-
Notifications
You must be signed in to change notification settings - Fork 4.6k
Integrating Particle Flow Network (PFN) Models into TICLv5 #47550
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
Conversation
|
cms-bot internal usage |
|
+code-checks Logs: https://cmssdt.cern.ch/SDT/code-checks/cms-sw-PR-47550/44025 |
|
test parameters: |
|
A new Pull Request was created by @Moanwar for master. It involves the following packages:
@Martin-Grunewald, @Moanwar, @cmsbuild, @jfernan2, @mandrenguyen, @mmusich, @srimanob, @subirsarkar can you please review it and eventually sign? Thanks. cms-bot commands are listed here |
|
@cmsbuild, please test |
|
-1 Failed Tests: RelVals
RelVals |
|
+code-checks Logs: https://cmssdt.cern.ch/SDT/code-checks/cms-sw-PR-47550/44027 |
|
+1 |
|
test parameters:
|
|
+hlt
|
|
@cmsbuild, please test |
|
-1 Failed Tests: RelVals
RelVals
|
OK, this is due to #47378, will fix shortly. |
|
+Upgrade |
|
This pull request is fully signed and it will be integrated in one of the next master IBs (but tests are reportedly failing). This pull request will now be reviewed by the release team before it's merged. @rappoccio, @sextonkennedy, @mandrenguyen, @antoniovilela (and backports should be raised in the release meeting by the corresponding L2) |
|
ignore tests-rejected with external-failure |
|
+1 |
This PR introduces Particle Flow Network (PFN) models trained using TICLv5 reconstruction data through a simple CNN/DNN-based approach. Two separate models were developed: one for trackster energy regression and another for particle identification. These models are integrated into different reconstruction steps, specifically CLU3D (pattern recognition) and trackster linking. To optimize processing time, the models are saved in ONNX format.
Additionally, a new inference plugin has been implemented to run these models, now serving as the default for TICLv5.
-This PR needs to be tested with the following cms-data PR: cms-data/RecoHGCal-TICL#8
-Additionally, this PR should be tested on the .203 workflow :
-test parameters:
workflow_opts= -w upgrade
workflow = 29888.203,29688.203
Tagging @felicepantaleo @waredjeb @hatakeyamak