public class ConvolutionLayer extends FeedForwardLayer
Modifier and Type | Class and Description |
---|---|
static class |
ConvolutionLayer.AlgoMode |
protected static class |
ConvolutionLayer.BaseConvBuilder<T extends ConvolutionLayer.BaseConvBuilder<T>> |
static class |
ConvolutionLayer.Builder |
Modifier and Type | Field and Description |
---|---|
protected ConvolutionMode |
convolutionMode |
protected ConvolutionLayer.AlgoMode |
cudnnAlgoMode
Defaults to "PREFER_FASTEST", but "NO_WORKSPACE" uses less memory.
|
protected int[] |
kernelSize |
protected int[] |
padding |
protected int[] |
stride |
nIn, nOut
activationFn, adamMeanDecay, adamVarDecay, biasInit, biasLearningRate, dist, dropOut, epsilon, gradientNormalization, gradientNormalizationThreshold, l1, l1Bias, l2, l2Bias, layerName, learningRate, learningRateSchedule, momentum, momentumSchedule, rho, rmsDecay, updater, weightInit
Modifier | Constructor and Description |
---|---|
protected |
ConvolutionLayer(ConvolutionLayer.BaseConvBuilder<?> builder)
ConvolutionLayer
nIn in the input layer is the number of channels
nOut is the number of filters to be used in the net or in other words the depth
The builder specifies the filter/kernel size, the stride and padding
The pooling layer takes the kernel size
|
Modifier and Type | Method and Description |
---|---|
ConvolutionLayer |
clone() |
double |
getL1ByParam(java.lang.String paramName)
Get the L1 coefficient for the given parameter.
|
double |
getL2ByParam(java.lang.String paramName)
Get the L2 coefficient for the given parameter.
|
double |
getLearningRateByParam(java.lang.String paramName)
Get the (initial) learning rate coefficient for the given parameter.
|
InputType |
getOutputType(int layerIndex,
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?
Returns null if no preprocessor is required, otherwise returns an appropriate InputPreProcessor
for this layer, such as a CnnToFeedForwardPreProcessor |
ParamInitializer |
initializer() |
Layer |
instantiate(NeuralNetConfiguration conf,
java.util.Collection<IterationListener> iterationListeners,
int layerIndex,
org.nd4j.linalg.api.ndarray.INDArray layerParamsView,
boolean initializeParams) |
void |
setNIn(InputType inputType,
boolean override)
Set the nIn value (number of inputs, or input depth for CNNs) based on the given input type
|
getUpdaterByParam, resetLayerDefaultConfig
protected ConvolutionMode convolutionMode
protected int[] kernelSize
protected int[] stride
protected int[] padding
protected ConvolutionLayer.AlgoMode cudnnAlgoMode
protected ConvolutionLayer(ConvolutionLayer.BaseConvBuilder<?> builder)
public ConvolutionLayer clone()
public Layer instantiate(NeuralNetConfiguration conf, java.util.Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)
instantiate
in class Layer
public ParamInitializer initializer()
initializer
in class Layer
public InputType getOutputType(int layerIndex, InputType inputType)
Layer
getOutputType
in class FeedForwardLayer
layerIndex
- Index of the layerinputType
- Type of input for the layerpublic void setNIn(InputType inputType, boolean override)
Layer
setNIn
in class FeedForwardLayer
inputType
- Input type for this layeroverride
- If false: only set the nIn value if it's not already set. If true: set it regardless of whether it's
already set or not.public InputPreProcessor getPreProcessorForInputType(InputType inputType)
Layer
InputPreProcessor
for this layer, such as a CnnToFeedForwardPreProcessor
getPreProcessorForInputType
in class FeedForwardLayer
inputType
- InputType to this layerpublic double getL1ByParam(java.lang.String paramName)
Layer
getL1ByParam
in class FeedForwardLayer
paramName
- Parameter namepublic double getL2ByParam(java.lang.String paramName)
Layer
getL2ByParam
in class FeedForwardLayer
paramName
- Parameter namepublic double getLearningRateByParam(java.lang.String paramName)
Layer
getLearningRateByParam
in class FeedForwardLayer
paramName
- Parameter name