Package org.deeplearning4j.nn.layers.convolution.subsampling

Interface SubsamplingHelper

All Superinterfaces:

LayerHelper

All Known Implementing Classes:

MKLDNNSubsamplingHelper

public interface SubsamplingHelper
extends LayerHelper

Helper for the subsampling layer.

Author:

saudet

Method Summary

Modifier and Type	Method	Description
INDArray	activate(INDArray input, boolean training, int[] kernel, int[] strides, int[] pad, PoolingType poolingType, ConvolutionMode convolutionMode, int[] dilation, CNN2DFormat format, LayerWorkspaceMgr workspaceMgr)
Pair<Gradient,INDArray>	backpropGradient(INDArray input, INDArray epsilon, int[] kernel, int[] strides, int[] pad, PoolingType poolingType, ConvolutionMode convolutionMode, int[] dilation, CNN2DFormat format, LayerWorkspaceMgr workspaceMgr)

Methods inherited from interface org.deeplearning4j.nn.layers.LayerHelper

checkSupported, helperMemoryUse

Method Detail

backpropGradient

Pair<Gradient,INDArray> backpropGradient(INDArray input,
                                               INDArray epsilon,
                                               int[] kernel,
                                               int[] strides,
                                               int[] pad,
                                               PoolingType poolingType,
                                               ConvolutionMode convolutionMode,
                                               int[] dilation,
                                               CNN2DFormat format,
                                               LayerWorkspaceMgr workspaceMgr)

activate

INDArray activate(INDArray input,
                  boolean training,
                  int[] kernel,
                  int[] strides,
                  int[] pad,
                  PoolingType poolingType,
                  ConvolutionMode convolutionMode,
                  int[] dilation,
                  CNN2DFormat format,
                  LayerWorkspaceMgr workspaceMgr)