update

DeepDoubleX/102X/V02/model_info.txt

@@ -0,0 +1,30 @@
+Trained in 2017, Phase-1, 102X configuration
+
+Sample info:
+	QCD:120M
+	H multimass: 60M (equal parts Hbb/Hcc)
+
+Training info:
+	100 epochs
+	weighted
+
+Training reqs:
+	Keras               		   2.2.4
+	Keras-Applications                 1.0.6
+	Keras-Preprocessing                1.0.5	
+	protobuf                           3.6.1
+	tensorboard                        1.9.0
+	tensorflow-gpu                     1.9.0
+
+Model convert/export reqs:
+	Keras                2.3.1
+	Keras-Applications   1.0.8
+	Keras-Preprocessing  1.1.0
+	keras2onnx           1.6.5
+	onnx                 1.6.0
+	onnxconverter-common 1.6.5
+	onnxmltools          1.6.0
+	tensorboard          1.14.0
+	tensorflow           1.14.0
+
+~ 

ParticleNetAK4/CHS/V00/README.md

@@ -0,0 +1,9 @@
+# ParticleNetAK4-CHS-V00
+
+This folder contains the ONNX models for the `ParticleNetAK4` tagger designed for AK4 jet tagging (i.e., b-/c-tagging, q/g-tagging, PU jet ID). The model is trained on AK4CHS jets using `RunIISummer19UL18MiniAOD` the following samples:
+  - `/TTToSemiLeptonic_mtop171p5_TuneCP5_13TeV-powheg-pythia8/RunIISummer19UL18MiniAOD-106X_upgrade2018_realistic_v11_L1v1-v2/MINIAODSIM` (300 files)
+  - `/TTToSemiLeptonic_mtop173p5_TuneCP5_13TeV-powheg-pythia8/RunIISummer19UL18MiniAOD-106X_upgrade2018_realistic_v11_L1v1-v2/MINIAODSIM` (300 files)
+  - `/QCD_Pt_XtoY_TuneCP5_13TeV_pythia8/RunIISummer19UL18MiniAOD-PUForMUOVal_106X_upgrade2018_realistic_v11_L1v1-v3/MINIAODSIM` (min_X=30, maxY=1400, 50 files each)
+  - `/BulkGravitonToHHTo4Q_MX-600to6000_MH-15to250_part*_TuneCP5_13TeV-madgraph_pythia8/RunIISummer19UL18MiniAOD-multigridpack_106X_upgrade2018_realistic_v11_L1v1-v1/MINIAODSIM` (300 files each)
+
+The output classes of the DNN can be found in the `preprocess.json` file.