Package | Description |
---|---|
org.deeplearning4j.nn.conf.layers |
Modifier and Type | Method and Description |
---|---|
Convolution3D.Builder |
Convolution3D.Builder.convolutionMode(ConvolutionMode mode) |
Convolution3D.Builder |
Convolution3D.Builder.dataFormat(Convolution3D.DataFormat dataFormat) |
Convolution3D.Builder |
Convolution3D.Builder.dilation(int... dilation)
Set dilation size for 3D convolutions in (depth, height, width) order
|
Convolution3D.Builder |
Convolution3D.Builder.kernelSize(int... kernelSize)
Set kernel size for 3D convolutions in (depth, height, width) order
|
Convolution3D.Builder |
Convolution3D.Builder.padding(int... padding)
Set padding size for 3D convolutions in (depth, height, width) order
|
Convolution3D.Builder |
Convolution3D.Builder.stride(int... stride)
Set stride size for 3D convolutions in (depth, height, width) order
|
Constructor and Description |
---|
Convolution3D(Convolution3D.Builder builder)
3-dimensional convolutional layer configuration
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
|
Copyright © 2018. All rights reserved.