reproducible example

No response

Relevant log output

Click here to see error details

[Paste the error here, it will be hidden by default]

Full env printout

Click here to see environment details

[Paste the results of print_env.sh here, it will be hidden by default]

Other/Misc.

No response

Code of Conduct

  • I agree to follow Morpheus' Code of Conduct
  • I have searched the open bugs and have found no duplicates for this bug report
@dagardner-nv dagardner-nv added the bug Something isn't working label May 1, 2024
@dagardner-nv dagardner-nv self-assigned this May 1, 2024
@dagardner-nv
Copy link
Contributor Author

dagardner-nv commented May 3, 2024

data being emitted from the pcap-preprocess stage (both dataframe and tensors) is identical in both modes.

@dagardner-nv
Copy link
Contributor Author

Verified the inconsistencies exist in v23.11

@dagardner-nv
Copy link
Contributor Author

dagardner-nv commented May 3, 2024

Issue appears to be that 100% of the values int he probs tensor coming out of the inference stage have a value of 1.0.

Running a C++ pipeline with the triton stage hard-coded to use the Python impl yields correct results

@dagardner-nv dagardner-nv moved this from Todo to Review - Ready for Review in Morpheus Boards May 3, 2024
@rapids-bot rapids-bot bot closed this as completed in #1687 May 8, 2024
rapids-bot bot pushed a commit that referenced this issue May 8, 2024
* Update the `pcap-preprocess` stage to ensure tensors are in row major as required by Triton.
* Update the `pcap-preprocess` stage to cast float64 data to model's expected input of float32, removing the need to specify  `force_convert_inputs`. Since this stage is specific to this pipeline & model.

Closes #1675

## By Submitting this PR I confirm:
- I am familiar with the [Contributing Guidelines](https://github.com/nv-morpheus/Morpheus/blob/main/docs/source/developer_guide/contributing.md).
- When the PR is ready for review, new or existing tests cover these changes.
- When the PR is ready for review, the documentation is up to date with these changes.

Authors:
  - David Gardner (https://github.com/dagardner-nv)

Approvers:
  - Michael Demoret (https://github.com/mdemoret-nv)

URL: #1687
@github-project-automation github-project-automation bot moved this from Review - Ready for Review to Done in Morpheus Boards May 8, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
Status: Done
Development

Successfully merging a pull request may close this issue.

1 participant