[15_0_X] Backport of #47801 (Add the Scouting Glo-ParT inference facility) #47853
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Contributor
|
A new Pull Request was created by @yiyangzha for CMSSW_15_0_X. It involves the following packages:
@cmsbuild, @ftorrresd, @hqucms, @jfernan2, @mandrenguyen can you please review it and eventually sign? Thanks. cms-bot commands are listed here
|
Contributor
|
cms-bot internal usage |
yiyangzha
changed the title
yiyangzha
changed the title
Contributor
Author
|
backport of #47801 |
Contributor
|
test parameters: |
Contributor
|
please test |
Contributor
|
-1 Failed Tests: UnitTests RelVals RelVals-NANO Unit TestsI found 4 errors in the following unit tests: ---> test test-btvNano-run had ERRORS ---> test test-btvNano-check had ERRORS ---> test test_MC_22_crosscheck had ERRORS and more ... RelValsExpand to see more relval errors ...RelVals-NANO |
Contributor
Author
|
Hi, I think those test failures are not related to our PR. |
Contributor
|
please test with cms-data/RecoBTag-Combined#64 |
Contributor
|
-1 Failed Tests: UnitTests RelVals RelVals-NANO Unit TestsI found 4 errors in the following unit tests: ---> test test-btvNano-run had ERRORS ---> test test-btvNano-check had ERRORS ---> test test_MC_22_crosscheck had ERRORS and more ... RelValsExpand to see more relval errors ...RelVals-NANO |
Contributor
|
Hi @yiyangzha -- If I understood correctly, the changes in a583e00 were merged to master by #47702 , but never backported to CMSSW_15_0. Is it correct? |
Contributor
Author
Hi @ftorrresd -- Yes, exactly. |
Contributor
|
+1 Size: This PR adds an extra 16KB to repository Comparison SummarySummary:
NANO Comparison SummarySummary:
Nano size comparison Summary:
|
Contributor
|
+1 |
Contributor
|
+1 |
cmsbuild
added
reconstruction-approved
fully-signed
and removed
reconstruction-pending
pending-signatures
labels
Contributor
|
This pull request is fully signed and it will be integrated in one of the next CMSSW_15_0_X IBs (tests are also fine) and once validation in the development release cycle CMSSW_15_1_X is complete. This pull request will now be reviewed by the release team before it's merged. @antoniovilela, @rappoccio, @sextonkennedy, @mandrenguyen (and backports should be raised in the release meeting by the corresponding L2) |
Contributor
|
+1 |
Contributor
|
I think this PR is leading to IB failures, see e.g: here. I think that cms-sw/cmsdist#9804 should be backported to the 15.0.X branch, see cms-sw/cmsdist#9804 (comment) |
Contributor
Author
Hi Marco, the RecoBTag/Combined/data/UParTAK4/PUPPI/V01/modelfile/model.onnx in your failure was added by RecoBTag-Combined#66. |
Contributor
@yiyangzha it wasn't applied, see the fix PR: https://github.com/cms-sw/cmsdist/pull/9808/files.
testing in PR is not sufficient. The PR tests worked because it was tested with the cms-data PR at #47853 (comment). But the tag in cmsdist must be backported as well to work in IBs. This PR merged alone is responsible of the failures. |
Contributor
Author
Hi @mmusich , thanks for explaining. In that case, the PR#47853 indeed should be back-ported. Sorry we didn't realize it when testing. |
Contributor
|
Hi @mmusich -- Thanks for the explanations. Since cms-sw/cmsdist#9808 in merged, is there any action to be taken? |
Contributor
no, let's wait the |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Please test this PR with cms-data/RecoBTag-Combined#67
PR description:
This PR adds the Scouting Glo-ParT model's inference facility into CMSSW, prepared for Scouting NanoAOD official production.
Model performance details are provided in these [slides] (accessible via CMS). This would add 13 taggers and 4 mass regression correctors to Scouting NanoAOD.
Scouting Global Particle Transformer (Glo-ParT) is an inclusive tagging model for AK8 scouting PFjets. It functions as both a global tagger and a mass regression model for AK8 scouting PFjets and can also be utilized as a pre-trained model. Further details can be found in the slides.
PR validation:
The PR passed the tests listed at https://cms-sw.github.io/PRWorkflow.html
Backport:
Backport of PR #47801