Superclustering DNN in TICLv5 #20
Closed
Conversation
This file contains 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
tcuisset
force-pushed
the
dnn-supercls-ticlv5
branch
from
1c4f13d to
6c05d4f
Compare
tcuisset
force-pushed
the
dnn-supercls-ticlv5
branch
from
6c05d4f to
0a1d080
Compare
waredjeb
reviewed
Apr 8, 2024
| reco::CaloCluster::particleFlow, // algoID (copying from output of PFECALCSuperClusterProducer) | ||
| hitsAndFractions.at(0).first // seedId : TODO figure out if needed or if we need to put the highest energy hit | ||
| ); | ||
| caloCluster.setCorrectedEnergy(emTrackster.regressed_energy()); |
There was a problem hiding this comment.
Is it expected to have the regressed energy for the CLUE3D Tracksters? Is the plan to have an energy regression model on the CLUE3D EM Tracksters before the SuperClustering?
There was a problem hiding this comment.
This still needs to be determined. We need to figure out if the CaloCluster corrected energy is used anywhere in the GsfTrack chain.
waredjeb
reviewed
Apr 8, 2024
waredjeb
reviewed
Apr 8, 2024
waredjeb
reviewed
Apr 8, 2024
tcuisset
force-pushed
the
dnn-supercls-ticlv5
branch
from
ef89765 to
4c531cf
Compare
tcuisset
changed the base branch from
ticlv5_14_0_0_pre0
to
ticlv5_14_1_X_2024-04-18-2300
|
Now rebased against ticlv5_14_1_X_2024-04-18-2300 |
tcuisset
force-pushed
the
dnn-supercls-ticlv5
branch
2 times, most recently
from
c388bfd to
ac56f5d
Compare
felicepantaleo
force-pushed
the
ticlv5_14_1_X_2024-04-18-2300
branch
from
2039d22 to
adbee95
Compare
felicepantaleo
force-pushed
the
ticlv5_14_1_X_2024-04-18-2300
branch
2 times, most recently
from
92e6a7f to
f7db43e
Compare
Added missing header in StreamerInputModule.h
…30-1 Remove unused constants in CondCore/EcalPlugins/plugins/Ecal*_PayloadInspector.cc
…loTrigger Removed duplicate cfi file in L1Trigger/L1CaloTrigger
…28-7 [CPP20][Visualization] Remove deprecated implicit capture of this in FWTEveViewer
…28-6 [CPP20][Visualisation] Fix deprecated enum bitwise operation in FWCandidateHGCalLegoProxyBuilder
Correction to cell shapes for partial wafers in v18 version of HGCal
Improve behavior after exception in begin/end run transitions
…mssw Bin L1 track quality MVA variable
Integration of sexaquark simulation code (for EXO-24-003)
Add D110 Default Input Dataset
…multiboard_cmsswmaster [L1T Phase-2] Correlator Layer 1 pattern file producer updates for multi-board tests
Adding various MEs to per-LS scope
Move commons.h to DataFormats/HGCalReco to break cyclic dep
[PF] Add fillDescription to RecoParticleFlow producers
either remove or make a bunch of configuration fragments compile
workaround for -O3/UBSAN compiler error in GeneratorInterface/SherpaInterface
…fixes_14_1_X double precision in `StandaloneTrackMonitor` and `TrackTypeMonitor` plots to avoid numerical overflow with high number of bin counts
Phase2-hgx356Y Update the Analyzer code for 2023 HGCal Test Beam codes utilizing 8 inch wafers
moduleAlloc_setupFile.h: ThreadAllocInfo is struct not class
Tracking MC truth: fixes and updates to TrackingTruthDumper
Remove unused lambda captures in test_catch2_WaitingThreadPool.cc
Remove unused constants from EcalChannelStatus_PayloadInspector.cc
…EventInfo `DQMEventInfo`: add the possibility to register the `GlobalTag` name in a `MonitorElement`
Include other in the re-scaled pie measurements
…yInAutocond Move phase2_realistic to the T33 tracker geometry in autoCond
…ionStreamerFiles Fix broken `DQM/Integration` unit tests after streamers layout update
Add new dEdx calibration and estimator
…ateWrapper [JMENano] Add customize functions to recompute Puppi weights and PuppiMET, add new autoNano option
Calo Layer-2 EG conditions for 2024 post-TS
Unpacker and DataFormat for L1 Trigger Scouting BMTF source
…QM_141X Add extended version of SCraw energy plots
…_fixJECInPuId [PileUpJetId] Set jet phi for JEC
…ification Removes duplicate/unneeded entries in serialization XML of test objects.
…Data-O3-workaround workaround for -O3 compilation issues in Geometry/HGCalCommonData
…er_14_1_X Improve plugins in `Alignment/HIPAlignmentAlgorithm` and add unit tests
Co-authored-by: Shamik Ghosh <[email protected]>
tcuisset
force-pushed
the
dnn-supercls-ticlv5
branch
2 times, most recently
from
118bcf8 to
e8b0e18
Compare
tcuisset
force-pushed
the
dnn-supercls-ticlv5
branch
from
e8b0e18 to
188e7a5
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
To test, you need to download the model (attached), rename it to
supercls_v2.pband move it toCMSSW_14_1_X_2024-04-18-2300/external/el8_amd64_gcc12/data/RecoHGCal/TICL/data/tf_models/supercls_v2.pb, replacing "el8_*" by your value of$SCRAM_ARCHsupercls_v2.pb.txt