public class TFOpLayer extends Layer
Layer.Builder<T extends Layer.Builder<T>>
constraints, iDropout, layerName
Modifier and Type | Method and Description |
---|---|
GradientNormalization |
getGradientNormalization() |
double |
getGradientNormalizationThreshold() |
LayerMemoryReport |
getMemoryReport(InputType inputType)
This is a report of the estimated memory consumption for the given layer
|
InputType |
getOutputType(int idx,
InputType inputType)
For a given type of input to this layer, what is the type of the output?
|
InputPreProcessor |
getPreProcessorForInputType(InputType inputType)
For the given type of input to this layer, what preprocessor (if any) is required?
|
List<Regularization> |
getRegularizationByParam(String paramName)
Get the regularization types (l1/l2/weight decay) for the given parameter.
|
ParamInitializer |
initializer() |
Layer |
instantiate(NeuralNetConfiguration conf,
Collection<TrainingListener> trainingListeners,
int layerIndex,
INDArray layerParamsView,
boolean initializeParams,
DataType networkDataType) |
boolean |
isPretrainParam(String param)
Is the specified parameter a layerwise pretraining only parameter?
|
void |
setNIn(InputType inputType,
boolean override)
Set the nIn value (number of inputs, or input channels for CNNs) based on the given input
type
|
clone, getUpdaterByParam, initializeConstraints, resetLayerDefaultConfig, setDataType
equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
getLayerName
public ParamInitializer initializer()
initializer
in class Layer
public InputPreProcessor getPreProcessorForInputType(InputType inputType)
Layer
InputPreProcessor
for this layer, such as a CnnToFeedForwardPreProcessor
getPreProcessorForInputType
in class Layer
inputType
- InputType to this layerpublic boolean isPretrainParam(String param)
Layer
isPretrainParam
in interface TrainingConfig
isPretrainParam
in class Layer
param
- Parameter name/keypublic InputType getOutputType(int idx, InputType inputType)
Layer
getOutputType
in class Layer
idx
- Index of the layerinputType
- Type of input for the layerpublic void setNIn(InputType inputType, boolean override)
Layer
public GradientNormalization getGradientNormalization()
public Layer instantiate(NeuralNetConfiguration conf, Collection<TrainingListener> trainingListeners, int layerIndex, INDArray layerParamsView, boolean initializeParams, DataType networkDataType)
instantiate
in class Layer
public double getGradientNormalizationThreshold()
public List<Regularization> getRegularizationByParam(String paramName)
Layer
getRegularizationByParam
in interface TrainingConfig
getRegularizationByParam
in class Layer
paramName
- Parameter name ("W", "b" etc)public LayerMemoryReport getMemoryReport(InputType inputType)
Layer
getMemoryReport
in class Layer
inputType
- Input type to the layer. Memory consumption is often a function of the input
typeCopyright © 2020. All rights reserved.