protected abstract static class ConvolutionLayer.BaseConvBuilder<T extends ConvolutionLayer.BaseConvBuilder<T>> extends FeedForwardLayer.Builder<T>
Modifier and Type | Field and Description |
---|---|
protected ConvolutionMode |
convolutionMode |
protected ConvolutionLayer.AlgoMode |
cudnnAlgoMode |
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, learningRatePolicy, learningRateSchedule, momentum, momentumAfter, rho, rmsDecay, updater, weightInit
Modifier | Constructor and Description |
---|---|
protected |
BaseConvBuilder() |
protected |
BaseConvBuilder(int... kernelSize) |
protected |
BaseConvBuilder(int[] kernelSize,
int[] stride) |
protected |
BaseConvBuilder(int[] kernelSize,
int[] stride,
int[] padding) |
Modifier and Type | Method and Description |
---|---|
T |
convolutionMode(ConvolutionMode convolutionMode)
Set the convolution mode for the Convolution layer.
|
T |
cudnnAlgoMode(ConvolutionLayer.AlgoMode cudnnAlgoMode)
Defaults to "PREFER_FASTEST", but "NO_WORKSPACE" uses less memory.
|
nIn, nOut
activation, activation, activation, adamMeanDecay, adamVarDecay, biasInit, biasLearningRate, build, dist, dropOut, epsilon, gradientNormalization, gradientNormalizationThreshold, l1, l1Bias, l2, l2Bias, learningRate, learningRateDecayPolicy, learningRateSchedule, momentum, momentumAfter, name, rho, rmsDecay, updater, weightInit
protected ConvolutionMode convolutionMode
protected int[] kernelSize
protected int[] stride
protected int[] padding
protected ConvolutionLayer.AlgoMode cudnnAlgoMode
protected BaseConvBuilder(int[] kernelSize, int[] stride, int[] padding)
protected BaseConvBuilder(int[] kernelSize, int[] stride)
protected BaseConvBuilder(int... kernelSize)
protected BaseConvBuilder()
public T convolutionMode(ConvolutionMode convolutionMode)
ConvolutionMode
for more detailsconvolutionMode
- Convolution mode for layerpublic T cudnnAlgoMode(ConvolutionLayer.AlgoMode cudnnAlgoMode)