The MyCaffeTraininerDual is used to perform both reinforcement and recurrent learning training tasks on an instance of the MyCaffeControl. More...

Inheritance diagram for MyCaffe.trainers.MyCaffeTrainerDual:

Public Member Functions
	MyCaffeTrainerDual ()
	The constructor. More...

	MyCaffeTrainerDual (IContainer container)
	The constructor. More...

bool	GetUpdateSnapshot (out int nIteration, out double dfAccuracy)
	Returns true when the training is ready for a snap-shot, false otherwise. More...

DatasetDescriptor	GetDatasetOverride (int nProjectID, ConnectInfo ci=null)
	Returns a dataset override to use (if any) instead of the project's dataset. If there is no dataset override null is returned and the project's dataset is used. More...

void	CleanUp ()
	Releases any resources used by the component. More...

void	Initialize (string strProperties, IXMyCaffeCustomTrainerCallback icallback)
	Initializes a new custom trainer by loading the key-value pair of properties into the property set. More...

void	Test (Component mycaffe, int nIterationOverride, ITERATOR_TYPE type=ITERATOR_TYPE.ITERATION)
	Create a new trainer and use it to run a test cycle using the current 'stage' = RNN or RL. More...

void	Train (Component mycaffe, int nIterationOverride, ITERATOR_TYPE type=ITERATOR_TYPE.ITERATION, TRAIN_STEP step=TRAIN_STEP.NONE)
	Create a new trainer and use it to run a training cycle using the current 'stage' = RNN or RL. More...

void	OnInitialize (InitializeArgs e)
	The OnIntialize callback fires when initializing the trainer. More...

void	OnShutdown ()
	The OnShutdown callback fires when shutting down the trainer. More...

void	OnGetData (GetDataArgs e)
	The OnGetData callback fires from within the Train method and is used to get a new observation data. More...

void	OnConvertOutput (ConvertOutputArgs e)
	The OnConvertOutput callback fires from within the Run method and is used to convert the network output into its native format. More...

void	OnTestAccuracyUpdate (TestAccuracyUpdateArgs e)
	The OnTestAccuracyUpdate callback fires from within the Run method and is used to give the recipient the chance to determine whether the label detected is correct or not. More...

void	OnUpdateStatus (GetStatusArgs e)
	The OnGetStatus callback fires on each iteration within the Train method. More...

void	OnWait (WaitArgs e)
	The OnWait callback fires when waiting for a shutdown. More...

double	GetProperty (string strProp)
	Return a property value from the trainer. More...

void	OpenUi ()
	Open the user interface for the trainer, of one exists. More...

byte[]	Run (Component mycaffe, int nN, out string type)
	Run the network using the run technique implemented by this trainer. More...

Protected Member Functions
virtual DatasetDescriptor	get_dataset_override (int nProjectID, ConnectInfo ci=null)
	Returns a dataset override to use (if any) instead of the project's dataset. If there is no dataset override null is returned and the project's dataset is used. More...

virtual string	get_information ()
	Returns information describing the specific trainer, such as the gym used, if any. More...

virtual IxTrainer	create_trainerD (Component caffe, Stage stage)
	Optionally overridden to return a new type of trainer. More...

virtual IxTrainer	create_trainerF (Component caffe, Stage stage)
	Optionally overridden to return a new type of trainer. More...

virtual void	dispose ()
	Override to dispose of resources used. More...

virtual void	initialize (InitializeArgs e)
	Override called by the Initialize method of the trainer. More...

virtual void	shutdown ()
	Override called from within the CleanUp method. More...

virtual bool	getData (GetDataArgs e)
	Override called by the OnGetData event fired by the Trainer to retrieve a new set of observation collections making up a set of experiences. More...

virtual bool	convertOutput (ConvertOutputArgs e)
	Override called by the OnConvertOutput event fired by the Trainer to convert the network output into its native format. More...

virtual void	testAccuracyUpdate (TestAccuracyUpdateArgs e)
	Override called by the OnTestAccuracyUpdate event fired from within the Run method and is used to give the recipient the chance to determine whether the label detected is correct or not. More...

virtual bool	get_update_snapshot (out int nIteration, out double dfAccuracy)
	Returns true when the training is ready for a snap-shot, false otherwise. More...

virtual void	openUi ()
	Called by OpenUi, override this when a UI (via WCF) should be displayed. More...

virtual BucketCollection	preloaddata (Log log, CancelEvent evtCancel, int nProjectID, PropertySet propertyOverride=null, ConnectInfo ci=null)
	The preloaddata method gives the custom trainer an opportunity to pre-load any data. More...

override void	Dispose (bool disposing)
	Clean up any resources being used. More...

Protected Attributes
CryptoRandom	m_random = new CryptoRandom()
	Random number generator used to get initial actions, etc. More...

PropertySet	m_properties = null
	Specifies the properties parsed from the key-value pair passed to the Initialize method. More...

int	m_nProjectID = 0
	Specifies the project ID of the project held by the instance of MyCaffe. More...

ConnectInfo	m_dsCi = null
	Optionally, specifies the dataset connection info, or null. More...

Properties
virtual string	name `[get]`
	Overriden to give the actual name of the custom trainer. More...

virtual TRAINING_CATEGORY	category `[get]`
	Override when using a training method other than the REINFORCEMENT method (the default). More...

Stage	Stage `[get]`
	Returns the stage under which the trainer is running based on the trainer type. More...

string	Name `[get]`
	Returns the name of the custom trainer. This method calls the 'name' override. More...

TRAINING_CATEGORY	TrainingCategory `[get]`
	Returns the training category of the custom trainer (default = REINFORCEMENT). More...

bool	IsTrainingSupported `[get]`
	Returns whether or not Training is supported. More...

bool	IsTestingSupported `[get]`
	Returns whether or not Testing is supported. More...

bool	IsRunningSupported `[get]`
	Returns whether or not Running is supported. More...

double?	GlobalRewards `[get]`
	Returns the global rewards based on the reward type specified by the 'RewardType' property. More...

double	ImmediateRewards `[get]`
	Returns the immediate rewards for the current training cycle as opposed to the averaged rewards. More...

double	GlobalLoss `[get]`
	Return the global loss. More...

int	GlobalIteration `[get]`
	Returns the global iteration. More...

int	GlobalEpisodeCount `[get]`
	Returns the global episode count. More...

int	GlobalEpisodeMax `[get]`
	Returns the maximum global episode count. More...

double	ExplorationRate `[get]`
	Returns the current exploration rate. More...

double	OptimalSelectionRate `[get]`
	Returns the rate of selection from the optimal set with the highest reward (this setting is optional, default = 0). More...

string	Information `[get]`
	Returns information describing the trainer. More...

Properties inherited from MyCaffe.trainers.IXMyCaffeCustomTrainer
Stage	Stage `[get]`
	Returns the stage that the trainer is running under based on the trainer type. More...

string	Name `[get]`
	Returns the name of the custom trainer. More...

TRAINING_CATEGORY	TrainingCategory `[get]`
	Returns the training category supported by the implementer of the interface. More...

bool	IsTrainingSupported `[get]`
	Returns true when the 'Train' method is supported - this should almost always be true. More...

bool	IsTestingSupported `[get]`
	Returns true when the 'Test' method is supported. More...

bool	IsRunningSupported `[get]`
	Returns true when the 'Run' method is supported. More...

string	Information `[get]`
	Returns general information about the custom trainer. More...

Detailed Description

The MyCaffeTraininerDual is used to perform both reinforcement and recurrent learning training tasks on an instance of the MyCaffeControl.

–RL– Currently, the MyCaffeTrainerDual supports the following reinforcement trainers, each of which are selected with the 'TrainerType=type' property value within the property set specified when calling the Initialize method.

TrainerType=PG.SIMPLE - creates the initial simple policy gradient trainer that only supports single-threaded Sigmoid based models. TrainerType=PG.ST - creates a single-threaded policy gradient trainer that supports both Sigmoid and Softmax based models. TrainerType=PG.MT - creates a multi-threaded policy gradient trainer that supports both Sigmoid and Softmax based models and can train across GPU's. TrainerType=C51.ST = creates a single-threaded network that implements the C51 DDQN algorithm.

Other intitialization properties include:

RewardType=VAL - reports the actual reward values. RewardType=MAX - reports the maximum reward value observed (recommended setting)

Threads=# - specifies the number of threads.

GPUs=#,#,... - specifies the GPU's on which to run each thread. The GPU IDs may be the same as the open project or other GPU's in the system. GPU selection starts with the first GPUID in the list, continues to the end, and then wraps back around to the start of the list. For example if you specifiy to use 3 thread with GPUIDs=0,1 the GPUs will be assigned to each thread as follows: Thread0 => GPUID0, Thread1 => GPUID1, Thread2 => GPUID0

Gamma - specifies the discount rate (default = 0.99) UseRawInput - when true the actual input is used directly, otherwise a difference between the current and previous input is used (default = false).

–RNN– Currently, the MyCaffeTrainerDual also supports the following recurrent trainers, each of which are selected with the 'TrainerType=type' property value within the property set specified when calling the Initialize method.

TrainerType=RNN.SIMPLE - creates the initial simple policy gradient trainer that only supports single-threaded Sigmoid based models.

The following settings are used from the Model and Solver descriptions:

Solver: base_lr - specifies the learning rate used. Model: batch_size - specifies how often accumulated gradients are applied.

Definition at line 57 of file MyCaffeTrainerDual.cs.

Constructor & Destructor Documentation

◆ MyCaffeTrainerDual() [1/2]

MyCaffe.trainers.MyCaffeTrainerDual.MyCaffeTrainerDual ( )

The constructor.

Definition at line 122 of file MyCaffeTrainerDual.cs.

◆ MyCaffeTrainerDual() [2/2]

MyCaffe.trainers.MyCaffeTrainerDual.MyCaffeTrainerDual ( IContainer container )

The constructor.

Parameters

container The container of the component.

Definition at line 131 of file MyCaffeTrainerDual.cs.

Member Function Documentation

◆ CleanUp()

void MyCaffe.trainers.MyCaffeTrainerDual.CleanUp ( )

Releases any resources used by the component.

Implements MyCaffe.trainers.IXMyCaffeCustomTrainer.

Definition at line 469 of file MyCaffeTrainerDual.cs.

◆ convertOutput()

virtual bool MyCaffe.trainers.MyCaffeTrainerDual.convertOutput ( ConvertOutputArgs e )

protectedvirtual

Override called by the OnConvertOutput event fired by the Trainer to convert the network output into its native format.

Parameters

e	Specifies the event arguments.

Returns: When handled this function retunrs true, otherwise it returns false.

Definition at line 340 of file MyCaffeTrainerDual.cs.

◆ create_trainerD()

virtual IxTrainer MyCaffe.trainers.MyCaffeTrainerDual.create_trainerD	(	Component	caffe,
		Stage	stage
	)

protectedvirtual

Optionally overridden to return a new type of trainer.

Override this method when using the MyCaffeControl that uses the double base type.

Parameters

caffe	Specifies the MyCaffeControl used.
stage	Specifies the stage under which the trainer is created.

Returns: The IxTraininer interface implemented by the new trainer is returned.

Definition at line 185 of file MyCaffeTrainerDual.cs.

◆ create_trainerF()

virtual IxTrainer MyCaffe.trainers.MyCaffeTrainerDual.create_trainerF	(	Component	caffe,
		Stage	stage
	)

protectedvirtual

Optionally overridden to return a new type of trainer.

Override this method when using the MyCaffeControl that uses the double base type.

Parameters

caffe	Specifies the MyCaffeControl used.
stage	Specifies the stage under which the trainer is created.

Returns: The IxTraininer interface implemented by the new trainer is returned.

Definition at line 247 of file MyCaffeTrainerDual.cs.

◆ dispose()

virtual void MyCaffe.trainers.MyCaffeTrainerDual.dispose ( )

protectedvirtual

Override to dispose of resources used.

Definition at line 303 of file MyCaffeTrainerDual.cs.

◆ Dispose()

override void MyCaffe.trainers.MyCaffeTrainerDual.Dispose ( bool disposing )

protected

Clean up any resources being used.

Parameters

disposing true if managed resources should be disposed; otherwise, false.

Definition at line 14 of file MyCaffeTrainerDual.Designer.cs.

◆ get_dataset_override()

virtual DatasetDescriptor MyCaffe.trainers.MyCaffeTrainerDual.get_dataset_override	(	int	nProjectID,
		ConnectInfo	ci = `null`
	)

protectedvirtual

Returns a dataset override to use (if any) instead of the project's dataset. If there is no dataset override null is returned and the project's dataset is used.

Parameters

nProjectID	Specifies the project ID associated with the trainer (if any)
ci	Optionally, specifies the database connection information (default = null).

Definition at line 162 of file MyCaffeTrainerDual.cs.

◆ get_information()

virtual string MyCaffe.trainers.MyCaffeTrainerDual.get_information ( )

protectedvirtual

Returns information describing the specific trainer, such as the gym used, if any.

Returns: The string describing the trainer is returned.

Definition at line 171 of file MyCaffeTrainerDual.cs.

◆ get_update_snapshot()

virtual bool MyCaffe.trainers.MyCaffeTrainerDual.get_update_snapshot	(	out int	nIteration,
		out double	dfAccuracy
	)

protectedvirtual

Returns true when the training is ready for a snap-shot, false otherwise.

Parameters

nIteration	Specifies the current iteration.
dfAccuracy	Specifies the current rewards.

Definition at line 358 of file MyCaffeTrainerDual.cs.

◆ getData()

virtual bool MyCaffe.trainers.MyCaffeTrainerDual.getData ( GetDataArgs e )

protectedvirtual

Override called by the OnGetData event fired by the Trainer to retrieve a new set of observation collections making up a set of experiences.

Parameters

e	Specifies the getData argments used to return the new observations.

Returns: A value of true is returned when data is retrieved.

Definition at line 330 of file MyCaffeTrainerDual.cs.

◆ GetDatasetOverride()

DatasetDescriptor MyCaffe.trainers.MyCaffeTrainerDual.GetDatasetOverride	(	int	nProjectID,
		ConnectInfo	ci = `null`
	)

Returns a dataset override to use (if any) instead of the project's dataset. If there is no dataset override null is returned and the project's dataset is used.

Parameters

nProjectID	Specifies the project ID associated with the trainer (if any)
ci	Optionally, specifies the database connection information (default = null).

Implements MyCaffe.trainers.IXMyCaffeCustomTrainer.

Definition at line 437 of file MyCaffeTrainerDual.cs.

◆ GetProperty()

double MyCaffe.trainers.MyCaffeTrainerDual.GetProperty ( string strProp )

Return a property value from the trainer.

Parameters

strProp Specifies the name of property to retrieve.

Returns: The property value is returned.

Implements MyCaffe.trainers.IXMyCaffeCustomTrainer.

Definition at line 719 of file MyCaffeTrainerDual.cs.

◆ GetUpdateSnapshot()

bool MyCaffe.trainers.MyCaffeTrainerDual.GetUpdateSnapshot	(	out int	nIteration,
		out double	dfAccuracy
	)

Returns true when the training is ready for a snap-shot, false otherwise.

Parameters

nIteration	Specifies the current iteration.
dfAccuracy	Specifies the current rewards.

Implements MyCaffe.trainers.IXMyCaffeCustomTrainer.

Definition at line 426 of file MyCaffeTrainerDual.cs.

◆ initialize()

virtual void MyCaffe.trainers.MyCaffeTrainerDual.initialize ( InitializeArgs e )

protectedvirtual

Override called by the Initialize method of the trainer.

When providing a new trainer, this method is not used.

Parameters

e	Specifies the initialization arguments.

Definition at line 314 of file MyCaffeTrainerDual.cs.

◆ Initialize()

void MyCaffe.trainers.MyCaffeTrainerDual.Initialize	(	string	strProperties,
		IXMyCaffeCustomTrainerCallback	icallback
	)

Initializes a new custom trainer by loading the key-value pair of properties into the property set.

Parameters

strProperties	Specifies the key-value pair of properties each separated by ';'. For example the expected format is 'key1'='value1';'key2'='value2';...
icallback	Specifies the parent callback.

Implements MyCaffe.trainers.IXMyCaffeCustomTrainer.

Definition at line 495 of file MyCaffeTrainerDual.cs.

◆ OnConvertOutput()

void MyCaffe.trainers.MyCaffeTrainerDual.OnConvertOutput ( ConvertOutputArgs e )

The OnConvertOutput callback fires from within the Run method and is used to convert the network output into its native format.

Parameters

e	Specifies the event arguments.

Implements MyCaffe.trainers.IxTrainerCallbackRNN.

Definition at line 651 of file MyCaffeTrainerDual.cs.

◆ OnGetData()

void MyCaffe.trainers.MyCaffeTrainerDual.OnGetData ( GetDataArgs e )

The OnGetData callback fires from within the Train method and is used to get a new observation data.

Implements MyCaffe.trainers.IxTrainerCallback.

Definition at line 642 of file MyCaffeTrainerDual.cs.

◆ OnInitialize()

void MyCaffe.trainers.MyCaffeTrainerDual.OnInitialize ( InitializeArgs e )

The OnIntialize callback fires when initializing the trainer.

Implements MyCaffe.trainers.IxTrainerCallback.

Definition at line 626 of file MyCaffeTrainerDual.cs.

◆ OnShutdown()

void MyCaffe.trainers.MyCaffeTrainerDual.OnShutdown ( )

The OnShutdown callback fires when shutting down the trainer.

Implements MyCaffe.trainers.IxTrainerCallback.

Definition at line 634 of file MyCaffeTrainerDual.cs.

◆ OnTestAccuracyUpdate()

void MyCaffe.trainers.MyCaffeTrainerDual.OnTestAccuracyUpdate ( TestAccuracyUpdateArgs e )

The OnTestAccuracyUpdate callback fires from within the Run method and is used to give the recipient the chance to determine whether the label detected is correct or not.

Parameters

e	Specifies the argument sent with the callback.

Implements MyCaffe.trainers.IxTrainerCallbackRNN.

Definition at line 660 of file MyCaffeTrainerDual.cs.

◆ OnUpdateStatus()

void MyCaffe.trainers.MyCaffeTrainerDual.OnUpdateStatus ( GetStatusArgs e )

The OnGetStatus callback fires on each iteration within the Train method.

Implements MyCaffe.trainers.IxTrainerCallback.

Definition at line 668 of file MyCaffeTrainerDual.cs.

◆ OnWait()

void MyCaffe.trainers.MyCaffeTrainerDual.OnWait ( WaitArgs e )

The OnWait callback fires when waiting for a shutdown.

Implements MyCaffe.trainers.IxTrainerCallback.

Definition at line 709 of file MyCaffeTrainerDual.cs.

◆ openUi()

virtual void MyCaffe.trainers.MyCaffeTrainerDual.openUi ( )

protectedvirtual

Called by OpenUi, override this when a UI (via WCF) should be displayed.

Definition at line 375 of file MyCaffeTrainerDual.cs.

◆ OpenUi()

void MyCaffe.trainers.MyCaffeTrainerDual.OpenUi ( )

Open the user interface for the trainer, of one exists.

Implements MyCaffe.trainers.IXMyCaffeCustomTrainer.

Definition at line 843 of file MyCaffeTrainerDual.cs.

◆ preloaddata()

virtual BucketCollection MyCaffe.trainers.MyCaffeTrainerDual.preloaddata	(	Log	log,
		CancelEvent	evtCancel,
		int	nProjectID,
		PropertySet	propertyOverride = `null`,
		ConnectInfo	ci = `null`
	)

protectedvirtual

The preloaddata method gives the custom trainer an opportunity to pre-load any data.

Parameters

log	Specifies the output log to use.
evtCancel	Specifies the cancel event.
nProjectID	Specifies the project ID if any.
propertyOverride	Optionally, specifies the properites to override those already specified during initialization (default = null).
ci	Optionally, specifies the database connection information (default = null).

Returns: When data is pre-loaded the discovered vocabulary is returned as a bucket collection.

Definition at line 388 of file MyCaffeTrainerDual.cs.

◆ Run()

byte[] MyCaffe.trainers.MyCaffeTrainerDual.Run	(	Component	mycaffe,
		int	nN,
		out string	type
	)

Run the network using the run technique implemented by this trainer.

Parameters

mycaffe	Specifies an instance to the MyCaffeControl component.
nN	Specifies the number of samples to run.
type	Specifies the output data type returned as a raw byte stream.

Returns: The run results are returned in the same native type as that of the CustomQuery used.

Implements MyCaffe.trainers.IXMyCaffeCustomTrainerRL.

Definition at line 878 of file MyCaffeTrainerDual.cs.

◆ shutdown()

virtual void MyCaffe.trainers.MyCaffeTrainerDual.shutdown ( )

protectedvirtual

Override called from within the CleanUp method.

Definition at line 321 of file MyCaffeTrainerDual.cs.

◆ Test()

void MyCaffe.trainers.MyCaffeTrainerDual.Test	(	Component	mycaffe,
		int	nIterationOverride,
		ITERATOR_TYPE	type = `ITERATOR_TYPE.ITERATION`
	)

Create a new trainer and use it to run a test cycle using the current 'stage' = RNN or RL.

Parameters

mycaffe	Specifies the MyCaffeControl to use.
nIterationOverride	Specifies the iterations to run if greater than zero.
type	Specifies the type of iterator to use.

Implements MyCaffe.trainers.IXMyCaffeCustomTrainer.

Definition at line 590 of file MyCaffeTrainerDual.cs.

◆ testAccuracyUpdate()

virtual void MyCaffe.trainers.MyCaffeTrainerDual.testAccuracyUpdate ( TestAccuracyUpdateArgs e )

protectedvirtual

Override called by the OnTestAccuracyUpdate event fired from within the Run method and is used to give the recipient the chance to determine whether the label detected is correct or not.

Parameters

e	Specifies the argument sent with the callback.

Definition at line 349 of file MyCaffeTrainerDual.cs.

◆ Train()

void MyCaffe.trainers.MyCaffeTrainerDual.Train	(	Component	mycaffe,
		int	nIterationOverride,
		ITERATOR_TYPE	type = `ITERATOR_TYPE.ITERATION`,
		TRAIN_STEP	step = `TRAIN_STEP.NONE`
	)

Create a new trainer and use it to run a training cycle using the current 'stage' = RNN or RL.

Parameters

mycaffe	Specifies the MyCaffeControl to use.
nIterationOverride	Specifies the iterations to run if greater than zero.
type	Specifies the type of iterator to use.
step	Optionally, specifies whether or not to step the training for debugging (default = NONE).

Implements MyCaffe.trainers.IXMyCaffeCustomTrainer.

Definition at line 609 of file MyCaffeTrainerDual.cs.

Member Data Documentation

◆ m_dsCi

ConnectInfo MyCaffe.trainers.MyCaffeTrainerDual.m_dsCi = null

protected

Optionally, specifies the dataset connection info, or null.

Definition at line 74 of file MyCaffeTrainerDual.cs.

◆ m_nProjectID

int MyCaffe.trainers.MyCaffeTrainerDual.m_nProjectID = 0

protected

Specifies the project ID of the project held by the instance of MyCaffe.

Definition at line 70 of file MyCaffeTrainerDual.cs.

◆ m_properties

PropertySet MyCaffe.trainers.MyCaffeTrainerDual.m_properties = null

protected

Specifies the properties parsed from the key-value pair passed to the Initialize method.

Definition at line 66 of file MyCaffeTrainerDual.cs.

◆ m_random

CryptoRandom MyCaffe.trainers.MyCaffeTrainerDual.m_random = new CryptoRandom()

protected

Random number generator used to get initial actions, etc.

Definition at line 62 of file MyCaffeTrainerDual.cs.

Property Documentation

◆ category

virtual TRAINING_CATEGORY MyCaffe.trainers.MyCaffeTrainerDual.category

getprotected

Override when using a training method other than the REINFORCEMENT method (the default).

Definition at line 151 of file MyCaffeTrainerDual.cs.

◆ ExplorationRate

double MyCaffe.trainers.MyCaffeTrainerDual.ExplorationRate

get

Returns the current exploration rate.

Definition at line 819 of file MyCaffeTrainerDual.cs.

◆ GlobalEpisodeCount

int MyCaffe.trainers.MyCaffeTrainerDual.GlobalEpisodeCount

get

Returns the global episode count.

Definition at line 803 of file MyCaffeTrainerDual.cs.

◆ GlobalEpisodeMax

int MyCaffe.trainers.MyCaffeTrainerDual.GlobalEpisodeMax

get

Returns the maximum global episode count.

Definition at line 811 of file MyCaffeTrainerDual.cs.

◆ GlobalIteration

int MyCaffe.trainers.MyCaffeTrainerDual.GlobalIteration

get

Returns the global iteration.

Definition at line 795 of file MyCaffeTrainerDual.cs.

◆ GlobalLoss

double MyCaffe.trainers.MyCaffeTrainerDual.GlobalLoss

get

Return the global loss.

Definition at line 787 of file MyCaffeTrainerDual.cs.

◆ GlobalRewards

double? MyCaffe.trainers.MyCaffeTrainerDual.GlobalRewards

get

Returns the global rewards based on the reward type specified by the 'RewardType' property.

The reward type can be one of the following: 'VAL' - report the global reward value. 'AVE' - report the global reward averaged over all threads. 'MAX' - report maximum global rewards (default)

Definition at line 758 of file MyCaffeTrainerDual.cs.

◆ ImmediateRewards

double MyCaffe.trainers.MyCaffeTrainerDual.ImmediateRewards

get

Returns the immediate rewards for the current training cycle as opposed to the averaged rewards.

Definition at line 779 of file MyCaffeTrainerDual.cs.

◆ Information

string MyCaffe.trainers.MyCaffeTrainerDual.Information

get

Returns information describing the trainer.

Definition at line 835 of file MyCaffeTrainerDual.cs.

◆ IsRunningSupported

bool MyCaffe.trainers.MyCaffeTrainerDual.IsRunningSupported

get

Returns whether or not Running is supported.

Definition at line 461 of file MyCaffeTrainerDual.cs.

◆ IsTestingSupported

bool MyCaffe.trainers.MyCaffeTrainerDual.IsTestingSupported

get

Returns whether or not Testing is supported.

Definition at line 453 of file MyCaffeTrainerDual.cs.

◆ IsTrainingSupported

bool MyCaffe.trainers.MyCaffeTrainerDual.IsTrainingSupported

get

Returns whether or not Training is supported.

Definition at line 445 of file MyCaffeTrainerDual.cs.

◆ name

virtual string MyCaffe.trainers.MyCaffeTrainerDual.name

getprotected

Overriden to give the actual name of the custom trainer.

Definition at line 143 of file MyCaffeTrainerDual.cs.

◆ Name

string MyCaffe.trainers.MyCaffeTrainerDual.Name

get

Returns the name of the custom trainer. This method calls the 'name' override.

Definition at line 408 of file MyCaffeTrainerDual.cs.

◆ OptimalSelectionRate

double MyCaffe.trainers.MyCaffeTrainerDual.OptimalSelectionRate

get

Returns the rate of selection from the optimal set with the highest reward (this setting is optional, default = 0).

Definition at line 827 of file MyCaffeTrainerDual.cs.

◆ Stage

Stage MyCaffe.trainers.MyCaffeTrainerDual.Stage

get

Returns the stage under which the trainer is running based on the trainer type.

Definition at line 400 of file MyCaffeTrainerDual.cs.

◆ TrainingCategory

TRAINING_CATEGORY MyCaffe.trainers.MyCaffeTrainerDual.TrainingCategory

get

Returns the training category of the custom trainer (default = REINFORCEMENT).

Definition at line 416 of file MyCaffeTrainerDual.cs.

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

C:/Data/Data/SS_Projects/Intelligence/GitHub/MyCaffe/MyCaffe.trainers/MyCaffeTrainerDual.cs
C:/Data/Data/SS_Projects/Intelligence/GitHub/MyCaffe/MyCaffe.trainers/MyCaffeTrainerDual.Designer.cs

Public Member Functions

Protected Member Functions

Protected Attributes

Properties

Detailed Description

Constructor & Destructor Documentation

◆ MyCaffeTrainerDual() [1/2]

◆ MyCaffeTrainerDual() [2/2]

Member Function Documentation

◆ CleanUp()

◆ convertOutput()

◆ create_trainerD()

◆ create_trainerF()

◆ dispose()

◆ Dispose()

◆ get_dataset_override()

◆ get_information()

◆ get_update_snapshot()

◆ getData()

◆ GetDatasetOverride()

◆ GetProperty()

◆ GetUpdateSnapshot()

◆ initialize()

◆ Initialize()

◆ OnConvertOutput()

◆ OnGetData()

◆ OnInitialize()

◆ OnShutdown()

◆ OnTestAccuracyUpdate()

◆ OnUpdateStatus()

◆ OnWait()

◆ openUi()

◆ OpenUi()

◆ preloaddata()

◆ Run()

◆ shutdown()

◆ Test()

◆ testAccuracyUpdate()

◆ Train()

Member Data Documentation

◆ m_dsCi

◆ m_nProjectID

◆ m_properties

◆ m_random

Property Documentation

◆ category

◆ ExplorationRate

◆ GlobalEpisodeCount

◆ GlobalEpisodeMax

◆ GlobalIteration

◆ GlobalLoss

◆ GlobalRewards

◆ ImmediateRewards

◆ Information

◆ IsRunningSupported

◆ IsTestingSupported

◆ IsTrainingSupported

◆ name

◆ Name

◆ OptimalSelectionRate

◆ Stage

◆ TrainingCategory