org.deeplearning4j.nn.layers.convolution.subsampling

Class CudnnSubsamplingHelper

java.lang.Object

org.deeplearning4j.nn.layers.convolution.subsampling.CudnnSubsamplingHelper

All Implemented Interfaces:

SubsamplingHelper

public class CudnnSubsamplingHelper
extends java.lang.Object
implements SubsamplingHelper

cuDNN-based helper for the subsampling layer.

Constructor Summary

Constructors

Constructor and Description
CudnnSubsamplingHelper()

Method Summary

Modifier and Type	Method and Description
org.nd4j.linalg.api.ndarray.INDArray	activate(org.nd4j.linalg.api.ndarray.INDArray input, boolean training, int[] kernel, int[] strides, int[] pad, PoolingType poolingType, ConvolutionMode convolutionMode)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	backpropGradient(org.nd4j.linalg.api.ndarray.INDArray input, org.nd4j.linalg.api.ndarray.INDArray epsilon, int[] kernel, int[] strides, int[] pad, PoolingType poolingType, ConvolutionMode convolutionMode)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

CudnnSubsamplingHelper

public CudnnSubsamplingHelper()

Method Detail

backpropGradient

public Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray> backpropGradient(org.nd4j.linalg.api.ndarray.INDArray input,
                                                                            org.nd4j.linalg.api.ndarray.INDArray epsilon,
                                                                            int[] kernel,
                                                                            int[] strides,
                                                                            int[] pad,
                                                                            PoolingType poolingType,
                                                                            ConvolutionMode convolutionMode)

Specified by:

backpropGradient in interface SubsamplingHelper

activate

public org.nd4j.linalg.api.ndarray.INDArray activate(org.nd4j.linalg.api.ndarray.INDArray input,
                                                     boolean training,
                                                     int[] kernel,
                                                     int[] strides,
                                                     int[] pad,
                                                     PoolingType poolingType,
                                                     ConvolutionMode convolutionMode)

Specified by:

activate in interface SubsamplingHelper