SmartEngine  1.6.0
Public Member Functions | List of all members
SmartEngine::ILoss Class Referenceabstract

The loss of a NeuralNetwork is computed using the formula (Expected Ouput - Actual Output)^2 The mean of all these values across the output tensor is used when crunching down the loss to a single value. More...

#include <Loss.h>

Inheritance diagram for SmartEngine::ILoss:
SmartEngine::IGraphNode SmartEngine::IObject

Public Member Functions

virtual float GetLoss ()=0
 Returns the mean L2 loss using the current network and expected state More...
 
- Public Member Functions inherited from SmartEngine::IGraphNode
virtual const char * GetName () const =0
 Returns the name of the graph node. More...
 
virtual int GetOutputDimension () const =0
 Returns the dimension of a single row of this node's output. The Output property's length will be a multiple of this value. More...
 
virtual ObjectPtr< IMatrixExecute ()=0
 Synchronously execute the graph. The returned matrix is read-only. More...
 
virtual ObjectPtr< IMatrixGetLastExecutionResult ()=0
 Get the results of last execution of the graph. The returned matrix is read-only. More...
 
- Public Member Functions inherited from SmartEngine::IObject
virtual ObjectId GetId () const =0
 Returns the ID of this object. More...
 
virtual void AddRef () const =0
 Increments the internal reference count on this object. It is not common to use this method directly. More...
 
virtual void Release () const =0
 Decrements the internal reference count on this object. It is not common to use this method directly. More...
 
virtual int GetRefCount () const =0
 Returns the number of references to this object. More...
 
virtual void * QueryInterface (ObjectClassId id)=0
 Queries the object for an interface and returns a pointer to that interface if found. More...
 
void operator= (IObject const &x)=delete
 

Additional Inherited Members

- Public Attributes inherited from SmartEngine::IObject
 private
 
 __pad0__: IObject() {} IObject(IObject const&) = delete
 

Detailed Description

The loss of a NeuralNetwork is computed using the formula (Expected Ouput - Actual Output)^2 The mean of all these values across the output tensor is used when crunching down the loss to a single value.

Member Function Documentation

◆ GetLoss()

virtual float SmartEngine::ILoss::GetLoss ( )
pure virtual

Returns the mean L2 loss using the current network and expected state

Returns