TMVA_SOFIE_Models.py File Reference

Detailed Description

Example of inference with SOFIE using a set of models trained with Keras.

This tutorial shows how to store several models in a single header file and the weights in a ROOT binary file. The models are then evaluated using the RDataFrame First, generate the input model by running TMVA_Higgs_Classification.C.

This tutorial parses the input model and runs the inference using ROOT's JITing capability.

 
import os
 
import numpy as np
import ROOT
from sklearn.model_selection import train_test_split
from tensorflow.keras.layers import Dense
from tensorflow.keras.models import Sequential
from tensorflow.keras.optimizers import Adam
 
## generate and train Keras models with different architectures
 
 
def CreateModel(nlayers = 4, nunits = 64):
   model = Sequential()
   model.add(Dense(nunits, activation='relu',input_dim=7))
   for i in range(1,nlayers) :
      model.add(Dense(nunits, activation='relu'))
 
   model.add(Dense(1, activation='sigmoid'))
   model.compile(loss = 'binary_crossentropy', optimizer = Adam(learning_rate = 0.001), weighted_metrics = ['accuracy'])
   model.summary()
   return model
 
def PrepareData() :
   #get the input data
   inputFile = str(ROOT.gROOT.GetTutorialDir()) + "/machine_learning/data/Higgs_data.root"
 
   df1 = ROOT.RDataFrame("sig_tree", inputFile)
   sigData = df1.AsNumpy(columns=['m_jj', 'm_jjj', 'm_lv', 'm_jlv', 'm_bb', 'm_wbb', 'm_wwbb'])
   #print(sigData)
 
   # stack all the 7 numpy array in a single array (nevents x nvars)
   xsig = np.column_stack(list(sigData.values()))
   data_sig_size = xsig.shape[0]
   print("size of data", data_sig_size)
 
   # make SOFIE inference on background data
   df2 = ROOT.RDataFrame("bkg_tree", inputFile)
   bkgData = df2.AsNumpy(columns=['m_jj', 'm_jjj', 'm_lv', 'm_jlv', 'm_bb', 'm_wbb', 'm_wwbb'])
   xbkg = np.column_stack(list(bkgData.values()))
   data_bkg_size = xbkg.shape[0]
 
   ysig = np.ones(data_sig_size)
   ybkg = np.zeros(data_bkg_size)
   inputs_data = np.concatenate((xsig,xbkg),axis=0)
   inputs_targets = np.concatenate((ysig,ybkg),axis=0)
 
   #split data in training and test data
 
   x_train, x_test, y_train, y_test = train_test_split(
        inputs_data, inputs_targets, test_size=0.50, random_state=1234)
 
   return x_train, y_train, x_test, y_test
 
def TrainModel(model, x, y, name) :
   model.fit(x,y,epochs=5,batch_size=50)
   modelFile = name + '.keras'
   model.save(modelFile)
   return modelFile
 
### run the models
 
x_train, y_train, x_test, y_test = PrepareData()
 
## create models and train them
 
model1 = TrainModel(CreateModel(4,64),x_train, y_train, 'Higgs_Model_4L_50')
model2 = TrainModel(CreateModel(4,64),x_train, y_train, 'Higgs_Model_4L_200')
model3 = TrainModel(CreateModel(4,64),x_train, y_train, 'Higgs_Model_2L_500')
 
#evaluate with SOFIE the 3 trained models
 
 
def GenerateModelCode(modelFile, generatedHeaderFile):
   model = ROOT.TMVA.Experimental.SOFIE.PyKeras.Parse(modelFile)
 
   print("Generating inference code for the Keras model from ",modelFile,"in the header ", generatedHeaderFile)
   #Generating inference code using a ROOT binary file
   model.Generate(ROOT.TMVA.Experimental.SOFIE.Options.kRootBinaryWeightFile)
   # add option to append to the same file the generated headers (pass True for append flag)
   model.OutputGenerated(generatedHeaderFile, True)
   #model.PrintGenerated()
   return generatedHeaderFile
 
 
generatedHeaderFile = "Higgs_Model.hxx"
#need to remove existing header file since we are appending on same one
if (os.path.exists(generatedHeaderFile)):
   print("removing existing file", generatedHeaderFile)
   os.remove(generatedHeaderFile)
 
weightFile = "Higgs_Model.root"
if (os.path.exists(weightFile)):
   print("removing existing file", weightFile)
   os.remove(weightFile)
 
GenerateModelCode(model1, generatedHeaderFile)
GenerateModelCode(model2, generatedHeaderFile)
GenerateModelCode(model3, generatedHeaderFile)
 
#compile the generated code
 
ROOT.gInterpreter.Declare('#include "' + generatedHeaderFile + '"')
 
 
#run the inference on the test data
session1 = ROOT.TMVA_SOFIE_Higgs_Model_4L_50.Session("Higgs_Model.root")
session2 = ROOT.TMVA_SOFIE_Higgs_Model_4L_200.Session("Higgs_Model.root")
session3 = ROOT.TMVA_SOFIE_Higgs_Model_2L_500.Session("Higgs_Model.root")
 
hs1 = ROOT.TH1D("hs1","Signal result 4L 50",100,0,1)
hs2 = ROOT.TH1D("hs2","Signal result 4L 200",100,0,1)
hs3 = ROOT.TH1D("hs3","Signal result 2L 500",100,0,1)
 
hb1 = ROOT.TH1D("hb1","Background result 4L 50",100,0,1)
hb2 = ROOT.TH1D("hb2","Background result 4L 200",100,0,1)
hb3 = ROOT.TH1D("hb3","Background result 2L 500",100,0,1)
 
def EvalModel(session, x) :
   result = session.infer(x)
   return result[0]
 
for i in range(0,x_test.shape[0]):
   result1 = EvalModel(session1, x_test[i,:])
   result2 = EvalModel(session2, x_test[i,:])
   result3 = EvalModel(session3, x_test[i,:])
   if (y_test[i] == 1) :
      hs1.Fill(result1)
      hs2.Fill(result2)
      hs3.Fill(result3)
   else:
      hb1.Fill(result1)
      hb2.Fill(result2)
      hb3.Fill(result3)
 
def PlotHistos(hs,hb):
   hs.SetLineColor("kRed")
   hb.SetLineColor("kBlue")
   hs.Draw()
   hb.Draw("same")
 
c1 = ROOT.TCanvas()
c1.Divide(1,3)
c1.cd(1)
PlotHistos(hs1,hb1)
c1.cd(2)
PlotHistos(hs2,hb2)
c1.cd(3)
PlotHistos(hs3,hb3)
c1.Draw()
 
## draw also ROC curves
 
def GetContent(h) :
   n = h.GetNbinsX()
   x = ROOT.std.vector['float'](n)
   w = ROOT.std.vector['float'](n)
   for  i in range(0,n):
      x[i] = h.GetBinCenter(i+1)
      w[i] = h.GetBinContent(i+1)
   return x,w
 
def MakeROCCurve(hs, hb) :
   xs,ws = GetContent(hs)
   xb,wb = GetContent(hb)
   roc = ROOT.TMVA.ROCCurve(xs,xb,ws,wb)
   print("ROC integral for ",hs.GetName(), roc.GetROCIntegral())
   curve = roc.GetROCCurve()
   curve.SetName(hs.GetName())
   return roc,curve
 
c2 = ROOT.TCanvas()
 
r1,curve1 = MakeROCCurve(hs1,hb1)
curve1.SetLineColor("kRed")
curve1.Draw("AC")
 
r2,curve2 = MakeROCCurve(hs2,hb2)
curve2.SetLineColor("kBlue")
curve2.Draw("C")
 
r3,curve3 = MakeROCCurve(hs3,hb3)
curve3.SetLineColor("kGreen")
curve3.Draw("C")
 
c2.Draw()

size of data 10000
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ dense (Dense)                   │ (None, 64)             │           512 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense_1 (Dense)                 │ (None, 64)             │         4,160 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense_2 (Dense)                 │ (None, 64)             │         4,160 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense_3 (Dense)                 │ (None, 64)             │         4,160 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense_4 (Dense)                 │ (None, 1)              │            65 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 13,057 (51.00 KB)
 Trainable params: 13,057 (51.00 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/5
 
␛[1m  1/200␛[0m ␛[37m━━━━━━━━━━━━━━━━━━━━␛[0m ␛[1m2:08␛[0m 647ms/step - accuracy: 0.5600 - loss: 0.6917␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m 59/200␛[0m ␛[32m━━━━━␛[0m␛[37m━━━━━━━━━━━━━━━␛[0m ␛[1m0s␛[0m 874us/step - accuracy: 0.5397 - loss: 0.6876  ␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m124/200␛[0m ␛[32m━━━━━━━━━━━━␛[0m␛[37m━━━━━━━━␛[0m ␛[1m0s␛[0m 825us/step - accuracy: 0.5537 - loss: 0.6815␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m193/200␛[0m ␛[32m━━━━━━━━━━━━━━━━━━━␛[0m␛[37m━␛[0m ␛[1m0s␛[0m 789us/step - accuracy: 0.5648 - loss: 0.6768␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m200/200␛[0m ␛[32m━━━━━━━━━━━━━━━━━━━━␛[0m␛[37m␛[0m ␛[1m1s␛[0m 839us/step - accuracy: 0.5896 - loss: 0.6653
Epoch 2/5
 
␛[1m  1/200␛[0m ␛[37m━━━━━━━━━━━━━━━━━━━━␛[0m ␛[1m2s␛[0m 11ms/step - accuracy: 0.6000 - loss: 0.6628␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m 69/200␛[0m ␛[32m━━━━━━␛[0m␛[37m━━━━━━━━━━━━━━␛[0m ␛[1m0s␛[0m 735us/step - accuracy: 0.6236 - loss: 0.6472␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m139/200␛[0m ␛[32m━━━━━━━━━━━━━␛[0m␛[37m━━━━━━━␛[0m ␛[1m0s␛[0m 727us/step - accuracy: 0.6316 - loss: 0.6436␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m200/200␛[0m ␛[32m━━━━━━━━━━━━━━━━━━━━␛[0m␛[37m␛[0m ␛[1m0s␛[0m 774us/step - accuracy: 0.6405 - loss: 0.6395
Epoch 3/5
 
␛[1m  1/200␛[0m ␛[37m━━━━━━━━━━━━━━━━━━━━␛[0m ␛[1m2s␛[0m 11ms/step - accuracy: 0.5000 - loss: 0.6741␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m 65/200␛[0m ␛[32m━━━━━━␛[0m␛[37m━━━━━━━━━━━━━━␛[0m ␛[1m0s␛[0m 784us/step - accuracy: 0.6266 - loss: 0.6346␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m131/200␛[0m ␛[32m━━━━━━━━━━━━━␛[0m␛[37m━━━━━━━␛[0m ␛[1m0s␛[0m 774us/step - accuracy: 0.6349 - loss: 0.6327␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m200/200␛[0m ␛[32m━━━━━━━━━━━━━━━━━━━━␛[0m␛[37m␛[0m ␛[1m0s␛[0m 758us/step - accuracy: 0.6392 - loss: 0.6312␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m200/200␛[0m ␛[32m━━━━━━━━━━━━━━━━━━━━␛[0m␛[37m␛[0m ␛[1m0s␛[0m 805us/step - accuracy: 0.6458 - loss: 0.6290
Epoch 4/5
 
␛[1m  1/200␛[0m ␛[37m━━━━━━━━━━━━━━━━━━━━␛[0m ␛[1m2s␛[0m 11ms/step - accuracy: 0.5400 - loss: 0.6575␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m 69/200␛[0m ␛[32m━━━━━━␛[0m␛[37m━━━━━━━━━━━━━━␛[0m ␛[1m0s␛[0m 738us/step - accuracy: 0.6352 - loss: 0.6344␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m140/200␛[0m ␛[32m━━━━━━━━━━━━━━␛[0m␛[37m━━━━━━␛[0m ␛[1m0s␛[0m 723us/step - accuracy: 0.6472 - loss: 0.6275␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m200/200␛[0m ␛[32m━━━━━━━━━━━━━━━━━━━━␛[0m␛[37m␛[0m ␛[1m0s␛[0m 770us/step - accuracy: 0.6550 - loss: 0.6212
Epoch 5/5
 
␛[1m  1/200␛[0m ␛[37m━━━━━━━━━━━━━━━━━━━━␛[0m ␛[1m2s␛[0m 11ms/step - accuracy: 0.7600 - loss: 0.5710␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m 70/200␛[0m ␛[32m━━━━━━━␛[0m␛[37m━━━━━━━━━━━━━␛[0m ␛[1m0s␛[0m 735us/step - accuracy: 0.6705 - loss: 0.6123␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m138/200␛[0m ␛[32m━━━━━━━━━━━━━␛[0m␛[37m━━━━━━━␛[0m ␛[1m0s␛[0m 740us/step - accuracy: 0.6644 - loss: 0.6159␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m200/200␛[0m ␛[32m━━━━━━━━━━━━━━━━━━━━␛[0m␛[37m␛[0m ␛[1m0s␛[0m 793us/step - accuracy: 0.6606 - loss: 0.6166
Model: "sequential_1"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ dense_5 (Dense)                 │ (None, 64)             │           512 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense_6 (Dense)                 │ (None, 64)             │         4,160 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense_7 (Dense)                 │ (None, 64)             │         4,160 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense_8 (Dense)                 │ (None, 64)             │         4,160 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense_9 (Dense)                 │ (None, 1)              │            65 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 13,057 (51.00 KB)
 Trainable params: 13,057 (51.00 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/5
 
␛[1m  1/200␛[0m ␛[37m━━━━━━━━━━━━━━━━━━━━␛[0m ␛[1m1:59␛[0m 600ms/step - accuracy: 0.4400 - loss: 0.7112␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m 59/200␛[0m ␛[32m━━━━━␛[0m␛[37m━━━━━━━━━━━━━━━␛[0m ␛[1m0s␛[0m 867us/step - accuracy: 0.5114 - loss: 0.6911  ␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m122/200␛[0m ␛[32m━━━━━━━━━━━━␛[0m␛[37m━━━━━━━━␛[0m ␛[1m0s␛[0m 834us/step - accuracy: 0.5394 - loss: 0.6830␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m188/200␛[0m ␛[32m━━━━━━━━━━━━━━━━━━␛[0m␛[37m━━␛[0m ␛[1m0s␛[0m 810us/step - accuracy: 0.5542 - loss: 0.6782␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m200/200␛[0m ␛[32m━━━━━━━━━━━━━━━━━━━━␛[0m␛[37m␛[0m ␛[1m1s␛[0m 859us/step - accuracy: 0.5898 - loss: 0.6649
Epoch 2/5
 
␛[1m  1/200␛[0m ␛[37m━━━━━━━━━━━━━━━━━━━━␛[0m ␛[1m2s␛[0m 12ms/step - accuracy: 0.6400 - loss: 0.6611␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m 68/200␛[0m ␛[32m━━━━━━␛[0m␛[37m━━━━━━━━━━━━━━␛[0m ␛[1m0s␛[0m 753us/step - accuracy: 0.6024 - loss: 0.6567␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m134/200␛[0m ␛[32m━━━━━━━━━━━━━␛[0m␛[37m━━━━━━━␛[0m ␛[1m0s␛[0m 756us/step - accuracy: 0.6079 - loss: 0.6537␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m200/200␛[0m ␛[32m━━━━━━━━━━━━━━━━━━━━␛[0m␛[37m␛[0m ␛[1m0s␛[0m 805us/step - accuracy: 0.6191 - loss: 0.6463
Epoch 3/5
 
␛[1m  1/200␛[0m ␛[37m━━━━━━━━━━━━━━━━━━━━␛[0m ␛[1m2s␛[0m 11ms/step - accuracy: 0.7000 - loss: 0.5799␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m 62/200␛[0m ␛[32m━━━━━━␛[0m␛[37m━━━━━━━━━━━━━━␛[0m ␛[1m0s␛[0m 828us/step - accuracy: 0.6424 - loss: 0.6319␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m126/200␛[0m ␛[32m━━━━━━━━━━━━␛[0m␛[37m━━━━━━━━␛[0m ␛[1m0s␛[0m 808us/step - accuracy: 0.6402 - loss: 0.6337␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m191/200␛[0m ␛[32m━━━━━━━━━━━━━━━━━━━␛[0m␛[37m━␛[0m ␛[1m0s␛[0m 796us/step - accuracy: 0.6400 - loss: 0.6336␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m200/200␛[0m ␛[32m━━━━━━━━━━━━━━━━━━━━␛[0m␛[37m␛[0m ␛[1m0s␛[0m 843us/step - accuracy: 0.6422 - loss: 0.6315
Epoch 4/5
 
␛[1m  1/200␛[0m ␛[37m━━━━━━━━━━━━━━━━━━━━␛[0m ␛[1m2s␛[0m 12ms/step - accuracy: 0.5600 - loss: 0.6972␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m 63/200␛[0m ␛[32m━━━━━━␛[0m␛[37m━━━━━━━━━━━━━━␛[0m ␛[1m0s␛[0m 814us/step - accuracy: 0.6388 - loss: 0.6340␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m131/200␛[0m ␛[32m━━━━━━━━━━━━━␛[0m␛[37m━━━━━━━␛[0m ␛[1m0s␛[0m 773us/step - accuracy: 0.6404 - loss: 0.6319␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m200/200␛[0m ␛[32m━━━━━━━━━━━━━━━━━━━━␛[0m␛[37m␛[0m ␛[1m0s␛[0m 757us/step - accuracy: 0.6433 - loss: 0.6296␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m200/200␛[0m ␛[32m━━━━━━━━━━━━━━━━━━━━␛[0m␛[37m␛[0m ␛[1m0s␛[0m 807us/step - accuracy: 0.6496 - loss: 0.6246
Epoch 5/5
 
␛[1m  1/200␛[0m ␛[37m━━━━━━━━━━━━━━━━━━━━␛[0m ␛[1m2s␛[0m 11ms/step - accuracy: 0.6600 - loss: 0.6131␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m 70/200␛[0m ␛[32m━━━━━━━␛[0m␛[37m━━━━━━━━━━━━━␛[0m ␛[1m0s␛[0m 733us/step - accuracy: 0.6339 - loss: 0.6323␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m140/200␛[0m ␛[32m━━━━━━━━━━━━━━␛[0m␛[37m━━━━━━␛[0m ␛[1m0s␛[0m 727us/step - accuracy: 0.6401 - loss: 0.6277␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m200/200␛[0m ␛[32m━━━━━━━━━━━━━━━━━━━━␛[0m␛[37m␛[0m ␛[1m0s␛[0m 775us/step - accuracy: 0.6520 - loss: 0.6208
Model: "sequential_2"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ dense_10 (Dense)                │ (None, 64)             │           512 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense_11 (Dense)                │ (None, 64)             │         4,160 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense_12 (Dense)                │ (None, 64)             │         4,160 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense_13 (Dense)                │ (None, 64)             │         4,160 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense_14 (Dense)                │ (None, 1)              │            65 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 13,057 (51.00 KB)
 Trainable params: 13,057 (51.00 KB)
 Non-trainable params: 0 (0.00 B)
Epoch 1/5
 
␛[1m  1/200␛[0m ␛[37m━━━━━━━━━━━━━━━━━━━━␛[0m ␛[1m2:29␛[0m 749ms/step - accuracy: 0.4600 - loss: 0.6980␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m 63/200␛[0m ␛[32m━━━━━━␛[0m␛[37m━━━━━━━━━━━━━━␛[0m ␛[1m0s␛[0m 818us/step - accuracy: 0.5278 - loss: 0.6888  ␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m129/200␛[0m ␛[32m━━━━━━━━━━━━␛[0m␛[37m━━━━━━━━␛[0m ␛[1m0s␛[0m 792us/step - accuracy: 0.5478 - loss: 0.6830␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m195/200␛[0m ␛[32m━━━━━━━━━━━━━━━━━━━␛[0m␛[37m━␛[0m ␛[1m0s␛[0m 781us/step - accuracy: 0.5580 - loss: 0.6785␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m200/200␛[0m ␛[32m━━━━━━━━━━━━━━━━━━━━␛[0m␛[37m␛[0m ␛[1m1s␛[0m 829us/step - accuracy: 0.5831 - loss: 0.6667
Epoch 2/5
 
␛[1m  1/200␛[0m ␛[37m━━━━━━━━━━━━━━━━━━━━␛[0m ␛[1m2s␛[0m 11ms/step - accuracy: 0.6400 - loss: 0.6575␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m 69/200␛[0m ␛[32m━━━━━━␛[0m␛[37m━━━━━━━━━━━━━━␛[0m ␛[1m0s␛[0m 742us/step - accuracy: 0.6348 - loss: 0.6497␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m136/200␛[0m ␛[32m━━━━━━━━━━━━━␛[0m␛[37m━━━━━━━␛[0m ␛[1m0s␛[0m 745us/step - accuracy: 0.6321 - loss: 0.6480␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m200/200␛[0m ␛[32m━━━━━━━━━━━━━━━━━━━━␛[0m␛[37m␛[0m ␛[1m0s␛[0m 793us/step - accuracy: 0.6314 - loss: 0.6404
Epoch 3/5
 
␛[1m  1/200␛[0m ␛[37m━━━━━━━━━━━━━━━━━━━━␛[0m ␛[1m2s␛[0m 11ms/step - accuracy: 0.7200 - loss: 0.5423␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m 68/200␛[0m ␛[32m━━━━━━␛[0m␛[37m━━━━━━━━━━━━━━␛[0m ␛[1m0s␛[0m 757us/step - accuracy: 0.6590 - loss: 0.6108␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m135/200␛[0m ␛[32m━━━━━━━━━━━━━␛[0m␛[37m━━━━━━━␛[0m ␛[1m0s␛[0m 756us/step - accuracy: 0.6526 - loss: 0.6170␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m200/200␛[0m ␛[32m━━━━━━━━━━━━━━━━━━━━␛[0m␛[37m␛[0m ␛[1m0s␛[0m 798us/step - accuracy: 0.6439 - loss: 0.6283
Epoch 4/5
 
␛[1m  1/200␛[0m ␛[37m━━━━━━━━━━━━━━━━━━━━␛[0m ␛[1m2s␛[0m 11ms/step - accuracy: 0.7200 - loss: 0.5474␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m 68/200␛[0m ␛[32m━━━━━━␛[0m␛[37m━━━━━━━━━━━━━━␛[0m ␛[1m0s␛[0m 753us/step - accuracy: 0.6667 - loss: 0.6076␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m136/200␛[0m ␛[32m━━━━━━━━━━━━━␛[0m␛[37m━━━━━━━␛[0m ␛[1m0s␛[0m 748us/step - accuracy: 0.6611 - loss: 0.6141␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m200/200␛[0m ␛[32m━━━━━━━━━━━━━━━━━━━━␛[0m␛[37m␛[0m ␛[1m0s␛[0m 797us/step - accuracy: 0.6562 - loss: 0.6210
Epoch 5/5
 
␛[1m  1/200␛[0m ␛[37m━━━━━━━━━━━━━━━━━━━━␛[0m ␛[1m2s␛[0m 11ms/step - accuracy: 0.6200 - loss: 0.6030␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m 70/200␛[0m ␛[32m━━━━━━━␛[0m␛[37m━━━━━━━━━━━━━␛[0m ␛[1m0s␛[0m 734us/step - accuracy: 0.6445 - loss: 0.6332␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m140/200␛[0m ␛[32m━━━━━━━━━━━━━━␛[0m␛[37m━━━━━━␛[0m ␛[1m0s␛[0m 724us/step - accuracy: 0.6504 - loss: 0.6263␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
␛[1m200/200␛[0m ␛[32m━━━━━━━━━━━━━━━━━━━━␛[0m␛[37m␛[0m ␛[1m0s␛[0m 766us/step - accuracy: 0.6589 - loss: 0.6157
PyKeras: parsing model  Higgs_Model_4L_50.keras
Generating inference code for the Keras model from  Higgs_Model_4L_50.keras in the header  Higgs_Model.hxx
PyKeras: parsing model  Higgs_Model_4L_200.keras
Generating inference code for the Keras model from  Higgs_Model_4L_200.keras in the header  Higgs_Model.hxx
PyKeras: parsing model  Higgs_Model_2L_500.keras
Generating inference code for the Keras model from  Higgs_Model_2L_500.keras in the header  Higgs_Model.hxx
ROC integral for  hs1 0.7305957914840208
ROC integral for  hs2 0.7256835974376156
ROC integral for  hs3 0.7378036775233272

Author

Lorenzo Moneta

Definition in file TMVA_SOFIE_Models.py.