Package org.deeplearning4j.gradientcheck

Class GradientCheckUtil

java.lang.Object

org.deeplearning4j.gradientcheck.GradientCheckUtil

public class GradientCheckUtil
extends Object

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	GradientCheckUtil.GraphConfig
static class	GradientCheckUtil.MLNConfig
static class	GradientCheckUtil.PrintMode

Method Summary

Modifier and Type	Method	Description
static boolean	checkGradients(GradientCheckUtil.GraphConfig c)
static boolean	checkGradients(GradientCheckUtil.MLNConfig c)
static boolean	checkGradients(MultiLayerNetwork mln, double epsilon, double maxRelError, double minAbsoluteError, boolean print, boolean exitOnFirstError, INDArray input, INDArray labels)	Deprecated.
static boolean	checkGradients(MultiLayerNetwork mln, double epsilon, double maxRelError, double minAbsoluteError, boolean print, boolean exitOnFirstError, INDArray input, INDArray labels, INDArray inputMask, INDArray labelMask, boolean subset, int maxPerParam, Set<String> excludeParams, Integer rngSeedResetEachIter)	Deprecated.
static boolean	checkGradientsPretrainLayer(Layer layer, double epsilon, double maxRelError, double minAbsoluteError, boolean print, boolean exitOnFirstError, INDArray input, int rngSeed)	Check backprop gradients for a pretrain layer NOTE: gradient checking pretrain layers can be difficult...

Methods inherited from class java.lang.Object

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

Method Detail

checkGradients

@Deprecated
public static boolean checkGradients(MultiLayerNetwork mln,
                                     double epsilon,
                                     double maxRelError,
                                     double minAbsoluteError,
                                     boolean print,
                                     boolean exitOnFirstError,
                                     INDArray input,
                                     INDArray labels)

Deprecated.

Check backprop gradients for a MultiLayerNetwork.

Parameters:

mln - MultiLayerNetwork to test. This must be initialized.

epsilon - Usually on the order/ of 1e-4 or so.

maxRelError - Maximum relative error. Usually < 1e-5 or so, though maybe more for deep networks or those with nonlinear activation

minAbsoluteError - Minimum absolute error to cause a failure. Numerical gradients can be non-zero due to precision issues. For example, 0.0 vs. 1e-18: relative error is 1.0, but not really a failure

print - Whether to print full pass/failure details for each parameter gradient

exitOnFirstError - If true: return upon first failure. If false: continue checking even if one parameter gradient has failed. Typically use false for debugging, true for unit tests.

input - Input array to use for forward pass. May be mini-batch data.

labels - Labels/targets to use to calculate backprop gradient. May be mini-batch data.

Returns:

true if gradients are passed, false otherwise.

checkGradients

@Deprecated
public static boolean checkGradients(MultiLayerNetwork mln,
                                     double epsilon,
                                     double maxRelError,
                                     double minAbsoluteError,
                                     boolean print,
                                     boolean exitOnFirstError,
                                     INDArray input,
                                     INDArray labels,
                                     INDArray inputMask,
                                     INDArray labelMask,
                                     boolean subset,
                                     int maxPerParam,
                                     Set<String> excludeParams,
                                     Integer rngSeedResetEachIter)

Deprecated.

checkGradients

public static boolean checkGradients(GradientCheckUtil.MLNConfig c)

checkGradients

public static boolean checkGradients(GradientCheckUtil.GraphConfig c)

checkGradientsPretrainLayer

public static boolean checkGradientsPretrainLayer(Layer layer,
                                                  double epsilon,
                                                  double maxRelError,
                                                  double minAbsoluteError,
                                                  boolean print,
                                                  boolean exitOnFirstError,
                                                  INDArray input,
                                                  int rngSeed)

Check backprop gradients for a pretrain layer NOTE: gradient checking pretrain layers can be difficult...