Logo ROOT  
Reference Guide
 
Loading...
Searching...
No Matches
TMVA::MethodDL Class Reference

Definition at line 89 of file MethodDL.h.

Public Member Functions

 MethodDL (const TString &jobName, const TString &methodTitle, DataSetInfo &theData, const TString &theOption)
 Constructor.
 
 MethodDL (DataSetInfo &theData, const TString &theWeightFile)
 Constructor.
 
virtual ~MethodDL ()
 Virtual Destructor.
 
void AddWeightsXMLTo (void *parent) const
 
const RankingCreateRanking ()
 
TString GetArchitectureString () const
 
size_t GetBatchDepth () const
 
size_t GetBatchHeight () const
 
TString GetBatchLayoutString () const
 
size_t GetBatchSize () const
 
size_t GetBatchWidth () const
 
const DeepNetImpl_tGetDeepNet () const
 
TString GetErrorStrategyString () const
 
size_t GetInputDepth () const
 
size_t GetInputDim () const
 
size_t GetInputHeight () const
 
TString GetInputLayoutString () const
 
std::vector< size_t > GetInputShape () const
 
size_t GetInputWidth () const
 
KeyValueVector_tGetKeyValueSettings ()
 
const KeyValueVector_tGetKeyValueSettings () const
 
TString GetLayoutString () const
 
DNN::ELossFunction GetLossFunction () const
 
virtual const std::vector< Float_t > & GetMulticlassValues ()
 
Double_t GetMvaValue (Double_t *err=nullptr, Double_t *errUpper=nullptr)
 
DNN::EOutputFunction GetOutputFunction () const
 
virtual const std::vector< Float_t > & GetRegressionValues ()
 
std::vector< TTrainingSettings > & GetTrainingSettings ()
 
const std::vector< TTrainingSettings > & GetTrainingSettings () const
 
TString GetTrainingStrategyString () const
 
DNN::EInitialization GetWeightInitialization () const
 
TString GetWeightInitializationString () const
 
Bool_t HasAnalysisType (Types::EAnalysisType type, UInt_t numberClasses, UInt_t numberTargets)
 Check the type of analysis the deep learning network can do.
 
virtual TClassIsA () const
 
KeyValueVector_t ParseKeyValueString (TString parseString, TString blockDelim, TString tokenDelim)
 Function for parsing the training settings, provided as a string in a key-value form.
 
void ReadWeightsFromStream (std::istream &)
 
virtual void ReadWeightsFromStream (std::istream &)=0
 Methods for writing and reading weights.
 
virtual void ReadWeightsFromStream (TFile &)
 Methods for writing and reading weights.
 
void ReadWeightsFromXML (void *wghtnode)
 
void SetArchitectureString (TString architectureString)
 
void SetBatchDepth (size_t batchDepth)
 
void SetBatchHeight (size_t batchHeight)
 
void SetBatchSize (size_t batchSize)
 
void SetBatchWidth (size_t batchWidth)
 
void SetErrorStrategyString (TString errorStrategy)
 
void SetInputDepth (int inputDepth)
 Setters.
 
void SetInputHeight (int inputHeight)
 
void SetInputShape (std::vector< size_t > inputShape)
 
void SetInputWidth (int inputWidth)
 
void SetLayoutString (TString layoutString)
 
void SetOutputFunction (DNN::EOutputFunction outputFunction)
 
void SetTrainingStrategyString (TString trainingStrategyString)
 
void SetWeightInitialization (DNN::EInitialization weightInitialization)
 
void SetWeightInitializationString (TString weightInitializationString)
 
virtual void Streamer (TBuffer &)
 
void StreamerNVirtual (TBuffer &ClassDef_StreamerNVirtual_b)
 
void Train ()
 Methods for training the deep learning network.
 
- Public Member Functions inherited from TMVA::MethodBase
 MethodBase (const TString &jobName, Types::EMVA methodType, const TString &methodTitle, DataSetInfo &dsi, const TString &theOption="")
 standard constructor
 
 MethodBase (Types::EMVA methodType, DataSetInfo &dsi, const TString &weightFile)
 constructor used for Testing + Application of the MVA, only (no training), using given WeightFiles
 
virtual ~MethodBase ()
 destructor
 
void AddOutput (Types::ETreeType type, Types::EAnalysisType analysisType)
 
TDirectoryBaseDir () const
 returns the ROOT directory where info/histograms etc of the corresponding MVA method instance are stored
 
virtual void CheckSetup ()
 check may be overridden by derived class (sometimes, eg, fitters are used which can only be implemented during training phase)
 
DataSetData () const
 
DataSetInfoDataInfo () const
 
virtual void DeclareCompatibilityOptions ()
 options that are used ONLY for the READER to ensure backward compatibility they are hence without any effect (the reader is only reading the training options that HAD been used at the training of the .xml weight file at hand
 
void DisableWriting (Bool_t setter)
 
Bool_t DoMulticlass () const
 
Bool_t DoRegression () const
 
void ExitFromTraining ()
 
Types::EAnalysisType GetAnalysisType () const
 
UInt_t GetCurrentIter ()
 
virtual Double_t GetEfficiency (const TString &, Types::ETreeType, Double_t &err)
 fill background efficiency (resp.
 
const EventGetEvent () const
 
const EventGetEvent (const TMVA::Event *ev) const
 
const EventGetEvent (Long64_t ievt) const
 
const EventGetEvent (Long64_t ievt, Types::ETreeType type) const
 
const std::vector< TMVA::Event * > & GetEventCollection (Types::ETreeType type)
 returns the event collection (i.e.
 
TFileGetFile () const
 
const TStringGetInputLabel (Int_t i) const
 
const char * GetInputTitle (Int_t i) const
 
const TStringGetInputVar (Int_t i) const
 
TMultiGraphGetInteractiveTrainingError ()
 
const TStringGetJobName () const
 
virtual Double_t GetKSTrainingVsTest (Char_t SorB, TString opt="X")
 
virtual Double_t GetMaximumSignificance (Double_t SignalEvents, Double_t BackgroundEvents, Double_t &optimal_significance_value) const
 plot significance, \( \frac{S}{\sqrt{S^2 + B^2}} \), curve for given number of signal and background events; returns cut for maximum significance also returned via reference is the maximum significance
 
UInt_t GetMaxIter ()
 
Double_t GetMean (Int_t ivar) const
 
const TStringGetMethodName () const
 
Types::EMVA GetMethodType () const
 
TString GetMethodTypeName () const
 
virtual TMatrixD GetMulticlassConfusionMatrix (Double_t effB, Types::ETreeType type)
 Construct a confusion matrix for a multiclass classifier.
 
virtual std::vector< Float_tGetMulticlassEfficiency (std::vector< std::vector< Float_t > > &purity)
 
virtual std::vector< Float_tGetMulticlassTrainingEfficiency (std::vector< std::vector< Float_t > > &purity)
 
Double_t GetMvaValue (const TMVA::Event *const ev, Double_t *err=nullptr, Double_t *errUpper=nullptr)
 
const char * GetName () const
 
UInt_t GetNEvents () const
 
UInt_t GetNTargets () const
 
UInt_t GetNvar () const
 
UInt_t GetNVariables () const
 
virtual Double_t GetProba (const Event *ev)
 
virtual Double_t GetProba (Double_t mvaVal, Double_t ap_sig)
 compute likelihood ratio
 
const TString GetProbaName () const
 
virtual Double_t GetRarity (Double_t mvaVal, Types::ESBType reftype=Types::kBackground) const
 compute rarity:
 
virtual void GetRegressionDeviation (UInt_t tgtNum, Types::ETreeType type, Double_t &stddev, Double_t &stddev90Percent) const
 
const std::vector< Float_t > & GetRegressionValues (const TMVA::Event *const ev)
 
Double_t GetRMS (Int_t ivar) const
 
virtual Double_t GetROCIntegral (PDF *pdfS=nullptr, PDF *pdfB=nullptr) const
 calculate the area (integral) under the ROC curve as a overall quality measure of the classification
 
virtual Double_t GetROCIntegral (TH1D *histS, TH1D *histB) const
 calculate the area (integral) under the ROC curve as a overall quality measure of the classification
 
virtual Double_t GetSeparation (PDF *pdfS=nullptr, PDF *pdfB=nullptr) const
 compute "separation" defined as
 
virtual Double_t GetSeparation (TH1 *, TH1 *) const
 compute "separation" defined as
 
Double_t GetSignalReferenceCut () const
 
Double_t GetSignalReferenceCutOrientation () const
 
virtual Double_t GetSignificance () const
 compute significance of mean difference
 
const EventGetTestingEvent (Long64_t ievt) const
 
Double_t GetTestTime () const
 
const TStringGetTestvarName () const
 
virtual Double_t GetTrainingEfficiency (const TString &)
 
const EventGetTrainingEvent (Long64_t ievt) const
 
virtual const std::vector< Float_t > & GetTrainingHistory (const char *)
 
UInt_t GetTrainingROOTVersionCode () const
 
TString GetTrainingROOTVersionString () const
 calculates the ROOT version string from the training version code on the fly
 
UInt_t GetTrainingTMVAVersionCode () const
 
TString GetTrainingTMVAVersionString () const
 calculates the TMVA version string from the training version code on the fly
 
Double_t GetTrainTime () const
 
TransformationHandlerGetTransformationHandler (Bool_t takeReroutedIfAvailable=true)
 
const TransformationHandlerGetTransformationHandler (Bool_t takeReroutedIfAvailable=true) const
 
TString GetWeightFileName () const
 retrieve weight file name
 
Double_t GetXmax (Int_t ivar) const
 
Double_t GetXmin (Int_t ivar) const
 
Bool_t HasMVAPdfs () const
 
void InitIPythonInteractive ()
 
Bool_t IsModelPersistence () const
 
virtual Bool_t IsSignalLike ()
 uses a pre-set cut on the MVA output (SetSignalReferenceCut and SetSignalReferenceCutOrientation) for a quick determination if an event would be selected as signal or background
 
virtual Bool_t IsSignalLike (Double_t mvaVal)
 uses a pre-set cut on the MVA output (SetSignalReferenceCut and SetSignalReferenceCutOrientation) for a quick determination if an event with this mva output value would be selected as signal or background
 
Bool_t IsSilentFile () const
 
virtual void MakeClass (const TString &classFileName=TString("")) const
 create reader class for method (classification only at present)
 
TDirectoryMethodBaseDir () const
 returns the ROOT directory where all instances of the corresponding MVA method are stored
 
virtual std::map< TString, Double_tOptimizeTuningParameters (TString fomType="ROCIntegral", TString fitType="FitGA")
 call the Optimizer with the set of parameters and ranges that are meant to be tuned.
 
void PrintHelpMessage () const
 prints out method-specific help method
 
void ProcessSetup ()
 process all options the "CheckForUnusedOptions" is done in an independent call, since it may be overridden by derived class (sometimes, eg, fitters are used which can only be implemented during training phase)
 
void ReadStateFromFile ()
 Function to write options and weights to file.
 
void ReadStateFromStream (std::istream &tf)
 read the header from the weight files of the different MVA methods
 
void ReadStateFromStream (TFile &rf)
 write reference MVA distributions (and other information) to a ROOT type weight file
 
void ReadStateFromXMLString (const char *xmlstr)
 for reading from memory
 
void RerouteTransformationHandler (TransformationHandler *fTargetTransformation)
 
virtual void Reset ()
 
virtual void SetAnalysisType (Types::EAnalysisType type)
 
void SetBaseDir (TDirectory *methodDir)
 
void SetFile (TFile *file)
 
void SetMethodBaseDir (TDirectory *methodDir)
 
void SetMethodDir (TDirectory *methodDir)
 
void SetModelPersistence (Bool_t status)
 
void SetSignalReferenceCut (Double_t cut)
 
void SetSignalReferenceCutOrientation (Double_t cutOrientation)
 
void SetSilentFile (Bool_t status)
 
void SetTestTime (Double_t testTime)
 
void SetTestvarName (const TString &v="")
 
void SetTrainTime (Double_t trainTime)
 
virtual void SetTuneParameters (std::map< TString, Double_t > tuneParameters)
 set the tuning parameters according to the argument This is just a dummy .
 
void SetupMethod ()
 setup of methods
 
void StreamerNVirtual (TBuffer &ClassDef_StreamerNVirtual_b)
 
virtual void TestClassification ()
 initialization
 
virtual void TestMulticlass ()
 test multiclass classification
 
virtual void TestRegression (Double_t &bias, Double_t &biasT, Double_t &dev, Double_t &devT, Double_t &rms, Double_t &rmsT, Double_t &mInf, Double_t &mInfT, Double_t &corr, Types::ETreeType type)
 calculate <sum-of-deviation-squared> of regression output versus "true" value from test sample
 
bool TrainingEnded ()
 
void TrainMethod ()
 
virtual void WriteEvaluationHistosToFile (Types::ETreeType treetype)
 writes all MVA evaluation histograms to file
 
virtual void WriteMonitoringHistosToFile () const
 write special monitoring histograms to file dummy implementation here --------------—
 
void WriteStateToFile () const
 write options and weights to file note that each one text file for the main configuration information and one ROOT file for ROOT objects are created
 
- Public Member Functions inherited from TMVA::IMethod
 IMethod ()
 
virtual ~IMethod ()
 
void StreamerNVirtual (TBuffer &ClassDef_StreamerNVirtual_b)
 
- Public Member Functions inherited from TMVA::Configurable
 Configurable (const TString &theOption="")
 constructor
 
virtual ~Configurable ()
 default destructor
 
void AddOptionsXMLTo (void *parent) const
 write options to XML file
 
template<class T >
void AddPreDefVal (const T &)
 
template<class T >
void AddPreDefVal (const TString &optname, const T &)
 
void CheckForUnusedOptions () const
 checks for unused options in option string
 
template<class T >
TMVA::OptionBaseDeclareOptionRef (T &ref, const TString &name, const TString &desc)
 
template<class T >
OptionBaseDeclareOptionRef (T &ref, const TString &name, const TString &desc="")
 
template<class T >
TMVA::OptionBaseDeclareOptionRef (T *&ref, Int_t size, const TString &name, const TString &desc)
 
template<class T >
OptionBaseDeclareOptionRef (T *&ref, Int_t size, const TString &name, const TString &desc="")
 
const char * GetConfigDescription () const
 
const char * GetConfigName () const
 
const TStringGetOptions () const
 
MsgLoggerLog () const
 
virtual void ParseOptions ()
 options parser
 
void PrintOptions () const
 prints out the options set in the options string and the defaults
 
void ReadOptionsFromStream (std::istream &istr)
 read option back from the weight file
 
void ReadOptionsFromXML (void *node)
 
void SetConfigDescription (const char *d)
 
void SetConfigName (const char *n)
 
void SetMsgType (EMsgType t)
 
void SetOptions (const TString &s)
 
void StreamerNVirtual (TBuffer &ClassDef_StreamerNVirtual_b)
 
void WriteOptionsToStream (std::ostream &o, const TString &prefix) const
 write options to output stream (e.g. in writing the MVA weight files
 
- Public Member Functions inherited from TNamed
 TNamed ()
 
 TNamed (const char *name, const char *title)
 
 TNamed (const TNamed &named)
 TNamed copy ctor.
 
 TNamed (const TString &name, const TString &title)
 
virtual ~TNamed ()
 TNamed destructor.
 
void Clear (Option_t *option="") override
 Set name and title to empty strings ("").
 
TObjectClone (const char *newname="") const override
 Make a clone of an object using the Streamer facility.
 
Int_t Compare (const TObject *obj) const override
 Compare two TNamed objects.
 
void Copy (TObject &named) const override
 Copy this to obj.
 
virtual void FillBuffer (char *&buffer)
 Encode TNamed into output buffer.
 
const char * GetName () const override
 Returns name of object.
 
const char * GetTitle () const override
 Returns title of object.
 
ULong_t Hash () const override
 Return hash value for this object.
 
TClassIsA () const override
 
Bool_t IsSortable () const override
 
void ls (Option_t *option="") const override
 List TNamed name and title.
 
TNamedoperator= (const TNamed &rhs)
 TNamed assignment operator.
 
void Print (Option_t *option="") const override
 Print TNamed name and title.
 
virtual void SetName (const char *name)
 Set the name of the TNamed.
 
virtual void SetNameTitle (const char *name, const char *title)
 Set all the TNamed parameters (name and title).
 
virtual void SetTitle (const char *title="")
 Set the title of the TNamed.
 
virtual Int_t Sizeof () const
 Return size of the TNamed part of the TObject.
 
void Streamer (TBuffer &) override
 Stream an object of class TObject.
 
void StreamerNVirtual (TBuffer &ClassDef_StreamerNVirtual_b)
 
- Public Member Functions inherited from TObject
 TObject ()
 TObject constructor.
 
 TObject (const TObject &object)
 TObject copy ctor.
 
virtual ~TObject ()
 TObject destructor.
 
void AbstractMethod (const char *method) const
 Use this method to implement an "abstract" method that you don't want to leave purely abstract.
 
virtual void AppendPad (Option_t *option="")
 Append graphics object to current pad.
 
virtual void Browse (TBrowser *b)
 Browse object. May be overridden for another default action.
 
ULong_t CheckedHash ()
 Check and record whether this class has a consistent Hash/RecursiveRemove setup (*) and then return the regular Hash value for this object.
 
virtual const char * ClassName () const
 Returns name of class to which the object belongs.
 
virtual void Delete (Option_t *option="")
 Delete this object.
 
virtual Int_t DistancetoPrimitive (Int_t px, Int_t py)
 Computes distance from point (px,py) to the object.
 
virtual void Draw (Option_t *option="")
 Default Draw method for all objects.
 
virtual void DrawClass () const
 Draw class inheritance tree of the class to which this object belongs.
 
virtual TObjectDrawClone (Option_t *option="") const
 Draw a clone of this object in the current selected pad with: gROOT->SetSelectedPad(c1).
 
virtual void Dump () const
 Dump contents of object on stdout.
 
virtual void Error (const char *method, const char *msgfmt,...) const
 Issue error message.
 
virtual void Execute (const char *method, const char *params, Int_t *error=nullptr)
 Execute method on this object with the given parameter string, e.g.
 
virtual void Execute (TMethod *method, TObjArray *params, Int_t *error=nullptr)
 Execute method on this object with parameters stored in the TObjArray.
 
virtual void ExecuteEvent (Int_t event, Int_t px, Int_t py)
 Execute action corresponding to an event at (px,py).
 
virtual void Fatal (const char *method, const char *msgfmt,...) const
 Issue fatal error message.
 
virtual TObjectFindObject (const char *name) const
 Must be redefined in derived classes.
 
virtual TObjectFindObject (const TObject *obj) const
 Must be redefined in derived classes.
 
virtual Option_tGetDrawOption () const
 Get option used by the graphics system to draw this object.
 
virtual const char * GetIconName () const
 Returns mime type name of object.
 
virtual char * GetObjectInfo (Int_t px, Int_t py) const
 Returns string containing info about the object at position (px,py).
 
virtual Option_tGetOption () const
 
virtual UInt_t GetUniqueID () const
 Return the unique object id.
 
virtual Bool_t HandleTimer (TTimer *timer)
 Execute action in response of a timer timing out.
 
Bool_t HasInconsistentHash () const
 Return true is the type of this object is known to have an inconsistent setup for Hash and RecursiveRemove (i.e.
 
virtual void Info (const char *method, const char *msgfmt,...) const
 Issue info message.
 
virtual Bool_t InheritsFrom (const char *classname) const
 Returns kTRUE if object inherits from class "classname".
 
virtual Bool_t InheritsFrom (const TClass *cl) const
 Returns kTRUE if object inherits from TClass cl.
 
virtual void Inspect () const
 Dump contents of this object in a graphics canvas.
 
void InvertBit (UInt_t f)
 
Bool_t IsDestructed () const
 IsDestructed.
 
virtual Bool_t IsEqual (const TObject *obj) const
 Default equal comparison (objects are equal if they have the same address in memory).
 
virtual Bool_t IsFolder () const
 Returns kTRUE in case object contains browsable objects (like containers or lists of other objects).
 
R__ALWAYS_INLINE Bool_t IsOnHeap () const
 
R__ALWAYS_INLINE Bool_t IsZombie () const
 
void MayNotUse (const char *method) const
 Use this method to signal that a method (defined in a base class) may not be called in a derived class (in principle against good design since a child class should not provide less functionality than its parent, however, sometimes it is necessary).
 
virtual Bool_t Notify ()
 This method must be overridden to handle object notification (the base implementation is no-op).
 
void Obsolete (const char *method, const char *asOfVers, const char *removedFromVers) const
 Use this method to declare a method obsolete.
 
void operator delete (void *ptr)
 Operator delete.
 
void operator delete (void *ptr, void *vp)
 Only called by placement new when throwing an exception.
 
void operator delete[] (void *ptr)
 Operator delete [].
 
void operator delete[] (void *ptr, void *vp)
 Only called by placement new[] when throwing an exception.
 
void * operator new (size_t sz)
 
void * operator new (size_t sz, void *vp)
 
void * operator new[] (size_t sz)
 
void * operator new[] (size_t sz, void *vp)
 
TObjectoperator= (const TObject &rhs)
 TObject assignment operator.
 
virtual void Paint (Option_t *option="")
 This method must be overridden if a class wants to paint itself.
 
virtual void Pop ()
 Pop on object drawn in a pad to the top of the display list.
 
virtual Int_t Read (const char *name)
 Read contents of object with specified name from the current directory.
 
virtual void RecursiveRemove (TObject *obj)
 Recursively remove this object from a list.
 
void ResetBit (UInt_t f)
 
virtual void SaveAs (const char *filename="", Option_t *option="") const
 Save this object in the file specified by filename.
 
virtual void SavePrimitive (std::ostream &out, Option_t *option="")
 Save a primitive as a C++ statement(s) on output stream "out".
 
void SetBit (UInt_t f)
 
void SetBit (UInt_t f, Bool_t set)
 Set or unset the user status bits as specified in f.
 
virtual void SetDrawOption (Option_t *option="")
 Set drawing option for object.
 
virtual void SetUniqueID (UInt_t uid)
 Set the unique object id.
 
void StreamerNVirtual (TBuffer &ClassDef_StreamerNVirtual_b)
 
virtual void SysError (const char *method, const char *msgfmt,...) const
 Issue system error message.
 
R__ALWAYS_INLINE Bool_t TestBit (UInt_t f) const
 
Int_t TestBits (UInt_t f) const
 
virtual void UseCurrentStyle ()
 Set current style settings in this object This function is called when either TCanvas::UseCurrentStyle or TROOT::ForceStyle have been invoked.
 
virtual void Warning (const char *method, const char *msgfmt,...) const
 Issue warning message.
 
virtual Int_t Write (const char *name=nullptr, Int_t option=0, Int_t bufsize=0)
 Write this object to the current directory.
 
virtual Int_t Write (const char *name=nullptr, Int_t option=0, Int_t bufsize=0) const
 Write this object to the current directory.
 

Static Public Member Functions

static TClassClass ()
 
static const char * Class_Name ()
 
static constexpr Version_t Class_Version ()
 
static const char * DeclFileName ()
 
- Static Public Member Functions inherited from TMVA::MethodBase
static TClassClass ()
 
static const char * Class_Name ()
 
static constexpr Version_t Class_Version ()
 
static const char * DeclFileName ()
 
- Static Public Member Functions inherited from TMVA::IMethod
static TClassClass ()
 
static const char * Class_Name ()
 
static constexpr Version_t Class_Version ()
 
static const char * DeclFileName ()
 
- Static Public Member Functions inherited from TMVA::Configurable
static TClassClass ()
 
static const char * Class_Name ()
 
static constexpr Version_t Class_Version ()
 
static const char * DeclFileName ()
 
- Static Public Member Functions inherited from TNamed
static TClassClass ()
 
static const char * Class_Name ()
 
static constexpr Version_t Class_Version ()
 
static const char * DeclFileName ()
 
- Static Public Member Functions inherited from TObject
static TClassClass ()
 
static const char * Class_Name ()
 
static constexpr Version_t Class_Version ()
 
static const char * DeclFileName ()
 
static Longptr_t GetDtorOnly ()
 Return destructor only flag.
 
static Bool_t GetObjectStat ()
 Get status of object stat flag.
 
static void SetDtorOnly (void *obj)
 Set destructor only flag.
 
static void SetObjectStat (Bool_t stat)
 Turn on/off tracking of objects in the TObjectTable.
 

Protected Member Functions

void GetHelpMessage () const
 
virtual std::vector< Double_tGetMvaValues (Long64_t firstEvt, Long64_t lastEvt, Bool_t logProgress)
 Evaluate the DeepNet on a vector of input values stored in the TMVA Event class Here we will evaluate using a default batch size and the same architecture used for Training.
 
- Protected Member Functions inherited from TMVA::MethodBase
virtual std::vector< Double_tGetDataMvaValues (DataSet *data=nullptr, Long64_t firstEvt=0, Long64_t lastEvt=-1, Bool_t logProgress=false)
 get all the MVA values for the events of the given Data type
 
const TStringGetInternalVarName (Int_t ivar) const
 
const TStringGetOriginalVarName (Int_t ivar) const
 
const TStringGetWeightFileDir () const
 
Bool_t HasTrainingTree () const
 
Bool_t Help () const
 
Bool_t IgnoreEventsWithNegWeightsInTraining () const
 
Bool_t IsConstructedFromWeightFile () const
 
Bool_t IsNormalised () const
 
virtual void MakeClassSpecific (std::ostream &, const TString &="") const
 
virtual void MakeClassSpecificHeader (std::ostream &, const TString &="") const
 
void NoErrorCalc (Double_t *const err, Double_t *const errUpper)
 
void SetNormalised (Bool_t norm)
 
void SetWeightFileDir (TString fileDir)
 set directory of weight file
 
void SetWeightFileName (TString)
 set the weight file name (depreciated)
 
void Statistics (Types::ETreeType treeType, const TString &theVarName, Double_t &, Double_t &, Double_t &, Double_t &, Double_t &, Double_t &)
 calculates rms,mean, xmin, xmax of the event variable this can be either done for the variables as they are or for normalised variables (in the range of 0-1) if "norm" is set to kTRUE
 
Bool_t TxtWeightsOnly () const
 
Bool_t Verbose () const
 
- Protected Member Functions inherited from TMVA::Configurable
void EnableLooseOptions (Bool_t b=kTRUE)
 
const TStringGetReferenceFile () const
 
Bool_t LooseOptionCheckingEnabled () const
 
void ResetSetFlag ()
 resets the IsSet flag for all declare options to be called before options are read from stream
 
void WriteOptionsReferenceToFile ()
 write complete options to output stream
 
- Protected Member Functions inherited from TObject
virtual void DoError (int level, const char *location, const char *fmt, va_list va) const
 Interface to ErrorHandler (protected).
 
void MakeZombie ()
 

Private Types

using ArchitectureImpl_t = TMVA::DNN::TCpu< Float_t >
 
using DeepNetImpl_t = TMVA::DNN::TDeepNet< ArchitectureImpl_t >
 
enum  ERecurrentLayerType { kLayerRNN = 0 , kLayerLSTM = 1 , kLayerGRU = 2 }
 
using HostBufferImpl_t = typename ArchitectureImpl_t::HostBuffer_t
 
using KeyValueVector_t = std::vector< std::map< TString, TString > >
 
using MatrixImpl_t = typename ArchitectureImpl_t::Matrix_t
 
using ScalarImpl_t = typename ArchitectureImpl_t::Scalar_t
 
using TensorImpl_t = typename ArchitectureImpl_t::Tensor_t
 

Private Member Functions

template<typename Architecture_t , typename Layer_t >
void CreateDeepNet (DNN::TDeepNet< Architecture_t, Layer_t > &deepNet, std::vector< DNN::TDeepNet< Architecture_t, Layer_t > > &nets)
 After calling the ProcesOptions(), all of the options are parsed, so using the parsed options, and given the architecture and the type of the layers, we build the Deep Network passed as a reference in the function.
 
void DeclareOptions ()
 The option handling methods.
 
void FillInputTensor ()
 Get the input event tensor for evaluation Internal function to fill the fXInput tensor with the correct shape from TMVA current Event class.
 
UInt_t GetNumValidationSamples ()
 parce the validation string and return the number of event data used for validation
 
void Init ()
 default initializations
 
void ParseBatchLayout ()
 Parse the input layout.
 
template<typename Architecture_t , typename Layer_t >
void ParseBatchNormLayer (DNN::TDeepNet< Architecture_t, Layer_t > &deepNet, std::vector< DNN::TDeepNet< Architecture_t, Layer_t > > &nets, TString layerString, TString delim)
 Pases the layer string and creates the appropriate reshape layer.
 
template<typename Architecture_t , typename Layer_t >
void ParseConvLayer (DNN::TDeepNet< Architecture_t, Layer_t > &deepNet, std::vector< DNN::TDeepNet< Architecture_t, Layer_t > > &nets, TString layerString, TString delim)
 Pases the layer string and creates the appropriate convolutional layer.
 
template<typename Architecture_t , typename Layer_t >
void ParseDenseLayer (DNN::TDeepNet< Architecture_t, Layer_t > &deepNet, std::vector< DNN::TDeepNet< Architecture_t, Layer_t > > &nets, TString layerString, TString delim)
 Pases the layer string and creates the appropriate dense layer.
 
void ParseInputLayout ()
 Parse the input layout.
 
template<typename Architecture_t , typename Layer_t >
void ParseMaxPoolLayer (DNN::TDeepNet< Architecture_t, Layer_t > &deepNet, std::vector< DNN::TDeepNet< Architecture_t, Layer_t > > &nets, TString layerString, TString delim)
 Pases the layer string and creates the appropriate max pool layer.
 
template<typename Architecture_t , typename Layer_t >
void ParseRecurrentLayer (ERecurrentLayerType type, DNN::TDeepNet< Architecture_t, Layer_t > &deepNet, std::vector< DNN::TDeepNet< Architecture_t, Layer_t > > &nets, TString layerString, TString delim)
 Pases the layer string and creates the appropriate rnn layer.
 
template<typename Architecture_t , typename Layer_t >
void ParseReshapeLayer (DNN::TDeepNet< Architecture_t, Layer_t > &deepNet, std::vector< DNN::TDeepNet< Architecture_t, Layer_t > > &nets, TString layerString, TString delim)
 Pases the layer string and creates the appropriate reshape layer.
 
template<typename Architecture_t >
std::vector< Double_tPredictDeepNet (Long64_t firstEvt, Long64_t lastEvt, size_t batchSize, Bool_t logProgress)
 perform prediction of the deep neural network using batches (called by GetMvaValues)
 
void ProcessOptions ()
 
template<typename Architecture_t >
void TrainDeepNet ()
 train of deep neural network using the defined architecture
 

Private Attributes

TString fArchitectureString
 The string defining the architecture: CPU or GPU.
 
size_t fBatchDepth
 The depth of the batch used to train the deep net.
 
size_t fBatchHeight
 The height of the batch used to train the deep net.
 
TString fBatchLayoutString
 The string defining the layout of the batch.
 
size_t fBatchWidth
 The width of the batch used to train the deep net.
 
bool fBuildNet
 Flag to control whether to build fNet, the stored network used for the evaluation.
 
TString fErrorStrategy
 The string defining the error strategy for training.
 
TString fInputLayoutString
 The string defining the layout of the input.
 
std::vector< size_t > fInputShape
 Contains the batch size (no.
 
TString fLayoutString
 The string defining the layout of the deep net.
 
DNN::ELossFunction fLossFunction
 The loss function.
 
std::unique_ptr< DeepNetImpl_tfNet
 
TString fNumValidationString
 The string defining the number (or percentage) of training data used for validation.
 
DNN::EOutputFunction fOutputFunction
 The output function for making the predictions.
 
size_t fRandomSeed
 The random seed used to initialize the weights and shuffling batches (default is zero)
 
bool fResume
 
KeyValueVector_t fSettings
 Map for the training strategy.
 
std::vector< TTrainingSettingsfTrainingSettings
 The vector defining each training strategy.
 
TString fTrainingStrategyString
 The string defining the training strategy.
 
DNN::EInitialization fWeightInitialization
 The initialization method.
 
TString fWeightInitializationString
 The string defining the weight initialization method.
 
TensorImpl_t fXInput
 
HostBufferImpl_t fXInputBuffer
 
std::unique_ptr< MatrixImpl_tfYHat
 

Additional Inherited Members

- Public Types inherited from TMVA::MethodBase
enum  EWeightFileType { kROOT =0 , kTEXT }
 
- Public Types inherited from TObject
enum  {
  kIsOnHeap = 0x01000000 , kNotDeleted = 0x02000000 , kZombie = 0x04000000 , kInconsistent = 0x08000000 ,
  kBitMask = 0x00ffffff
}
 
enum  { kSingleKey = (1ULL << ( 0 )) , kOverwrite = (1ULL << ( 1 )) , kWriteDelete = (1ULL << ( 2 )) }
 
enum  EDeprecatedStatusBits { kObjInCanvas = (1ULL << ( 3 )) }
 
enum  EStatusBits {
  kCanDelete = (1ULL << ( 0 )) , kMustCleanup = (1ULL << ( 3 )) , kIsReferenced = (1ULL << ( 4 )) , kHasUUID = (1ULL << ( 5 )) ,
  kCannotPick = (1ULL << ( 6 )) , kNoContextMenu = (1ULL << ( 8 )) , kInvalidObject = (1ULL << ( 13 ))
}
 
- Public Attributes inherited from TMVA::MethodBase
Bool_t fSetupCompleted
 
TrainingHistory fTrainHistory
 
- Protected Types inherited from TObject
enum  { kOnlyPrepStep = (1ULL << ( 3 )) }
 
- Protected Attributes inherited from TMVA::MethodBase
Types::EAnalysisType fAnalysisType
 
UInt_t fBackgroundClass
 
bool fExitFromTraining = false
 
std::vector< TString > * fInputVars
 
IPythonInteractivefInteractive = nullptr
 temporary dataset used when evaluating on a different data (used by MethodCategory::GetMvaValues)
 
UInt_t fIPyCurrentIter = 0
 
UInt_t fIPyMaxIter = 0
 
std::vector< Float_t > * fMulticlassReturnVal
 
Int_t fNbins
 
Int_t fNbinsH
 
Int_t fNbinsMVAoutput
 
RankingfRanking
 
std::vector< Float_t > * fRegressionReturnVal
 
ResultsfResults
 
UInt_t fSignalClass
 
DataSetfTmpData = nullptr
 temporary event when testing on a different DataSet than the own one
 
const EventfTmpEvent
 
- Protected Attributes inherited from TMVA::Configurable
MsgLoggerfLogger
 ! message logger
 
- Protected Attributes inherited from TNamed
TString fName
 
TString fTitle
 

#include <TMVA/MethodDL.h>

Inheritance diagram for TMVA::MethodDL:
[legend]

Member Typedef Documentation

◆ ArchitectureImpl_t

Definition at line 103 of file MethodDL.h.

◆ DeepNetImpl_t

◆ HostBufferImpl_t

Definition at line 110 of file MethodDL.h.

◆ KeyValueVector_t

using TMVA::MethodDL::KeyValueVector_t = std::vector<std::map<TString, TString> >
private

Definition at line 93 of file MethodDL.h.

◆ MatrixImpl_t

Definition at line 107 of file MethodDL.h.

◆ ScalarImpl_t

Definition at line 109 of file MethodDL.h.

◆ TensorImpl_t

Definition at line 108 of file MethodDL.h.

Member Enumeration Documentation

◆ ERecurrentLayerType

Enumerator
kLayerRNN 
kLayerLSTM 
kLayerGRU 

Definition at line 153 of file MethodDL.h.

Constructor & Destructor Documentation

◆ MethodDL() [1/2]

TMVA::MethodDL::MethodDL ( const TString jobName,
const TString methodTitle,
DataSetInfo theData,
const TString theOption 
)

Constructor.

Standard constructor.

Definition at line 1019 of file MethodDL.cxx.

◆ MethodDL() [2/2]

TMVA::MethodDL::MethodDL ( DataSetInfo theData,
const TString theWeightFile 
)

Constructor.

Constructor from a weight file.

Definition at line 1032 of file MethodDL.cxx.

◆ ~MethodDL()

TMVA::MethodDL::~MethodDL ( )
virtual

Virtual Destructor.

Destructor.

Definition at line 1045 of file MethodDL.cxx.

Member Function Documentation

◆ AddWeightsXMLTo()

void TMVA::MethodDL::AddWeightsXMLTo ( void *  parent) const
virtual

Implements TMVA::MethodBase.

Definition at line 2051 of file MethodDL.cxx.

◆ Class()

static TClass * TMVA::MethodDL::Class ( )
static
Returns
TClass describing this class

◆ Class_Name()

static const char * TMVA::MethodDL::Class_Name ( )
static
Returns
Name of this class

◆ Class_Version()

static constexpr Version_t TMVA::MethodDL::Class_Version ( )
inlinestaticconstexpr
Returns
Version of this class

Definition at line 212 of file MethodDL.h.

◆ CreateDeepNet()

template<typename Architecture_t , typename Layer_t >
void TMVA::MethodDL::CreateDeepNet ( DNN::TDeepNet< Architecture_t, Layer_t > &  deepNet,
std::vector< DNN::TDeepNet< Architecture_t, Layer_t > > &  nets 
)
private

After calling the ProcesOptions(), all of the options are parsed, so using the parsed options, and given the architecture and the type of the layers, we build the Deep Network passed as a reference in the function.

Create a deep net based on the layout string.

Definition at line 529 of file MethodDL.cxx.

◆ CreateRanking()

const Ranking * TMVA::MethodDL::CreateRanking ( )
virtual

Implements TMVA::MethodBase.

Definition at line 2335 of file MethodDL.cxx.

◆ DeclareOptions()

void TMVA::MethodDL::DeclareOptions ( )
privatevirtual

The option handling methods.

Implements TMVA::MethodBase.

Definition at line 167 of file MethodDL.cxx.

◆ DeclFileName()

static const char * TMVA::MethodDL::DeclFileName ( )
inlinestatic
Returns
Name of the file containing the class declaration

Definition at line 212 of file MethodDL.h.

◆ FillInputTensor()

void TMVA::MethodDL::FillInputTensor ( )
private

Get the input event tensor for evaluation Internal function to fill the fXInput tensor with the correct shape from TMVA current Event class.

Definition at line 1704 of file MethodDL.cxx.

◆ GetArchitectureString()

TString TMVA::MethodDL::GetArchitectureString ( ) const
inline

Definition at line 278 of file MethodDL.h.

◆ GetBatchDepth()

size_t TMVA::MethodDL::GetBatchDepth ( ) const
inline

Definition at line 262 of file MethodDL.h.

◆ GetBatchHeight()

size_t TMVA::MethodDL::GetBatchHeight ( ) const
inline

Definition at line 263 of file MethodDL.h.

◆ GetBatchLayoutString()

TString TMVA::MethodDL::GetBatchLayoutString ( ) const
inline

Definition at line 273 of file MethodDL.h.

◆ GetBatchSize()

size_t TMVA::MethodDL::GetBatchSize ( ) const
inline

Definition at line 261 of file MethodDL.h.

◆ GetBatchWidth()

size_t TMVA::MethodDL::GetBatchWidth ( ) const
inline

Definition at line 264 of file MethodDL.h.

◆ GetDeepNet()

const DeepNetImpl_t & TMVA::MethodDL::GetDeepNet ( ) const
inline

Definition at line 266 of file MethodDL.h.

◆ GetErrorStrategyString()

TString TMVA::MethodDL::GetErrorStrategyString ( ) const
inline

Definition at line 275 of file MethodDL.h.

◆ GetHelpMessage()

void TMVA::MethodDL::GetHelpMessage ( ) const
protectedvirtual

Implements TMVA::IMethod.

Definition at line 2342 of file MethodDL.cxx.

◆ GetInputDepth()

size_t TMVA::MethodDL::GetInputDepth ( ) const
inline

Definition at line 255 of file MethodDL.h.

◆ GetInputDim()

size_t TMVA::MethodDL::GetInputDim ( ) const
inline

Definition at line 258 of file MethodDL.h.

◆ GetInputHeight()

size_t TMVA::MethodDL::GetInputHeight ( ) const
inline

Definition at line 256 of file MethodDL.h.

◆ GetInputLayoutString()

TString TMVA::MethodDL::GetInputLayoutString ( ) const
inline

Definition at line 272 of file MethodDL.h.

◆ GetInputShape()

std::vector< size_t > TMVA::MethodDL::GetInputShape ( ) const
inline

Definition at line 259 of file MethodDL.h.

◆ GetInputWidth()

size_t TMVA::MethodDL::GetInputWidth ( ) const
inline

Definition at line 257 of file MethodDL.h.

◆ GetKeyValueSettings() [1/2]

KeyValueVector_t & TMVA::MethodDL::GetKeyValueSettings ( )
inline

Definition at line 283 of file MethodDL.h.

◆ GetKeyValueSettings() [2/2]

const KeyValueVector_t & TMVA::MethodDL::GetKeyValueSettings ( ) const
inline

Definition at line 282 of file MethodDL.h.

◆ GetLayoutString()

TString TMVA::MethodDL::GetLayoutString ( ) const
inline

Definition at line 274 of file MethodDL.h.

◆ GetLossFunction()

DNN::ELossFunction TMVA::MethodDL::GetLossFunction ( ) const
inline

Definition at line 270 of file MethodDL.h.

◆ GetMulticlassValues()

virtual const std::vector< Float_t > & TMVA::MethodDL::GetMulticlassValues ( )
virtual

Reimplemented from TMVA::MethodBase.

◆ GetMvaValue()

Double_t TMVA::MethodDL::GetMvaValue ( Double_t err = nullptr,
Double_t errUpper = nullptr 
)
virtual

Implements TMVA::MethodBase.

Definition at line 1772 of file MethodDL.cxx.

◆ GetMvaValues()

std::vector< Double_t > TMVA::MethodDL::GetMvaValues ( Long64_t  firstEvt,
Long64_t  lastEvt,
Bool_t  logProgress 
)
protectedvirtual

Evaluate the DeepNet on a vector of input values stored in the TMVA Event class Here we will evaluate using a default batch size and the same architecture used for Training.

Reimplemented from TMVA::MethodBase.

Definition at line 2022 of file MethodDL.cxx.

◆ GetNumValidationSamples()

UInt_t TMVA::MethodDL::GetNumValidationSamples ( )
private

parce the validation string and return the number of event data used for validation

◆ GetOutputFunction()

DNN::EOutputFunction TMVA::MethodDL::GetOutputFunction ( ) const
inline

Definition at line 269 of file MethodDL.h.

◆ GetRegressionValues()

virtual const std::vector< Float_t > & TMVA::MethodDL::GetRegressionValues ( )
virtual

Reimplemented from TMVA::MethodBase.

◆ GetTrainingSettings() [1/2]

std::vector< TTrainingSettings > & TMVA::MethodDL::GetTrainingSettings ( )
inline

Definition at line 281 of file MethodDL.h.

◆ GetTrainingSettings() [2/2]

const std::vector< TTrainingSettings > & TMVA::MethodDL::GetTrainingSettings ( ) const
inline

Definition at line 280 of file MethodDL.h.

◆ GetTrainingStrategyString()

TString TMVA::MethodDL::GetTrainingStrategyString ( ) const
inline

Definition at line 276 of file MethodDL.h.

◆ GetWeightInitialization()

DNN::EInitialization TMVA::MethodDL::GetWeightInitialization ( ) const
inline

Definition at line 268 of file MethodDL.h.

◆ GetWeightInitializationString()

TString TMVA::MethodDL::GetWeightInitializationString ( ) const
inline

Definition at line 277 of file MethodDL.h.

◆ HasAnalysisType()

Bool_t TMVA::MethodDL::HasAnalysisType ( Types::EAnalysisType  type,
UInt_t  numberClasses,
UInt_t  numberTargets 
)
virtual

Check the type of analysis the deep learning network can do.

What kind of analysis type can handle the CNN.

Implements TMVA::IMethod.

Definition at line 1091 of file MethodDL.cxx.

◆ Init()

void TMVA::MethodDL::Init ( void  )
privatevirtual

default initializations

Implements TMVA::MethodBase.

Definition at line 432 of file MethodDL.cxx.

◆ IsA()

virtual TClass * TMVA::MethodDL::IsA ( ) const
inlinevirtual
Returns
TClass describing current object

Reimplemented from TMVA::MethodBase.

Definition at line 212 of file MethodDL.h.

◆ ParseBatchLayout()

void TMVA::MethodDL::ParseBatchLayout ( )
private

Parse the input layout.

Definition at line 482 of file MethodDL.cxx.

◆ ParseBatchNormLayer()

template<typename Architecture_t , typename Layer_t >
void TMVA::MethodDL::ParseBatchNormLayer ( DNN::TDeepNet< Architecture_t, Layer_t > &  deepNet,
std::vector< DNN::TDeepNet< Architecture_t, Layer_t > > &  nets,
TString  layerString,
TString  delim 
)
private

Pases the layer string and creates the appropriate reshape layer.

Definition at line 890 of file MethodDL.cxx.

◆ ParseConvLayer()

template<typename Architecture_t , typename Layer_t >
void TMVA::MethodDL::ParseConvLayer ( DNN::TDeepNet< Architecture_t, Layer_t > &  deepNet,
std::vector< DNN::TDeepNet< Architecture_t, Layer_t > > &  nets,
TString  layerString,
TString  delim 
)
private

Pases the layer string and creates the appropriate convolutional layer.

Definition at line 669 of file MethodDL.cxx.

◆ ParseDenseLayer()

template<typename Architecture_t , typename Layer_t >
void TMVA::MethodDL::ParseDenseLayer ( DNN::TDeepNet< Architecture_t, Layer_t > &  deepNet,
std::vector< DNN::TDeepNet< Architecture_t, Layer_t > > &  nets,
TString  layerString,
TString  delim 
)
private

Pases the layer string and creates the appropriate dense layer.

Definition at line 583 of file MethodDL.cxx.

◆ ParseInputLayout()

void TMVA::MethodDL::ParseInputLayout ( )
private

Parse the input layout.

Definition at line 439 of file MethodDL.cxx.

◆ ParseKeyValueString()

auto TMVA::MethodDL::ParseKeyValueString ( TString  parseString,
TString  blockDelim,
TString  tokenDelim 
)

Function for parsing the training settings, provided as a string in a key-value form.

Parse key value pairs in blocks -> return vector of blocks with map of key value pairs.


Definition at line 1052 of file MethodDL.cxx.

◆ ParseMaxPoolLayer()

template<typename Architecture_t , typename Layer_t >
void TMVA::MethodDL::ParseMaxPoolLayer ( DNN::TDeepNet< Architecture_t, Layer_t > &  deepNet,
std::vector< DNN::TDeepNet< Architecture_t, Layer_t > > &  nets,
TString  layerString,
TString  delim 
)
private

Pases the layer string and creates the appropriate max pool layer.

Definition at line 768 of file MethodDL.cxx.

◆ ParseRecurrentLayer()

template<typename Architecture_t , typename Layer_t >
void TMVA::MethodDL::ParseRecurrentLayer ( ERecurrentLayerType  type,
DNN::TDeepNet< Architecture_t, Layer_t > &  deepNet,
std::vector< DNN::TDeepNet< Architecture_t, Layer_t > > &  nets,
TString  layerString,
TString  delim 
)
private

Pases the layer string and creates the appropriate rnn layer.

Definition at line 931 of file MethodDL.cxx.

◆ ParseReshapeLayer()

template<typename Architecture_t , typename Layer_t >
void TMVA::MethodDL::ParseReshapeLayer ( DNN::TDeepNet< Architecture_t, Layer_t > &  deepNet,
std::vector< DNN::TDeepNet< Architecture_t, Layer_t > > &  nets,
TString  layerString,
TString  delim 
)
private

Pases the layer string and creates the appropriate reshape layer.

Definition at line 829 of file MethodDL.cxx.

◆ PredictDeepNet()

template<typename Architecture_t >
std::vector< Double_t > TMVA::MethodDL::PredictDeepNet ( Long64_t  firstEvt,
Long64_t  lastEvt,
size_t  batchSize,
Bool_t  logProgress 
)
private

perform prediction of the deep neural network using batches (called by GetMvaValues)

Evaluate the DeepNet on a vector of input values stored in the TMVA Event class.

Definition at line 1828 of file MethodDL.cxx.

◆ ProcessOptions()

void TMVA::MethodDL::ProcessOptions ( )
privatevirtual

Implements TMVA::MethodBase.

Definition at line 219 of file MethodDL.cxx.

◆ ReadWeightsFromStream() [1/3]

void TMVA::MethodDL::ReadWeightsFromStream ( std::istream &  )
virtual

Implements TMVA::MethodBase.

Definition at line 2330 of file MethodDL.cxx.

◆ ReadWeightsFromStream() [2/3]

virtual void TMVA::MethodBase::ReadWeightsFromStream ( std::istream &  )
virtual

Methods for writing and reading weights.

Implements TMVA::MethodBase.

◆ ReadWeightsFromStream() [3/3]

virtual void TMVA::MethodBase::ReadWeightsFromStream ( TFile )
inlinevirtual

Methods for writing and reading weights.

Reimplemented from TMVA::MethodBase.

Definition at line 266 of file MethodBase.h.

◆ ReadWeightsFromXML()

void TMVA::MethodDL::ReadWeightsFromXML ( void *  wghtnode)
virtual

Implements TMVA::MethodBase.

Definition at line 2112 of file MethodDL.cxx.

◆ SetArchitectureString()

void TMVA::MethodDL::SetArchitectureString ( TString  architectureString)
inline

Definition at line 307 of file MethodDL.h.

◆ SetBatchDepth()

void TMVA::MethodDL::SetBatchDepth ( size_t  batchDepth)
inline

Definition at line 292 of file MethodDL.h.

◆ SetBatchHeight()

void TMVA::MethodDL::SetBatchHeight ( size_t  batchHeight)
inline

Definition at line 293 of file MethodDL.h.

◆ SetBatchSize()

void TMVA::MethodDL::SetBatchSize ( size_t  batchSize)
inline

Definition at line 291 of file MethodDL.h.

◆ SetBatchWidth()

void TMVA::MethodDL::SetBatchWidth ( size_t  batchWidth)
inline

Definition at line 294 of file MethodDL.h.

◆ SetErrorStrategyString()

void TMVA::MethodDL::SetErrorStrategyString ( TString  errorStrategy)
inline

Definition at line 301 of file MethodDL.h.

◆ SetInputDepth()

void TMVA::MethodDL::SetInputDepth ( int  inputDepth)
inline

Setters.

Definition at line 286 of file MethodDL.h.

◆ SetInputHeight()

void TMVA::MethodDL::SetInputHeight ( int  inputHeight)
inline

Definition at line 287 of file MethodDL.h.

◆ SetInputShape()

void TMVA::MethodDL::SetInputShape ( std::vector< size_t >  inputShape)
inline

Definition at line 289 of file MethodDL.h.

◆ SetInputWidth()

void TMVA::MethodDL::SetInputWidth ( int  inputWidth)
inline

Definition at line 288 of file MethodDL.h.

◆ SetLayoutString()

void TMVA::MethodDL::SetLayoutString ( TString  layoutString)
inline

Definition at line 308 of file MethodDL.h.

◆ SetOutputFunction()

void TMVA::MethodDL::SetOutputFunction ( DNN::EOutputFunction  outputFunction)
inline

Definition at line 300 of file MethodDL.h.

◆ SetTrainingStrategyString()

void TMVA::MethodDL::SetTrainingStrategyString ( TString  trainingStrategyString)
inline

Definition at line 302 of file MethodDL.h.

◆ SetWeightInitialization()

void TMVA::MethodDL::SetWeightInitialization ( DNN::EInitialization  weightInitialization)
inline

Definition at line 296 of file MethodDL.h.

◆ SetWeightInitializationString()

void TMVA::MethodDL::SetWeightInitializationString ( TString  weightInitializationString)
inline

Definition at line 303 of file MethodDL.h.

◆ Streamer()

virtual void TMVA::MethodDL::Streamer ( TBuffer )
virtual

Reimplemented from TMVA::MethodBase.

◆ StreamerNVirtual()

void TMVA::MethodDL::StreamerNVirtual ( TBuffer ClassDef_StreamerNVirtual_b)
inline

Definition at line 212 of file MethodDL.h.

◆ Train()

void TMVA::MethodDL::Train ( void  )
virtual

Methods for training the deep learning network.

Implements TMVA::MethodBase.

Definition at line 1659 of file MethodDL.cxx.

◆ TrainDeepNet()

template<typename Architecture_t >
void TMVA::MethodDL::TrainDeepNet
private

train of deep neural network using the defined architecture

Implementation of architecture specific train method.

Definition at line 1164 of file MethodDL.cxx.

Member Data Documentation

◆ fArchitectureString

TString TMVA::MethodDL::fArchitectureString
private

The string defining the architecture: CPU or GPU.

Definition at line 198 of file MethodDL.h.

◆ fBatchDepth

size_t TMVA::MethodDL::fBatchDepth
private

The depth of the batch used to train the deep net.

Definition at line 182 of file MethodDL.h.

◆ fBatchHeight

size_t TMVA::MethodDL::fBatchHeight
private

The height of the batch used to train the deep net.

Definition at line 183 of file MethodDL.h.

◆ fBatchLayoutString

TString TMVA::MethodDL::fBatchLayoutString
private

The string defining the layout of the batch.

Definition at line 193 of file MethodDL.h.

◆ fBatchWidth

size_t TMVA::MethodDL::fBatchWidth
private

The width of the batch used to train the deep net.

Definition at line 184 of file MethodDL.h.

◆ fBuildNet

bool TMVA::MethodDL::fBuildNet
private

Flag to control whether to build fNet, the stored network used for the evaluation.

Definition at line 201 of file MethodDL.h.

◆ fErrorStrategy

TString TMVA::MethodDL::fErrorStrategy
private

The string defining the error strategy for training.

Definition at line 195 of file MethodDL.h.

◆ fInputLayoutString

TString TMVA::MethodDL::fInputLayoutString
private

The string defining the layout of the input.

Definition at line 192 of file MethodDL.h.

◆ fInputShape

std::vector<size_t> TMVA::MethodDL::fInputShape
private

Contains the batch size (no.

of images in the batch), input depth (no. channels) and further input dimensions of the data (image height, width ...)

Definition at line 178 of file MethodDL.h.

◆ fLayoutString

TString TMVA::MethodDL::fLayoutString
private

The string defining the layout of the deep net.

Definition at line 194 of file MethodDL.h.

◆ fLossFunction

DNN::ELossFunction TMVA::MethodDL::fLossFunction
private

The loss function.

Definition at line 190 of file MethodDL.h.

◆ fNet

std::unique_ptr<DeepNetImpl_t> TMVA::MethodDL::fNet
private

Definition at line 209 of file MethodDL.h.

◆ fNumValidationString

TString TMVA::MethodDL::fNumValidationString
private

The string defining the number (or percentage) of training data used for validation.

Definition at line 199 of file MethodDL.h.

◆ fOutputFunction

DNN::EOutputFunction TMVA::MethodDL::fOutputFunction
private

The output function for making the predictions.

Definition at line 189 of file MethodDL.h.

◆ fRandomSeed

size_t TMVA::MethodDL::fRandomSeed
private

The random seed used to initialize the weights and shuffling batches (default is zero)

Definition at line 186 of file MethodDL.h.

◆ fResume

bool TMVA::MethodDL::fResume
private

Definition at line 200 of file MethodDL.h.

◆ fSettings

KeyValueVector_t TMVA::MethodDL::fSettings
private

Map for the training strategy.

Definition at line 203 of file MethodDL.h.

◆ fTrainingSettings

std::vector<TTrainingSettings> TMVA::MethodDL::fTrainingSettings
private

The vector defining each training strategy.

Definition at line 204 of file MethodDL.h.

◆ fTrainingStrategyString

TString TMVA::MethodDL::fTrainingStrategyString
private

The string defining the training strategy.

Definition at line 196 of file MethodDL.h.

◆ fWeightInitialization

DNN::EInitialization TMVA::MethodDL::fWeightInitialization
private

The initialization method.

Definition at line 188 of file MethodDL.h.

◆ fWeightInitializationString

TString TMVA::MethodDL::fWeightInitializationString
private

The string defining the weight initialization method.

Definition at line 197 of file MethodDL.h.

◆ fXInput

TensorImpl_t TMVA::MethodDL::fXInput
private

Definition at line 206 of file MethodDL.h.

◆ fXInputBuffer

HostBufferImpl_t TMVA::MethodDL::fXInputBuffer
private

Definition at line 207 of file MethodDL.h.

◆ fYHat

std::unique_ptr<MatrixImpl_t> TMVA::MethodDL::fYHat
private

Definition at line 208 of file MethodDL.h.

Libraries for TMVA::MethodDL:

The documentation for this class was generated from the following files: