Class Subsampling3DLayer.Builder
- java.lang.Object
-
- org.deeplearning4j.nn.conf.layers.Layer.Builder<T>
-
- org.deeplearning4j.nn.conf.layers.Subsampling3DLayer.BaseSubsamplingBuilder<Subsampling3DLayer.Builder>
-
- org.deeplearning4j.nn.conf.layers.Subsampling3DLayer.Builder
-
- Enclosing class:
- Subsampling3DLayer
public static class Subsampling3DLayer.Builder extends Subsampling3DLayer.BaseSubsamplingBuilder<Subsampling3DLayer.Builder>
-
-
Field Summary
Fields Modifier and Type Field Description protected Convolution3D.DataFormat
dataFormat
The data format for input and output activations.
NCDHW: activations (in/out) should have shape [minibatch, channels, depth, height, width]
NDHWC: activations (in/out) should have shape [minibatch, depth, height, width, channels]-
Fields inherited from class org.deeplearning4j.nn.conf.layers.Subsampling3DLayer.BaseSubsamplingBuilder
convolutionMode, cudnnAllowFallback, dilation, kernelSize, padding, poolingType, stride
-
Fields inherited from class org.deeplearning4j.nn.conf.layers.Layer.Builder
allParamConstraints, biasConstraints, iDropout, layerName, weightConstraints
-
-
Constructor Summary
Constructors Constructor Description Builder(int... kernelSize)
Builder(int[] kernelSize, int[] stride)
Builder(int[] kernelSize, int[] stride, int[] padding)
Builder(PoolingType poolingType)
Builder(PoolingType poolingType, int[] kernelSize)
Builder(PoolingType poolingType, int[] kernelSize, int[] stride, int[] padding)
Builder(Subsampling3DLayer.PoolingType poolingType)
Builder(Subsampling3DLayer.PoolingType poolingType, int[] kernelSize)
Builder(Subsampling3DLayer.PoolingType poolingType, int[] kernelSize, int[] stride)
Builder(Subsampling3DLayer.PoolingType poolingType, int[] kernelSize, int[] stride, int[] padding)
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description Subsampling3DLayer
build()
Subsampling3DLayer.Builder
dataFormat(Convolution3D.DataFormat dataFormat)
The data format for input and output activations.
NCDHW: activations (in/out) should have shape [minibatch, channels, depth, height, width]
NDHWC: activations (in/out) should have shape [minibatch, depth, height, width, channels]Subsampling3DLayer.Builder
kernelSize(int... kernelSize)
Kernel sizeSubsampling3DLayer.Builder
padding(int... padding)
Paddingvoid
setDilation(int... dilation)
Dilationvoid
setKernelSize(int... kernelSize)
void
setPadding(int... padding)
Paddingvoid
setStride(int... stride)
StrideSubsampling3DLayer.Builder
stride(int... stride)
Stride-
Methods inherited from class org.deeplearning4j.nn.conf.layers.Subsampling3DLayer.BaseSubsamplingBuilder
convolutionMode, cudnnAllowFallback, dilation, helperAllowFallback, poolingType, poolingType, setConvolutionMode
-
Methods inherited from class org.deeplearning4j.nn.conf.layers.Layer.Builder
constrainAllParameters, constrainBias, constrainWeights, dropOut, dropOut, name
-
-
-
-
Field Detail
-
dataFormat
protected Convolution3D.DataFormat dataFormat
The data format for input and output activations.
NCDHW: activations (in/out) should have shape [minibatch, channels, depth, height, width]
NDHWC: activations (in/out) should have shape [minibatch, depth, height, width, channels]
-
-
Constructor Detail
-
Builder
public Builder(Subsampling3DLayer.PoolingType poolingType, int[] kernelSize, int[] stride)
-
Builder
public Builder(Subsampling3DLayer.PoolingType poolingType, int[] kernelSize)
-
Builder
public Builder(Subsampling3DLayer.PoolingType poolingType, int[] kernelSize, int[] stride, int[] padding)
-
Builder
public Builder(PoolingType poolingType, int[] kernelSize)
-
Builder
public Builder(PoolingType poolingType, int[] kernelSize, int[] stride, int[] padding)
-
Builder
public Builder(int[] kernelSize, int[] stride, int[] padding)
-
Builder
public Builder(int[] kernelSize, int[] stride)
-
Builder
public Builder(int... kernelSize)
-
Builder
public Builder(Subsampling3DLayer.PoolingType poolingType)
-
Builder
public Builder(PoolingType poolingType)
-
-
Method Detail
-
kernelSize
public Subsampling3DLayer.Builder kernelSize(int... kernelSize)
Kernel size- Parameters:
kernelSize
- kernel size in height and width dimensions
-
stride
public Subsampling3DLayer.Builder stride(int... stride)
Stride- Parameters:
stride
- stride in height and width dimensions
-
padding
public Subsampling3DLayer.Builder padding(int... padding)
Padding- Parameters:
padding
- padding in the height and width dimensions
-
dataFormat
public Subsampling3DLayer.Builder dataFormat(Convolution3D.DataFormat dataFormat)
The data format for input and output activations.
NCDHW: activations (in/out) should have shape [minibatch, channels, depth, height, width]
NDHWC: activations (in/out) should have shape [minibatch, depth, height, width, channels]- Parameters:
dataFormat
- Data format to use for activations
-
build
public Subsampling3DLayer build()
- Specified by:
build
in classLayer.Builder<Subsampling3DLayer.Builder>
-
setKernelSize
public void setKernelSize(int... kernelSize)
-
setStride
public void setStride(int... stride)
Stride- Parameters:
stride
- stride in height and width dimensions
-
setPadding
public void setPadding(int... padding)
Padding- Parameters:
padding
- padding in the height and width dimensions
-
setDilation
public void setDilation(int... dilation)
Dilation- Overrides:
setDilation
in classSubsampling3DLayer.BaseSubsamplingBuilder<Subsampling3DLayer.Builder>
- Parameters:
dilation
- padding in the height and width dimensions
-
-