[tmva][sofie] Fix issue in Keras parser in Redhape operator

With this fix now the Keras parser can parse the convolutional model generated by TMVA_CNN_Classification

Author: lmoneta

bindings/pyroot/pythonizations/python/ROOT/_pythonization/_tmva/_sofie/_parser/_keras/layers/flatten.py

@@ -17,9 +17,9 @@ def MakeKerasFlatten(layer):
     Returns:
     ROperator_Reshape: A SOFIE framework operator representing the flattening operation.
     """
-    
+
     keras_version = get_keras_version()
-    
+
     finput = layer['layerInput']
     foutput = layer['layerOutput']
     attributes = layer['layerAttributes']
@@ -31,6 +31,6 @@ def MakeKerasFlatten(layer):
     fLayerDType = layer['layerDType']
     fNameData = finput[0]
     fNameOutput = foutput[0]
-    fNameShape = flayername + "ReshapeAxes"
+    fNameShape = flayername + "_shape"
     op =  gbl_namespace.TMVA.Experimental.SOFIE.ROperator_Reshape(fOpMode, 0, fNameData, fNameShape, fNameOutput)
     return op

bindings/pyroot/pythonizations/python/ROOT/_pythonization/_tmva/_sofie/_parser/_keras/layers/reshape.py

@@ -15,9 +15,9 @@ def MakeKerasReshape(layer):
     Returns:
     ROperator_Reshape: A SOFIE framework operator representing the reshaping operation.
     """
-    
+
     keras_version = get_keras_version()
-    
+
     finput = layer['layerInput']
     foutput = layer['layerOutput']
     attributes = layer['layerAttributes']
@@ -29,6 +29,6 @@ def MakeKerasReshape(layer):
     fLayerDType = layer['layerDType']
     fNameData = finput[0]
     fNameOutput = foutput[0]
-    fNameShape = flayername + "ReshapeAxes"
+    fNameShape = flayername + "_shape"
     op =  gbl_namespace.TMVA.Experimental.SOFIE.ROperator_Reshape(fOpMode, 0, fNameData, fNameShape, fNameOutput)
     return op

bindings/pyroot/pythonizations/python/ROOT/_pythonization/_tmva/_sofie/_parser/_keras/parser.py

@@ -98,8 +98,9 @@ def add_layer_into_RModel(rmodel, layer_data):
 
     fLayerType = layer_data['layerType']
 
-    # reshape and flatten layers don't have weights, but they are needed inside the list of initialized
-    # tensor list in the Rmodel
+    print('Model: adding layer',fLayerType)
+
+    # reshape and flatten layers don't have weights, but they need constant tensor for the shape
     if fLayerType == "Reshape" or fLayerType == "Flatten":
         Attributes = layer_data['layerAttributes']
         if keras_version < '2.16':
@@ -108,8 +109,8 @@ def add_layer_into_RModel(rmodel, layer_data):
             LayerName = Attributes['name']
 
         if fLayerType == "Reshape":
-            TargetShape = np.asarray(Attributes['target_shape']).astype("int")
-            TargetShape = np.insert(TargetShape,0,0)
+            TargetShape = np.asarray(Attributes['target_shape']).astype("int64")
+            TargetShape = np.insert(TargetShape,0,1)
         else:
             if '_build_input_shape' in Attributes.keys():
                 input_shape = Attributes['_build_input_shape']
@@ -124,8 +125,14 @@ def add_layer_into_RModel(rmodel, layer_data):
 
         # since the AddInitializedTensor method in RModel requires unique pointer, we call a helper function
         # in c++ that does the conversion from a regular pointer to unique one in c++
-        rmodel.AddInitializedTensor['long'](LayerName+"ReshapeAxes", [len(TargetShape)], TargetShape)
-
+        #print('adding initialized tensor..',LayerName, TargetShape)
+        shape_tensor_name = LayerName + "_shape"
+        shape_data = TargetShape.data
+        print(TargetShape, shape_data)
+        print(len(TargetShape))
+        rmodel.AddInitializedTensor['int64_t'](shape_tensor_name, [len(TargetShape)], shape_data)
+
+    print('check other layers...')
     # These layers only have one operator - excluding the recurrent layers, in which the activation function(s)
     # are included in the recurrent operator
     if fLayerType in mapKerasLayer.keys():
@@ -340,7 +347,6 @@ def Parse(filename, batch_size=1):  # If a model does not have a defined batch s
         # and output names
         layer_iter = 0
         is_functional_model = True if keras_model.__class__.__name__ == 'Functional' else False
-        prev_layer_name = "input"
         for layer in keras_model.layers:
             layer_data={}
             layer_data['layerType']=layer.__class__.__name__
@@ -365,14 +371,13 @@ def Parse(filename, batch_size=1):  # If a model does not have a defined batch s
             if keras_version < '2.16' or is_functional_model:
                 layer_data['layerOutput']=[x.name for x in layer.output] if isinstance(layer.output,list) else [layer.output.name]
             else:
-                #sequentiall model in Keras3
+                #sequential model in Keras3
                 output_layer_name = "tensor_output_" + layer.name
                 layer_data['layerOutput']=[x.name for x in layer.output] if isinstance(layer.output,list) else [output_layer_name]
 
             layer_iter += 1
             fLayerType = layer_data['layerType']
             layer_data['layerDType'] = layer.dtype
-            prev_layer_name = layer.name
 
             if len(layer.weights) > 0:
                 if keras_version < '2.16':

tutorials/machine_learning/TMVA_SOFIE_Keras_HiggsModel.py

@@ -92,22 +92,26 @@ def  GenerateCode(modelFile = "model.keras") :
 modelFile = TrainModel(model,x_train, y_train, 'HiggsModel')
 
 ###################################################################
-## Step 2 : Pase model and generate inference code with SOFIE
+## Step 2 : Parse model and generate inference code with SOFIE
 ###################################################################
 
-
 modelName = GenerateCode(modelFile)
 modelHeaderFile = modelName + ".hxx"
 
-#compile the generated code
+###################################################################
+## Step 3 : Compile the generated C++ model code
+###################################################################
+
 ROOT.gInterpreter.Declare('#include "' + modelHeaderFile + '"')
 
-#get the sofie session namespace
+###################################################################
+## Step 4: Evaluate the model
+###################################################################
+
+#get first the SOFIE session namespace
 sofie = getattr(ROOT, 'TMVA_SOFIE_' + modelName)
 session = sofie.Session()
 
-#Evaluate the model
-
 x = np.random.normal(0,1,7).astype(np.float32)
 y = session.infer(x)
 ykeras = model(x.reshape(1,7)).numpy()