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)
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] |
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 © 2019. All rights reserved.