[tmva][sofie] Migrate SOFIE tutorials from Keras to PyTorch and ONNX

PyTorch has become the dominant training framework in the particle
physics community, and it comes with better ONNX support than Keras.
Since ONNX is the primary input format for SOFIE, the SOFIE tutorials
based on the Higgs dataset are migrated from Keras to PyTorch with
ONNX export.

Replace TMVA_SOFIE_Keras_HiggsModel.py with
TMVA_SOFIE_PyTorch_HiggsModel.py, which trains the same architecture
(7 -> 64 -> 64 -> 1 with sigmoid output, binary cross-entropy, Adam,
5 epochs) with PyTorch, exports it to HiggsModel.onnx and generates
the inference code with RModelParser_ONNX. The generated code is
validated against the PyTorch predictions, and the trained model was
checked to be roughly equivalent to the Keras one (test AUC 0.712 vs.
0.720 on an identical data split).

Adapt the downstream tutorials that consume the trained Higgs model
(TMVA_SOFIE_RDataFrame.C/.py, TMVA_SOFIE_RDataFrame_JIT.C,
TMVA_SOFIE_RSofieReader.C, TMVA_SOFIE_Inference.py) to use
HiggsModel.onnx instead of HiggsModel.keras. Also migrate
TMVA_SOFIE_Models.py, which demonstrates storing several models in a
single generated header with weights in one ROOT binary file: this
feature is independent of the training framework.

The PyTorch ONNX export and ROOT's SOFIE parser are usually linked
against different protobuf versions, so the training and export run
in a separate Python process, following the pattern established in
TMVA_SOFIE_ONNX.py.

The CMake test dependencies are updated accordingly, and the migrated
tutorials are now gated on tmva-sofie plus the torch and onnx Python
modules instead of keras.

🤖 Done with the help of AI.

Author: guitargeek

tmva/sofie/README.md

@@ -176,9 +176,9 @@ parser.CheckModel("example_model.ONNX");
 - **Tutorials**
     - [TMVA_SOFIE_Inference](https://github.com/root-project/root/blob/master/tutorials/machine_learning/TMVA_SOFIE_Inference.py)
     - [TMVA_SOFIE_Keras](https://github.com/root-project/root/blob/master/tutorials/machine_learning/TMVA_SOFIE_Keras.C)
-    - [TMVA_SOFIE_Keras_HiggsModel](https://github.com/root-project/root/blob/master/tutorials/machine_learning/TMVA_SOFIE_Keras_HiggsModel.C)
     - [TMVA_SOFIE_ONNX](https://github.com/root-project/root/blob/master/tutorials/machine_learning/TMVA_SOFIE_ONNX.C)
     - [TMVA_SOFIE_PyTorch](https://github.com/root-project/root/blob/master/tutorials/machine_learning/TMVA_SOFIE_PyTorch.py)
+    - [TMVA_SOFIE_PyTorch_HiggsModel](https://github.com/root-project/root/blob/master/tutorials/machine_learning/TMVA_SOFIE_PyTorch_HiggsModel.py)
     - [TMVA_SOFIE_RDataFrame](https://github.com/root-project/root/blob/master/tutorials/machine_learning/TMVA_SOFIE_RDataFrame.C)
     - [TMVA_SOFIE_RDataFrame](https://github.com/root-project/root/blob/master/tutorials/machine_learning/TMVA_SOFIE_RDataFrame.py)
     - [TMVA_SOFIE_RDataFrame_JIT](https://github.com/root-project/root/blob/master/tutorials/machine_learning/TMVA_SOFIE_RDataFrame_JIT.C)

tutorials/CMakeLists.txt

@@ -370,20 +370,20 @@ else()
   # These SOFIE tutorials take models trained via PyMVA-PyKeras as input
   if (NOT tmva-sofie OR NOT ROOT_KERAS_FOUND)
     list(APPEND tmva_veto machine_learning/TMVA_SOFIE_Keras.py)
-    list(APPEND tmva_veto machine_learning/TMVA_SOFIE_Models.py)
-    list(APPEND tmva_veto machine_learning/TMVA_SOFIE_Keras_HiggsModel.py)
-    list(APPEND tmva_veto machine_learning/TMVA_SOFIE_RDataFrame.C)
-    list(APPEND tmva_veto machine_learning/TMVA_SOFIE_RDataFrame_JIT.C)
-    list(APPEND tmva_veto machine_learning/TMVA_SOFIE_RSofieReader.C)
-    list(APPEND tmva_veto machine_learning/TMVA_SOFIE_RDataFrame.py)
-    list(APPEND tmva_veto machine_learning/TMVA_SOFIE_RSofieReader.C)
-    list(APPEND tmva_veto machine_learning/TMVA_SOFIE_Inference.py)
   endif()
   if (NOT tmva-sofie OR NOT ROOT_TORCH_FOUND)
     list(APPEND tmva_veto machine_learning/TMVA_SOFIE_PyTorch.py)
   endif()
+  # These SOFIE tutorials take the ONNX HiggsModel trained with PyTorch as input
   if (NOT tmva-sofie OR NOT ROOT_TORCH_FOUND OR NOT ROOT_ONNX_FOUND)
     list(APPEND tmva_veto machine_learning/TMVA_SOFIE_ONNX.py)
+    list(APPEND tmva_veto machine_learning/TMVA_SOFIE_Models.py)
+    list(APPEND tmva_veto machine_learning/TMVA_SOFIE_PyTorch_HiggsModel.py)
+    list(APPEND tmva_veto machine_learning/TMVA_SOFIE_RDataFrame.C)
+    list(APPEND tmva_veto machine_learning/TMVA_SOFIE_RDataFrame_JIT.C)
+    list(APPEND tmva_veto machine_learning/TMVA_SOFIE_RSofieReader.C)
+    list(APPEND tmva_veto machine_learning/TMVA_SOFIE_RDataFrame.py)
+    list(APPEND tmva_veto machine_learning/TMVA_SOFIE_Inference.py)
   endif()
   #veto this tutorial since it is added directly
   list(APPEND tmva_veto machine_learning/TMVA_SOFIE_GNN_Parser.py)
@@ -655,7 +655,7 @@ set (machine_learning-tmva004_RStandardScaler-depends tutorial-machine_learning-
 set (machine_learning-pytorch-ApplicationClassificationPyTorch-depends tutorial-machine_learning-pytorch-ClassificationPyTorch-py)
 set (machine_learning-pytorch-RegressionPyTorch-depends tutorial-machine_learning-pytorch-ApplicationClassificationPyTorch-py)
 set (machine_learning-pytorch-ApplicationRegressionPyTorch-depends tutorial-machine_learning-pytorch-RegressionPyTorch-py)
-set (machine_learning-TMVA_SOFIE_RDataFrame-depends tutorial-machine_learning-TMVA_SOFIE_Keras_HiggsModel-py)
+set (machine_learning-TMVA_SOFIE_RDataFrame-depends tutorial-machine_learning-TMVA_SOFIE_PyTorch_HiggsModel-py)
 set (machine_learning-TMVA_SOFIE_RDataFrame_JIT-depends tutorial-machine_learning-TMVA_SOFIE_RDataFrame)
 set (machine_learning-TMVA_SOFIE_RSofieReader-depends tutorial-machine_learning-TMVA_SOFIE_RDataFrame_JIT)
 set (machine_learning-TMVA_SOFIE_Inference-depends tutorial-machine_learning-TMVA_SOFIE_RSofieReader)
@@ -848,8 +848,8 @@ if(pyroot)
     list(APPEND pyveto ${tmva_veto_py})
   endif()
 
-  if (ROOT_KERAS_FOUND)
-    set (machine_learning-TMVA_SOFIE_RDataFrame-py-depends tutorial-machine_learning-TMVA_SOFIE_Keras_HiggsModel)
+  if (ROOT_TORCH_FOUND AND ROOT_ONNX_FOUND)
+    set (machine_learning-TMVA_SOFIE_RDataFrame-py-depends tutorial-machine_learning-TMVA_SOFIE_PyTorch_HiggsModel)
   endif()
 
   if(NOT tmva-pymva)
@@ -947,17 +947,16 @@ if(pyroot)
       roofit/roofit/rf409_NumPyPandasToRooFit.py)
 
   file(GLOB requires_keras   RELATIVE ${CMAKE_CURRENT_SOURCE_DIR}
-      machine_learning/TMVA_SOFIE_Inference.py
-      machine_learning/TMVA_SOFIE_Models.py
-      machine_learning/TMVA_SOFIE_RDataFrame.py
       machine_learning/keras/*.py
   )
   file(GLOB requires_torch   RELATIVE ${CMAKE_CURRENT_SOURCE_DIR}
       machine_learning/pytorch/*.py
       machine_learning/ml_dataloader_PyTorch.py
       machine_learning/ml_dataloader_resampling.py
       machine_learning/ml_dataloader_Higgs_Classification.py
+      machine_learning/TMVA_SOFIE_Models.py
       machine_learning/TMVA_SOFIE_PyTorch.py
+      machine_learning/TMVA_SOFIE_PyTorch_HiggsModel.py
   )
   file(GLOB requires_xgboost RELATIVE ${CMAKE_CURRENT_SOURCE_DIR}
       machine_learning/tmva101_Training.py
@@ -966,7 +965,6 @@ if(pyroot)
       roofit/roofit/rf618_mixture_models.py
   )
   file(GLOB requires_sklearn RELATIVE ${CMAKE_CURRENT_SOURCE_DIR}
-      machine_learning/TMVA_SOFIE_Models.py
       machine_learning/tmva101_Training.py # uses the xgboost sklearn plugin
       machine_learning/tmva102_Testing.py # requires tmva101_Training.py
       machine_learning/ml_dataloader_XGBoost.py

tutorials/machine_learning/TMVA_SOFIE_Inference.py

@@ -1,10 +1,10 @@
 ### \file
 ### \ingroup tutorial_ml
 ### \notebook -nodraw
-### This macro provides an example of using a trained model with Keras
+### This macro provides an example of using a trained model with PyTorch
 ### and make inference using SOFIE directly from Numpy
-### This macro uses as input a Keras model generated with the
-### TMVA_Higgs_Classification.C tutorial
+### This macro uses as input an ONNX model generated with the
+### TMVA_SOFIE_PyTorch_HiggsModel.py tutorial
 ### You need to run that macro before this one.
 ### In this case we are parsing the input file and then run the inference in the same
 ### macro making use of the ROOT JITing capability
@@ -20,32 +20,28 @@
 import ROOT
 
 # check if the input file exists
-modelFile = "HiggsModel.keras"
+modelFile = "HiggsModel.onnx"
 
 if not exists(modelFile):
-    raise FileNotFoundError("You need to run TMVA_Higgs_Classification.C to generate the Keras trained model")
+    raise FileNotFoundError("You need to run TMVA_SOFIE_PyTorch_HiggsModel.py to generate the ONNX trained model")
 
 
-# parse the input Keras model into RModel object
-model = ROOT.TMVA.Experimental.SOFIE.PyKeras.Parse(modelFile)
+# parse the input ONNX model into RModel object
+parser = ROOT.TMVA.Experimental.SOFIE.RModelParser_ONNX()
+model = parser.Parse(modelFile)
 
-generatedHeaderFile = modelFile.replace(".keras",".hxx")
-print("Generating inference code for the Keras model from ",modelFile,"in the header ", generatedHeaderFile)
+generatedHeaderFile = modelFile.replace(".onnx", ".hxx")
+print("Generating inference code for the ONNX model from ", modelFile, "in the header ", generatedHeaderFile)
 #Generating inference code
 model.Generate()
 model.OutputGenerated(generatedHeaderFile)
 model.PrintGenerated()
 
 # now compile using ROOT JIT trained model
-modelName = modelFile.replace(".keras","")
+modelName = modelFile.replace(".onnx", "")
 print("compiling SOFIE model ", modelName)
 ROOT.gInterpreter.Declare('#include "' + generatedHeaderFile + '"')
 
-
-generatedHeaderFile = modelFile.replace(".keras",".hxx")
-print("Generating inference code for the Keras model from ",modelFile,"in the header ", generatedHeaderFile)
-#Generating inference
-
 inputFileName = "Higgs_data.root"
 inputFile = str(ROOT.gROOT.GetTutorialDir()) + "/machine_learning/data/" + inputFileName