ULearningNeuralNetworkData | Unreal Engine 5.7 Documentation

API > API/Plugins > API/Plugins/Learning

Neural Network Data Object

This is the UObject which contains the actual data used by a Neural Network. It stores the raw FileData used to construct the network using NNE, as well as the input and output sizes and a compatibility hash that can be used to quickly check if two networks may be compatible in terms of inputs and outputs.

Internally this also stores the various things required to map between NNE style inference and the style of inference used in Learning via FNeuralNetwork and FNeuralNetworkInference.


Name	ULearningNeuralNetworkData
Type	class
Header File	/Engine/Plugins/Experimental/LearningAgents/Source/Learning/Public/LearningNeuralNetwork.h
Include Path	#include "LearningNeuralNetwork.h"

Syntax

UCLASS (MinimalAPI, BlueprintType)  
class ULearningNeuralNetworkData : public UObject

Inheritance Hierarchy

UObjectBase → UObjectBaseUtility → UObject → ULearningNeuralNetworkData

Variables

Protected

Name	Type	Remarks	Include Path	Unreal Specifiers
CompatibilityHash	int32	Compatibility hash used for testing if inputs to one network are compatible with another.	LearningNeuralNetwork.h	VisibleAnywhere Category="Network Properties"
ContentHash	int32	Content hash which can be used to see when the network data has changed.	LearningNeuralNetwork.h	VisibleAnywhere Category="Network Properties"
FileData	TArray< uint8 >	File data used by NNE.	LearningNeuralNetwork.h
InputSize	int32	Size of the inputs expected by this network.	LearningNeuralNetwork.h	VisibleAnywhere Category="Network Properties"
ModelData	TObjectPtr< UNNEModelData >	Model Data used by NNE.	LearningNeuralNetwork.h
Network	TSharedPtr< UE::Learning::FNeuralNetwork >	Internal in-memory network representation.	LearningNeuralNetwork.h
OutputSize	int32	Size of the output produced by this network.	LearningNeuralNetwork.h	VisibleAnywhere Category="Network Properties"

Functions

Public

Name	Remarks	Include Path
int32 GetCompatibilityHash()	Gets the compatibility hash.	LearningNeuralNetwork.h
int32 GetContentHash()	Gets the content hash.	LearningNeuralNetwork.h
int32 GetInputSize()	Gets the network input size.	LearningNeuralNetwork.h
TSharedPtr< UE::Learning::FNeuralNetwork > & GetNetwork()	Get the FNeuralNetwork object that can be used to do inference.	LearningNeuralNetwork.h
int32 GetOutputSize()	Gets the network output size.	LearningNeuralNetwork.h
int32 GetSnapshotByteNum()	Number of bytes required to save or load a snapshot of this network.	LearningNeuralNetwork.h
void Init ( const int32 InInputSize, const int32 InOutputSize, const int32 InCompatibilityHash, const TArrayView< const uint8 > InFileData )	Initialize the ULearningNeuralNetworkData object given some input and output sizes as well as a compatibility hash and FileData.	LearningNeuralNetwork.h
void InitFrom ( const ULearningNeuralNetworkData* OtherNetworkData )	Initialize this network from another ULearningNeuralNetworkData object.	LearningNeuralNetwork.h
bool IsEmpty()	If this network is empty or not.	LearningNeuralNetwork.h
bool LoadFromSnapshot ( const TArrayView< const uint8 > InBytes )	Load a snapshot of this network from the given array of bytes.	LearningNeuralNetwork.h
void SaveToSnapshot ( TArrayView< uint8 > OutBytes ) const	Save a snapshot of this network to the given array of bytes.	LearningNeuralNetwork.h