Class DropConnect
- java.lang.Object
-
- org.deeplearning4j.nn.conf.weightnoise.DropConnect
-
- All Implemented Interfaces:
Serializable
,Cloneable
,IWeightNoise
public class DropConnect extends Object implements IWeightNoise
- See Also:
- Serialized Form
-
-
Constructor Summary
Constructors Constructor Description DropConnect(double weightRetainProbability)
DropConnect(double weightRetainProbability, boolean applyToBiases)
DropConnect(ISchedule weightRetainProbSchedule)
DropConnect(ISchedule weightRetainProbSchedule, boolean applyToBiases)
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description DropConnect
clone()
INDArray
getParameter(Layer layer, String paramKey, int iteration, int epoch, boolean train, LayerWorkspaceMgr workspaceMgr)
Get the parameter, after applying weight noise
-
-
-
Constructor Detail
-
DropConnect
public DropConnect(double weightRetainProbability)
- Parameters:
weightRetainProbability
- Probability of retaining a weight
-
DropConnect
public DropConnect(double weightRetainProbability, boolean applyToBiases)
- Parameters:
weightRetainProbability
- Probability of retaining a weightapplyToBiases
- If true: apply to biases (default: weights only)
-
DropConnect
public DropConnect(ISchedule weightRetainProbSchedule)
- Parameters:
weightRetainProbSchedule
- Probability (schedule) of retaining a weight
-
DropConnect
public DropConnect(ISchedule weightRetainProbSchedule, boolean applyToBiases)
- Parameters:
weightRetainProbSchedule
- Probability (schedule) of retaining a weightapplyToBiases
- If true: apply to biases (default: weights only)
-
-
Method Detail
-
getParameter
public INDArray getParameter(Layer layer, String paramKey, int iteration, int epoch, boolean train, LayerWorkspaceMgr workspaceMgr)
Description copied from interface:IWeightNoise
Get the parameter, after applying weight noise- Specified by:
getParameter
in interfaceIWeightNoise
- Parameters:
layer
- Layer to get the parameter forparamKey
- Parameter keyiteration
- Iteration numberepoch
- Epoch numbertrain
- If true: training. False: at test time- Returns:
- Parameter, after applying weight noise
-
clone
public DropConnect clone()
- Specified by:
clone
in interfaceIWeightNoise
- Overrides:
clone
in classObject
-
-