[tmva][sofie] FIx setting batch size in Keras parsing

Fix for setting t he batch size when parsing a Keras model where the
input batch size is not defined
Add extra optional parameter in the Parse function to specify the batch size

Author: lmoneta

tmva/pymva/inc/TMVA/RModelParser_Keras.h

@@ -45,7 +45,9 @@ namespace PyKeras{
 /// Parser function for translatng Keras .h5 model into a RModel object.
 /// Accepts the file location of a Keras model and returns the
 /// equivalent RModel object.
-RModel Parse(std::string filename);
+/// One can specify as option a batch size that can be used when the input Keras model
+/// has not a defined input batch size : e.g. for input = (input_dim,)
+RModel Parse(std::string filename, int batch_size = -1);
 
 }//PyKeras
 }//SOFIE

tmva/pymva/src/RModelParser_Keras.cxx

@@ -791,12 +791,15 @@ std::unique_ptr<ROperator> MakeKerasIdentity(PyObject* fLayer)
 /// For adding the Output Tensor infos, only the names of the model's output
 /// tensors are extracted and are then passed into `AddOutputTensorNameList()`.
 ///
+/// Provide optionally a batch size that can be used to overwrite the one given by the
+/// model. If a batch size is not given 1 is used if the model does not provide a batch size
+///
 /// Example Usage:
 /// ~~~ {.cpp}
 /// using TMVA::Experimental::SOFIE;
 /// RModel model = PyKeras::Parse("trained_model_dense.h5");
 /// ~~~
-RModel Parse(std::string filename){
+RModel Parse(std::string filename, int batch_size){
 
    char sep = '/';
    #ifdef _WIN32
@@ -966,8 +969,11 @@ RModel Parse(std::string filename){
          // Getting the shape vector from the Tuple object
          std::vector<size_t>fInputShape = GetDataFromTuple(fPInputShapes);
          if (static_cast<int>(fInputShape[0]) <= 0){
-            fInputShape[0] = 1;
-            std::cout << "Model has not a defined batch size, assume is 1 - input shape : "
+            fInputShape[0] = std::max(batch_size,1);
+            std::cout << "Model has not a defined batch size ";
+            if (batch_size <=0) std::cout << " assume is 1 ";
+            else std::cout << " use given value of " << batch_size;
+            std::cout << " - input shape for tensor " << fInputName << " : "
                       << TMVA::Experimental::SOFIE::ConvertShapeToString(fInputShape) << std::endl;
          }
          rmodel.AddInputTensorInfo(fInputName, ETensorType::FLOAT, fInputShape);
@@ -995,8 +1001,11 @@ RModel Parse(std::string filename){
 
          std::vector<size_t>fInputShape = GetDataFromTuple(fInputShapeTuple);
          if (static_cast<int>(fInputShape[0]) <= 0){
-            fInputShape[0] = 1;
-            std::cout << "Model has not a defined batch size, assume is 1 - input shape for tensor "
+            fInputShape[0] = std::max(batch_size,1);
+            std::cout << "Model has not a defined batch size ";
+            if (batch_size <=0) std::cout << " assume is 1 ";
+            else std::cout << " use given value of " << batch_size;
+            std::cout << " - input shape for tensor "
                       << fInputName << " : " << TMVA::Experimental::SOFIE::ConvertShapeToString(fInputShape) << std::endl;
          }
          rmodel.AddInputTensorInfo(fInputName, ETensorType::FLOAT, fInputShape);

tmva/pymva/test/TestRModelParserKeras.C

@@ -24,6 +24,7 @@ void GenerateModels() {
 TEST(RModelParser_Keras, SEQUENTIAL)
 {
    constexpr float TOLERANCE = DEFAULT_TOLERANCE;
+   // input is 8 x batch size that is fixed to be 4
    std::vector<float> inputSequential = { 0.12107884, 0.89718615, 0.89123899, 0.32197549,
                              0.17891638, 0.83555135, 0.98680066, 0.14496809,
                              0.07255503, 0.55386989, 0.6628149 , 0.29843291,
@@ -38,7 +39,7 @@ TEST(RModelParser_Keras, SEQUENTIAL)
     if (gSystem->AccessPathName("KerasModelSequential.h5",kFileExists))
         GenerateModels();
 
-    TMVA::Experimental:: RSofieReader r("KerasModelSequential.h5");
+    TMVA::Experimental:: RSofieReader r("KerasModelSequential.h5",{{4,8}});
     std::vector<float> outputSequential = r.Compute(inputSequential);
 
 

tmva/tmva/inc/TMVA/RSofieReader.hxx

@@ -113,7 +113,12 @@ public:
          if (gSystem->Load("libPyMVA") < 0) {
             throw std::runtime_error("RSofieReader: cannot use SOFIE with Keras since libPyMVA is missing");
          }
-         parserCode += "{\nTMVA::Experimental::SOFIE::RModel model = TMVA::Experimental::SOFIE::PyKeras::Parse(\"" + path + "\"); \n";
+         // assume batch size is first entry in first input !
+         std::string batch_size = "-1";
+         if (!inputShapes.empty() && ! inputShapes[0].empty())
+            batch_size = std::to_string(inputShapes[0][0]);
+         parserCode += "{\nTMVA::Experimental::SOFIE::RModel model = TMVA::Experimental::SOFIE::PyKeras::Parse(\"" + path +
+                       "\"," + batch_size + "); \n";
       }
       else if (type == kPt) {
          // use PyTorch direct parser