org.deeplearning4j.nn.layers.convolution

Class CudnnConvolutionHelper

java.lang.Object

org.deeplearning4j.nn.layers.convolution.CudnnConvolutionHelper

All Implemented Interfaces:

ConvolutionHelper

public class CudnnConvolutionHelper
extends java.lang.Object
implements ConvolutionHelper

cuDNN-based helper for the convolution layer.

Field Summary

Fields

Modifier and Type	Field and Description
protected static org.slf4j.Logger	log

Constructor Summary

Constructors

Constructor and Description
CudnnConvolutionHelper()

Method Summary

Modifier and Type	Method and Description
org.nd4j.linalg.api.ndarray.INDArray	activate(org.nd4j.linalg.api.ndarray.INDArray z, org.nd4j.linalg.activations.IActivation afn)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	backpropGradient(org.nd4j.linalg.api.ndarray.INDArray input, org.nd4j.linalg.api.ndarray.INDArray weights, org.nd4j.linalg.api.ndarray.INDArray delta, int[] kernel, int[] strides, int[] pad, org.nd4j.linalg.api.ndarray.INDArray biasGradView, org.nd4j.linalg.api.ndarray.INDArray weightGradView, org.nd4j.linalg.activations.IActivation afn, ConvolutionLayer.AlgoMode mode, ConvolutionMode convolutionMode)
org.nd4j.linalg.api.ndarray.INDArray	preOutput(org.nd4j.linalg.api.ndarray.INDArray input, org.nd4j.linalg.api.ndarray.INDArray weights, org.nd4j.linalg.api.ndarray.INDArray bias, int[] kernel, int[] strides, int[] pad, ConvolutionLayer.AlgoMode mode, ConvolutionMode convolutionMode)

Methods inherited from class java.lang.Object

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

Field Detail

log

protected static final org.slf4j.Logger log

Constructor Detail

CudnnConvolutionHelper

public CudnnConvolutionHelper()

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 weights,
                                                                            org.nd4j.linalg.api.ndarray.INDArray delta,
                                                                            int[] kernel,
                                                                            int[] strides,
                                                                            int[] pad,
                                                                            org.nd4j.linalg.api.ndarray.INDArray biasGradView,
                                                                            org.nd4j.linalg.api.ndarray.INDArray weightGradView,
                                                                            org.nd4j.linalg.activations.IActivation afn,
                                                                            ConvolutionLayer.AlgoMode mode,
                                                                            ConvolutionMode convolutionMode)

Specified by:

backpropGradient in interface ConvolutionHelper

preOutput

public org.nd4j.linalg.api.ndarray.INDArray preOutput(org.nd4j.linalg.api.ndarray.INDArray input,
                                                      org.nd4j.linalg.api.ndarray.INDArray weights,
                                                      org.nd4j.linalg.api.ndarray.INDArray bias,
                                                      int[] kernel,
                                                      int[] strides,
                                                      int[] pad,
                                                      ConvolutionLayer.AlgoMode mode,
                                                      ConvolutionMode convolutionMode)

Specified by:

preOutput in interface ConvolutionHelper

activate

public org.nd4j.linalg.api.ndarray.INDArray activate(org.nd4j.linalg.api.ndarray.INDArray z,
                                                     org.nd4j.linalg.activations.IActivation afn)

Specified by:

activate in interface ConvolutionHelper