Uses of Class
org.deeplearning4j.nn.conf.layers.SeparableConvolution2D.Builder

Packages that use SeparableConvolution2D.Builder

Package	Description
org.deeplearning4j.nn.conf.layers

Uses of SeparableConvolution2D.Builder in org.deeplearning4j.nn.conf.layers

Methods in org.deeplearning4j.nn.conf.layers that return SeparableConvolution2D.Builder

Modifier and Type	Method and Description
SeparableConvolution2D.Builder	SeparableConvolution2D.Builder.constrainPointWise(LayerConstraint... constraints) Set constraints to be applied to the point-wise convolution weight parameters of this layer.
SeparableConvolution2D.Builder	SeparableConvolution2D.Builder.dataFormat(CNN2DFormat format) Set the data format for the CNN activations - NCHW (channels first) or NHWC (channels last).
SeparableConvolution2D.Builder	SeparableConvolution2D.Builder.depthMultiplier(int depthMultiplier) Set channels multiplier of channels-wise step in separable convolution
SeparableConvolution2D.Builder	SeparableConvolution2D.Builder.kernelSize(int... kernelSize) Size of the convolution rows/columns (height/width)
SeparableConvolution2D.Builder	SeparableConvolution2D.Builder.padding(int... padding) Padding - rows/columns (height/width)
SeparableConvolution2D.Builder	SeparableConvolution2D.Builder.stride(int... stride) Stride of the convolution rows/columns (height/width)

Constructors in org.deeplearning4j.nn.conf.layers with parameters of type SeparableConvolution2D.Builder

Constructor and Description
SeparableConvolution2D(SeparableConvolution2D.Builder builder) SeparableConvolution2D layer 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 channels The builder specifies the filter/kernel size, the stride and padding The pooling layer takes the kernel size