The SolverParameter is a parameter for the solver, specifying the train and test networks. More...

Inheritance diagram for MyCaffe.param.SolverParameter:

Public Types
enum	EvaluationType { CLASSIFICATION , DETECTION }
	Defines the evaluation method used in the SSD algorithm. More...

enum	SnapshotFormat { BINARYPROTO = 1 }
	Defines the format of each snapshot. More...

enum	SolverType { SGD = 0 , NESTEROV = 1 , ADAGRAD = 2 , RMSPROP = 3 , ADADELTA = 4 , ADAM = 5 , LBFGS = 6 , ADAMW = 7 , _MAX = 8 }
	Defines the type of solver. More...

enum	LearningRatePolicyType { FIXED , STEP , EXP , INV , MULTISTEP , POLY , SIGMOID }
	Defines the learning rate policy to use. More...

enum	RegularizationType { NONE , L1 , L2 }
	Defines the regularization type. When enabled, weight_decay is used. More...

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

SolverParameter	Clone ()
	Creates a new copy of the SolverParameter. More...

override RawProto	ToProto (string strName)
	Converts the SolverParameter into a RawProto. More...

string	DebugString ()
	Returns a debug string for the SolverParameter. More...

Public Member Functions inherited from MyCaffe.basecode.BaseParameter
	BaseParameter ()
	Constructor for the parameter. More...

virtual bool	Compare (BaseParameter p)
	Compare this parameter to another parameter. More...

Static Public Member Functions
static SolverParameter	FromProto (RawProto rp)
	Parses a new SolverParameter from a RawProto. More...

Static Public Member Functions inherited from MyCaffe.basecode.BaseParameter
static double	ParseDouble (string strVal)
	Parse double values using the US culture if the decimal separator = '.', then using the native culture, and if then lastly trying the US culture to handle prototypes containing '.' as the separator, yet parsed in a culture that does not use '.' as a decimal. More...

static bool	TryParse (string strVal, out double df)
	Parse double values using the US culture if the decimal separator = '.', then using the native culture, and if then lastly trying the US culture to handle prototypes containing '.' as the separator, yet parsed in a culture that does not use '.' as a decimal. More...

static float	ParseFloat (string strVal)
	Parse float values using the US culture if the decimal separator = '.', then using the native culture, and if then lastly trying the US culture to handle prototypes containing '.' as the separator, yet parsed in a culture that does not use '.' as a decimal. More...

static bool	TryParse (string strVal, out float f)
	Parse doufloatble values using the US culture if the decimal separator = '.', then using the native culture, and if then lastly trying the US culture to handle prototypes containing '.' as the separator, yet parsed in a culture that does not use '.' as a decimal. More...

Properties
bool	output_average_results `[getset]`
	Specifies to average loss results before they are output - this can be faster when there are a lot of results in a cycle. More...

string	custom_trainer `[getset]`
	Specifies the Name of the custom trainer (if any) - this is an optional setting used by exteral software to provide a customized training process. Each custom trainer must implement the IDnnCustomTraininer interface which contains a 'Name'property - the named returned from this property is the value set here as the 'custom_trainer'. More...

string	custom_trainer_properties `[getset]`
	Specifies the custom trainer properties (if any) - this is an optional setting used by exteral software to provide the propreties for a customized training process. More...

NetParameter	net_param `[getset]`
	Inline train net param, possibly combined with one or more test nets. More...

NetParameter	train_net_param `[getset]`
	Inline train net param, possibly combined with one or more test nets. More...

List< NetParameter >	test_net_param `[getset]`
	Inline test net params. More...

NetState	train_state `[getset]`
	The states for the train/test nets. Must be unspecified or specified once per net. More...

List< NetState >	test_state `[getset]`
	The states for the train/test nets. Must be unspecified or specified once per net. More...

List< int >	test_iter `[getset]`
	The number of iterations for each test. More...

int	test_interval `[getset]`
	The number of iterations between two testing phases. More...

bool	test_compute_loss `[getset]`
	Test the compute loss. More...

bool	test_initialization `[getset]`
	If true, run an initial test pass before the first iteration, ensuring memory availability and printing the starting value of the loss. More...

double	base_lr `[getset]`
	The base learning rate (default = 0.01). More...

int	display `[getset]`
	The number of iterations between displaying info. If display = 0, no info will be displayed. More...

int	average_loss `[getset]`
	Display the loss averaged over the last average_loss iterations. More...

int	max_iter `[getset]`
	The maximum number of iterations. More...

int	iter_size `[getset]`
	Accumulate gradients over 'iter_size' x 'batch_size' instances. More...

LearningRatePolicyType	LearningRatePolicy `[getset]`
	The learning rate decay policy. More...

string	lr_policy `[getset]`
	The learning rate decay policy. More...

double	gamma `[getset]`
	Specifies the 'gamma' parameter to compute the 'step', 'exp', 'inv', and 'sigmoid' learning policy (default = 0.1). More...

double	power `[getset]`
	The 'power' parameter to compute the learning rate. More...

double	momentum `[getset]`
	Specifies the momentum value - used by all solvers EXCEPT the 'AdaGrad' and 'RMSProp' solvers. For these latter solvers, momentum should = 0. More...

double	weight_decay `[getset]`
	Specifies the weight decay (default = 0.0005). More...

RegularizationType	Regularization `[getset]`
	Specifies the regularization type (default = L2). More...

string	regularization_type `[getset]`
	Specifies the regularization type (default = 'L2'). More...

int	stepsize `[getset]`
	The stepsize for learning rate policy 'step'. More...

List< int >	stepvalue `[getset]`
	The step values for learning rate policy 'multistep'. More...

double	clip_gradients `[getset]`
	Set clip_gradients to >= 0 to clip parameter gradients to that L2 norm, whenever their actual L2 norm is larger. More...

bool	enable_clip_gradient_status `[getset]`
	Optionally, enable status output when gradients are clipped (default = true) More...

int	snapshot `[getset]`
	Specifies the snapshot interval. More...

string	snapshot_prefix `[getset]`
	The prefix for the snapshot. More...

bool	snapshot_diff `[getset]`
	Whether to snapshot diff in the results or not. Snapshotting diff will help debugging but the final protocol buffer size will be much larger. More...

SnapshotFormat	snapshot_format `[getset]`
	The snapshot format. More...

bool	snapshot_include_weights `[getset]`
	Specifies whether or not the snapshot includes the trained weights. The default = true. More...

bool	snapshot_include_state `[getset]`
	Specifies whether or not the snapshot includes the solver state. The default = false. Including the solver state will slow down the time of each snapshot. More...

int	device_id `[getset]`
	The device id that will be used when run on the GPU. More...

long	random_seed `[getset]`
	If non-negative, the seed with which the Solver will initialize the caffe random number generator – useful for repoducible results. Otherwise (and by default) initialize using a seed derived from the system clock. More...

SolverType	type `[getset]`
	Specifies the solver type. More...

double	delta `[getset]`
	Numerical stability for RMSProp, AdaGrad, AdaDelta, Adam and AdamW solvers (default = 1e-08). More...

double	momentum2 `[getset]`
	An additional momentum property for the Adam and AdamW solvers (default = 0.999). More...

double	rms_decay `[getset]`
	Specifies the 'RMSProp' decay value used by the 'RMSProp' solver (default = 0.95). More...

double	adamw_decay `[getset]`
	Specifies the 'AdamW' detached weight decay value used by the 'AdamW' solver (default = 0.1). More...

bool	debug_info `[getset]`
	If true, print information about the state of the net that may help with debugging learning problems. More...

int	lbgfs_corrections `[getset]`
	Specifies the number of lbgfs corrections used with the L-BGFS solver. More...

bool	snapshot_after_train `[getset]`
	If false, don't save a snapshot after training finishes. More...

EvaluationType	eval_type `[getset]`
	Specifies the evaluation type to use when using Single-Shot Detection (SSD) - (default = NONE, SSD not used). More...

ApVersion	ap_version `[getset]`
	Specifies the AP Version to use for average precision when using Single-Shot Detection (SSD) - (default = INTEGRAL). More...

bool	show_per_class_result `[getset]`
	Specifies whether or not to display results per class when using Single-Shot Detection (SSD) - (default = false). More...

int	accuracy_average_window `[getset]`
	Specifies the window over which to average the accuracies (default = 0 which ignores averaging). More...

Detailed Description

The SolverParameter is a parameter for the solver, specifying the train and test networks.

Exactly one train net must be specified using one of the following fields: train_net_param, train_net, net_param, net

One or more of the test nets may be specified using any of the following fields: test_net_param, test_net, net_param, net

If more than one test net field is specified (e.g., both net and test_net are specified), they will be evaluated in the field order given above: (1) test_net_param, (2) test_net, (3) net_param/net

A test_iter must be specified for each test_net. A test_level and/or test_stage may also be specified for each test_net.

Definition at line 31 of file SolverParameter.cs.

Member Enumeration Documentation

◆ EvaluationType

enum MyCaffe.param.SolverParameter.EvaluationType

Defines the evaluation method used in the SSD algorithm.

Enumerator
CLASSIFICATION	Specifies to run a standard classification evaluation.
DETECTION	Specifies detection evaluation used in the SSD algorithm.

Definition at line 86 of file SolverParameter.cs.

◆ LearningRatePolicyType

enum MyCaffe.param.SolverParameter.LearningRatePolicyType

Defines the learning rate policy to use.

Enumerator
FIXED	Use a fixed learning rate which always returns base_lr.
STEP	Use a stepped learning rate which returns $base_lr * gamma ^ {floor{iter/step}}$
EXP	Use an exponential learning rate which returns $base_lr * gamma ^ {iter}$
INV	Use an inverse learning rate which returns $base_lr * {1 + gamma * iter}^{-power}$
MULTISTEP	Use a multi-step learning rate which is similar to INV, but allows for non-uniform steps defined by stepvalue.
POLY	Use a polynomial learning rate where the effective learning rate follows a polynomial decay, to be zero by the max_iter. Returns $base_lr * {1 - iter/max_iter}^{power}$
SIGMOID	Use a sigmoid learning rate where the effective learning rate follows a sigmoid decay. Returns $base_lr * {1/{1 + exp{-gamma * {iter - stepsize}}}}$

Definition at line 181 of file SolverParameter.cs.

◆ RegularizationType

enum MyCaffe.param.SolverParameter.RegularizationType

Defines the regularization type. When enabled, weight_decay is used.

Enumerator
NONE	Specifies to not use regularization.
L1	Specifies L1 regularization.
L2	Specifies L2 regularization.

Definition at line 216 of file SolverParameter.cs.

◆ SnapshotFormat

enum MyCaffe.param.SolverParameter.SnapshotFormat

Defines the format of each snapshot.

Enumerator
BINARYPROTO	Save snapshots in the binary prototype format.

Definition at line 101 of file SolverParameter.cs.

◆ SolverType

enum MyCaffe.param.SolverParameter.SolverType

Defines the type of solver.

Enumerator
SGD	Use Stochastic Gradient Descent solver with momentum updates weights by a linear combination of the negative gradient and the previous weight update. See also Stochastic Gradient Descent Wikipedia.
NESTEROV	Use Nesterov's accelerated gradient, similar to SGD, but error gradient is computed on the weights with added momentum. See also Lecture 6c The momentum method by Hinton, Geoffrey and Srivastava, Nitish and Swersky, Kevin, 2012. Nesterov's Accelerated Gradient and Momentum as approximations to Regularised Update Descent by Botev, Alexandar and Lever, Guy and Barber, David, 2016.
ADAGRAD	Use Gradient based optimization like SGD that tries to find rarely seen features See also Adaptive Subgradient Methods for Online Learning and Stochastic Optimization by Duchi, John and Hazan, Elad, and Singer, Yoram, 2011.
RMSPROP	Use RMS Prop gradient based optimization like SGD. See also Lecture 6e rmsprop: Divide the gradient by a running average of its recent magnitude by Tieleman and Hinton, 2012, RMSProp and equilibrated adaptive learning rates for non-convex optimization by Dauphin, Yann N. and de Vries, Harm and Chung, Junyoung and Bengio, Yoshua, 2015.
ADADELTA	Use AdaDelta gradient based optimization like SGD. See ADADELTA: An Adaptive Learning Rate Method by Zeiler, Matthew D., 2012.
ADAM	Use Adam gradient based optimization like SGD that includes 'adaptive momentum estimation' and can be thougth of as a generalization of AdaGrad. See also Adam: A Method for Stochastic Optimization by Kingma, Diederik P. and Ba, Jimmy, 2014.
LBFGS	Use the L-BFGS solver based on the implementation of minFunc by Marc Schmidt. See also minFunc by Marc Schmidt, 2005
ADAMW	Use AdamW gradient based optimization like Adam that includes a detached weight decay. See also Decoupled Weight Decay Regularization by Loshchilov, I. and Hutter, F., 2019. Adam: A Method for Stochastic Optimization by Kingma, Diederik P. and Ba, Jimmy, 2014.

Definition at line 112 of file SolverParameter.cs.

Constructor & Destructor Documentation

◆ SolverParameter()

MyCaffe.param.SolverParameter.SolverParameter ( )

The SolverParameter constructor.

Definition at line 235 of file SolverParameter.cs.

Member Function Documentation

◆ Clone()

SolverParameter MyCaffe.param.SolverParameter.Clone ( )

Creates a new copy of the SolverParameter.

Returns: A new instance of the SolverParameter is returned.

Definition at line 244 of file SolverParameter.cs.

◆ DebugString()

string MyCaffe.param.SolverParameter.DebugString ( )

Returns a debug string for the SolverParameter.

Returns: The debug string is returned.

Definition at line 1342 of file SolverParameter.cs.

◆ FromProto()

static SolverParameter MyCaffe.param.SolverParameter.FromProto ( RawProto rp )

static

Parses a new SolverParameter from a RawProto.

Parameters

rp	Specifies the RawProto representing the SolverParameter.

Returns: The new SolverParameter instance is returned.

Definition at line 1092 of file SolverParameter.cs.

◆ ToProto()

override RawProto MyCaffe.param.SolverParameter.ToProto ( string strName )

virtual

Converts the SolverParameter into a RawProto.

Parameters

strName Specifies a name given to the RawProto.

Returns: The new RawProto representing the SolverParameter is returned.

Implements MyCaffe.basecode.BaseParameter.

Definition at line 965 of file SolverParameter.cs.

Property Documentation

◆ accuracy_average_window

int MyCaffe.param.SolverParameter.accuracy_average_window

getset

Specifies the window over which to average the accuracies (default = 0 which ignores averaging).

Definition at line 954 of file SolverParameter.cs.

◆ adamw_decay

double MyCaffe.param.SolverParameter.adamw_decay

getset

Specifies the 'AdamW' detached weight decay value used by the 'AdamW' solver (default = 0.1).

Decay applied to detached weight decay.

Definition at line 877 of file SolverParameter.cs.

◆ ap_version

ApVersion MyCaffe.param.SolverParameter.ap_version

getset

Specifies the AP Version to use for average precision when using Single-Shot Detection (SSD) - (default = INTEGRAL).

Definition at line 933 of file SolverParameter.cs.

◆ average_loss

int MyCaffe.param.SolverParameter.average_loss

getset

Display the loss averaged over the last average_loss iterations.

Definition at line 423 of file SolverParameter.cs.

◆ base_lr

double MyCaffe.param.SolverParameter.base_lr

getset

The base learning rate (default = 0.01).

Definition at line 401 of file SolverParameter.cs.

◆ clip_gradients

double MyCaffe.param.SolverParameter.clip_gradients

getset

Set clip_gradients to >= 0 to clip parameter gradients to that L2 norm, whenever their actual L2 norm is larger.

Definition at line 706 of file SolverParameter.cs.

◆ custom_trainer

string MyCaffe.param.SolverParameter.custom_trainer

getset

Specifies the Name of the custom trainer (if any) - this is an optional setting used by exteral software to provide a customized training process. Each custom trainer must implement the IDnnCustomTraininer interface which contains a 'Name'property - the named returned from this property is the value set here as the 'custom_trainer'.

Definition at line 268 of file SolverParameter.cs.

◆ custom_trainer_properties

string MyCaffe.param.SolverParameter.custom_trainer_properties

getset

Specifies the custom trainer properties (if any) - this is an optional setting used by exteral software to provide the propreties for a customized training process.

Note all spaces are replaced with '~' characters to avoid parsing errors.

Definition at line 283 of file SolverParameter.cs.

◆ debug_info

bool MyCaffe.param.SolverParameter.debug_info

getset

If true, print information about the state of the net that may help with debugging learning problems.

Definition at line 889 of file SolverParameter.cs.

◆ delta

double MyCaffe.param.SolverParameter.delta

getset

Numerical stability for RMSProp, AdaGrad, AdaDelta, Adam and AdamW solvers (default = 1e-08).

Definition at line 838 of file SolverParameter.cs.

◆ device_id

int MyCaffe.param.SolverParameter.device_id

getset

The device id that will be used when run on the GPU.

Definition at line 797 of file SolverParameter.cs.

◆ display

int MyCaffe.param.SolverParameter.display

getset

The number of iterations between displaying info. If display = 0, no info will be displayed.

Definition at line 413 of file SolverParameter.cs.

◆ enable_clip_gradient_status

bool MyCaffe.param.SolverParameter.enable_clip_gradient_status

getset

Optionally, enable status output when gradients are clipped (default = true)

Definition at line 716 of file SolverParameter.cs.

◆ eval_type

EvaluationType MyCaffe.param.SolverParameter.eval_type

getset

Specifies the evaluation type to use when using Single-Shot Detection (SSD) - (default = NONE, SSD not used).

Definition at line 922 of file SolverParameter.cs.

◆ gamma

double MyCaffe.param.SolverParameter.gamma

getset

Specifies the 'gamma' parameter to compute the 'step', 'exp', 'inv', and 'sigmoid' learning policy (default = 0.1).

Definition at line 575 of file SolverParameter.cs.

◆ iter_size

int MyCaffe.param.SolverParameter.iter_size

getset

Accumulate gradients over 'iter_size' x 'batch_size' instances.

Definition at line 445 of file SolverParameter.cs.

◆ lbgfs_corrections

int MyCaffe.param.SolverParameter.lbgfs_corrections

getset

Specifies the number of lbgfs corrections used with the L-BGFS solver.

Definition at line 900 of file SolverParameter.cs.

◆ LearningRatePolicy

LearningRatePolicyType MyCaffe.param.SolverParameter.LearningRatePolicy

getset

The learning rate decay policy.

The currently implemented learning rate policies are as follows:

fixed: always return .
step: return $base_lr * gamma ^ {floor{iter / step}}$
exp: return
inv: return $base_lr * {1 + gamma * iter} ^ {-power}$
multistep: similar to step but it allows non-uniform steps defined by stepvalue.
poly: the effective learning rate follows a polynomial decay, to be zero by the max_iter. return $base_lr * {1 - iter/max_iter} ^ {power}$
sigmoid: the effective learning rate follows a sigmoid decay. return $base_lr * {1/{1 + exp{-gamma * {iter - stepsize}}}}$

where base_lr, max_iter, gamma, step, stepvalue and power are defined int the solver protocol buffer, and iter is the current iteration.

Definition at line 474 of file SolverParameter.cs.

◆ lr_policy

string MyCaffe.param.SolverParameter.lr_policy

getset

The learning rate decay policy.

The currently implemented learning rate policies are as follows:

fixed: always return base_lr.
step: return base_lr * gamma ^ (floor(iter / step))
exp: return base_lr * gamma ^ iter
inv: return base_lr * (1 + gamma * iter) ^ (-power)
multistep: similar to step but it allows non-uniform steps defined by stepvalue.
poly: the effective learning rate follows a polynomial decay, to be zero by the max_iter. return base_lr * (1 - iter/max_iter) ^ (power)
sigmoid: the effective learning rate follows a sigmoid decay. return base_lr * (1/(1 + exp(-gamma * (iter - stepsize))))

where base_lr, max_iter, gamma, step, stepvalue and power are defined int the solver protocol buffer, and iter is the current iteration.

See also: Don't Decay the Learning Rate, Increase the Batch Size by Samuel L. Smith, Pieter-Jan Kindermans, Chris Ying and Quoc V. Le, 2017.

Definition at line 564 of file SolverParameter.cs.

◆ max_iter

int MyCaffe.param.SolverParameter.max_iter

getset

The maximum number of iterations.

Definition at line 434 of file SolverParameter.cs.

◆ momentum

double MyCaffe.param.SolverParameter.momentum

getset

Specifies the momentum value - used by all solvers EXCEPT the 'AdaGrad' and 'RMSProp' solvers. For these latter solvers, momentum should = 0.

Definition at line 598 of file SolverParameter.cs.

◆ momentum2

double MyCaffe.param.SolverParameter.momentum2

getset

An additional momentum property for the Adam and AdamW solvers (default = 0.999).

Definition at line 849 of file SolverParameter.cs.

◆ net_param

NetParameter MyCaffe.param.SolverParameter.net_param

getset

Inline train net param, possibly combined with one or more test nets.

Definition at line 293 of file SolverParameter.cs.

◆ output_average_results

bool MyCaffe.param.SolverParameter.output_average_results

getset

Specifies to average loss results before they are output - this can be faster when there are a lot of results in a cycle.

Definition at line 255 of file SolverParameter.cs.

◆ power

double MyCaffe.param.SolverParameter.power

getset

The 'power' parameter to compute the learning rate.

Definition at line 586 of file SolverParameter.cs.

◆ random_seed

long MyCaffe.param.SolverParameter.random_seed

getset

If non-negative, the seed with which the Solver will initialize the caffe random number generator – useful for repoducible results. Otherwise (and by default) initialize using a seed derived from the system clock.

Definition at line 809 of file SolverParameter.cs.

◆ Regularization

RegularizationType MyCaffe.param.SolverParameter.Regularization

getset

Specifies the regularization type (default = L2).

The regularization types supported are:

L1 and L2 controlled by weight_decay.

Definition at line 623 of file SolverParameter.cs.

◆ regularization_type

string MyCaffe.param.SolverParameter.regularization_type

getset

Specifies the regularization type (default = 'L2').

The regularization types supported are:

L1 and L2 controlled by weight_decay.

Definition at line 673 of file SolverParameter.cs.

◆ rms_decay

double MyCaffe.param.SolverParameter.rms_decay

getset

Specifies the 'RMSProp' decay value used by the 'RMSProp' solver (default = 0.95).

MeanSquare(t) = rms_decay * MeanSquare(t-1) + (1 - rms_decay) * SquareGradient(t)

Definition at line 863 of file SolverParameter.cs.

◆ show_per_class_result

bool MyCaffe.param.SolverParameter.show_per_class_result

getset

Specifies whether or not to display results per class when using Single-Shot Detection (SSD) - (default = false).

Definition at line 944 of file SolverParameter.cs.

◆ snapshot

int MyCaffe.param.SolverParameter.snapshot

getset

Specifies the snapshot interval.

Definition at line 727 of file SolverParameter.cs.

◆ snapshot_after_train

bool MyCaffe.param.SolverParameter.snapshot_after_train

getset

If false, don't save a snapshot after training finishes.

Definition at line 911 of file SolverParameter.cs.

◆ snapshot_diff

bool MyCaffe.param.SolverParameter.snapshot_diff

getset

Whether to snapshot diff in the results or not. Snapshotting diff will help debugging but the final protocol buffer size will be much larger.

Definition at line 750 of file SolverParameter.cs.

◆ snapshot_format

SnapshotFormat MyCaffe.param.SolverParameter.snapshot_format

getset

The snapshot format.

Currently only the Binary Proto Buffer format is supported.

Definition at line 764 of file SolverParameter.cs.

◆ snapshot_include_state

bool MyCaffe.param.SolverParameter.snapshot_include_state

getset

Specifies whether or not the snapshot includes the solver state. The default = false. Including the solver state will slow down the time of each snapshot.

Definition at line 786 of file SolverParameter.cs.

◆ snapshot_include_weights

bool MyCaffe.param.SolverParameter.snapshot_include_weights

getset

Specifies whether or not the snapshot includes the trained weights. The default = true.

Definition at line 775 of file SolverParameter.cs.

◆ snapshot_prefix

string MyCaffe.param.SolverParameter.snapshot_prefix

getset

The prefix for the snapshot.

Definition at line 738 of file SolverParameter.cs.

◆ stepsize

int MyCaffe.param.SolverParameter.stepsize

getset

The stepsize for learning rate policy 'step'.

Definition at line 684 of file SolverParameter.cs.

◆ stepvalue

List<int> MyCaffe.param.SolverParameter.stepvalue

getset

The step values for learning rate policy 'multistep'.

Definition at line 695 of file SolverParameter.cs.

◆ test_compute_loss

bool MyCaffe.param.SolverParameter.test_compute_loss

getset

Test the compute loss.

Definition at line 379 of file SolverParameter.cs.

◆ test_initialization

bool MyCaffe.param.SolverParameter.test_initialization

getset

If true, run an initial test pass before the first iteration, ensuring memory availability and printing the starting value of the loss.

Definition at line 391 of file SolverParameter.cs.

◆ test_interval

int MyCaffe.param.SolverParameter.test_interval

getset

The number of iterations between two testing phases.

Definition at line 369 of file SolverParameter.cs.

◆ test_iter

List<int> MyCaffe.param.SolverParameter.test_iter

getset

The number of iterations for each test.

Definition at line 358 of file SolverParameter.cs.

◆ test_net_param

List<NetParameter> MyCaffe.param.SolverParameter.test_net_param

getset

Inline test net params.

Definition at line 313 of file SolverParameter.cs.

◆ test_state

List<NetState> MyCaffe.param.SolverParameter.test_state

getset

The states for the train/test nets. Must be unspecified or specified once per net.

By default, all states will have solver = true; train_state will have phase = TRAIN, and all test_state's will have phase = TESET. Other defaults are set according to NetState defaults.

Definition at line 347 of file SolverParameter.cs.

◆ train_net_param

NetParameter MyCaffe.param.SolverParameter.train_net_param

getset

Inline train net param, possibly combined with one or more test nets.

Definition at line 303 of file SolverParameter.cs.

◆ train_state

NetState MyCaffe.param.SolverParameter.train_state

getset

The states for the train/test nets. Must be unspecified or specified once per net.

By default, all states will have solver = true; train_state will have phase = TRAIN, and all test_state's will have phase = TESET. Other defaults are set according to NetState defaults.

Definition at line 330 of file SolverParameter.cs.

◆ type

SolverType MyCaffe.param.SolverParameter.type

getset

Specifies the solver type.

Definition at line 827 of file SolverParameter.cs.

◆ weight_decay

double MyCaffe.param.SolverParameter.weight_decay

getset

Specifies the weight decay (default = 0.0005).

Definition at line 608 of file SolverParameter.cs.

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

C:/Data/Data/SS_Projects/Intelligence/GitHub/MyCaffe/MyCaffe/param/SolverParameter.cs

Public Types

Public Member Functions

Static Public Member Functions

Properties

Detailed Description

Member Enumeration Documentation

◆ EvaluationType

◆ LearningRatePolicyType

◆ RegularizationType

◆ SnapshotFormat

◆ SolverType

Constructor & Destructor Documentation

◆ SolverParameter()

Member Function Documentation

◆ Clone()

◆ DebugString()

◆ FromProto()

◆ ToProto()

Property Documentation

◆ accuracy_average_window

◆ adamw_decay

◆ ap_version

◆ average_loss

◆ base_lr

◆ clip_gradients

◆ custom_trainer

◆ custom_trainer_properties

◆ debug_info

◆ delta

◆ device_id

◆ display

◆ enable_clip_gradient_status

◆ eval_type

◆ gamma

◆ iter_size

◆ lbgfs_corrections

◆ LearningRatePolicy

◆ lr_policy

◆ max_iter

◆ momentum

◆ momentum2

◆ net_param

◆ output_average_results

◆ power

◆ random_seed

◆ Regularization

◆ regularization_type

◆ rms_decay

◆ show_per_class_result

◆ snapshot

◆ snapshot_after_train

◆ snapshot_diff

◆ snapshot_format

◆ snapshot_include_state

◆ snapshot_include_weights

◆ snapshot_prefix

◆ stepsize

◆ stepvalue

◆ test_compute_loss

◆ test_initialization

◆ test_interval

◆ test_iter

◆ test_net_param

◆ test_state

◆ train_net_param

◆ train_state

◆ type

◆ weight_decay