Java Code Examples for org.nd4j.linalg.activations.Activation#ELU
The following examples show how to use
org.nd4j.linalg.activations.Activation#ELU .
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example 1
| Source File: KerasActivationUtils.java From deeplearning4j with Apache License 2.0 | 5 votes |
|
/**
* Map Keras to DL4J activation functions.
*
* @param conf Keras layer configuration
* @param kerasActivation String containing Keras activation function name
* @return Activation enum value containing DL4J activation function name
*/
public static Activation mapToActivation(String kerasActivation, KerasLayerConfiguration conf)
throws UnsupportedKerasConfigurationException {
Activation dl4jActivation;
if (kerasActivation.equals(conf.getKERAS_ACTIVATION_SOFTMAX())) {
dl4jActivation = Activation.SOFTMAX;
} else if (kerasActivation.equals(conf.getKERAS_ACTIVATION_SOFTPLUS())) {
dl4jActivation = Activation.SOFTPLUS;
} else if (kerasActivation.equals(conf.getKERAS_ACTIVATION_SOFTSIGN())) {
dl4jActivation = Activation.SOFTSIGN;
} else if (kerasActivation.equals(conf.getKERAS_ACTIVATION_RELU())) {
dl4jActivation = Activation.RELU;
} else if (kerasActivation.equals(conf.getKERAS_ACTIVATION_RELU6())) {
dl4jActivation = Activation.RELU6;
} else if (kerasActivation.equals(conf.getKERAS_ACTIVATION_ELU())) {
dl4jActivation = Activation.ELU;
} else if (kerasActivation.equals(conf.getKERAS_ACTIVATION_SELU())) {
dl4jActivation = Activation.SELU;
} else if (kerasActivation.equals(conf.getKERAS_ACTIVATION_TANH())) {
dl4jActivation = Activation.TANH;
} else if (kerasActivation.equals(conf.getKERAS_ACTIVATION_SIGMOID())) {
dl4jActivation = Activation.SIGMOID;
} else if (kerasActivation.equals(conf.getKERAS_ACTIVATION_HARD_SIGMOID())) {
dl4jActivation = Activation.HARDSIGMOID;
} else if (kerasActivation.equals(conf.getKERAS_ACTIVATION_LINEAR())) {
dl4jActivation = Activation.IDENTITY;
} else if (kerasActivation.equals(conf.getKERAS_ACTIVATION_SWISH())) {
dl4jActivation = Activation.SWISH;
} else {
throw new UnsupportedKerasConfigurationException(
"Unknown Keras activation function " + kerasActivation);
}
return dl4jActivation;
}
Example 2
| Source File: SameDiffTests.java From nd4j with Apache License 2.0 | 4 votes |
|
@Test
public void testActivationBackprop() {
Activation[] afns = new Activation[]{
Activation.TANH,
Activation.SIGMOID,
Activation.ELU,
Activation.SOFTPLUS,
Activation.SOFTSIGN,
Activation.HARDTANH,
Activation.CUBE, //WRONG output - see issue https://github.com/deeplearning4j/nd4j/issues/2426
Activation.RELU, //JVM crash
Activation.LEAKYRELU //JVM crash
};
for (Activation a : afns) {
SameDiff sd = SameDiff.create();
INDArray inArr = Nd4j.linspace(-3, 3, 7);
INDArray labelArr = Nd4j.linspace(-3, 3, 7).muli(0.5);
SDVariable in = sd.var("in", inArr.dup());
// System.out.println("inArr: " + inArr);
INDArray outExp;
SDVariable out;
switch (a) {
case ELU:
out = sd.elu("out", in);
outExp = Transforms.elu(inArr, true);
break;
case HARDTANH:
out = sd.hardTanh("out", in);
outExp = Transforms.hardTanh(inArr, true);
break;
case LEAKYRELU:
out = sd.leakyRelu("out", in, 0.01);
outExp = Transforms.leakyRelu(inArr, true);
break;
case RELU:
out = sd.relu("out", in, 0.0);
outExp = Transforms.relu(inArr, true);
break;
case SIGMOID:
out = sd.sigmoid("out", in);
outExp = Transforms.sigmoid(inArr, true);
break;
case SOFTPLUS:
out = sd.softplus("out", in);
outExp = Transforms.softPlus(inArr, true);
break;
case SOFTSIGN:
out = sd.softsign("out", in);
outExp = Transforms.softsign(inArr, true);
break;
case TANH:
out = sd.tanh("out", in);
outExp = Transforms.tanh(inArr, true);
break;
case CUBE:
out = sd.cube("out", in);
outExp = Transforms.pow(inArr, 3, true);
break;
default:
throw new RuntimeException(a.toString());
}
//Sum squared error loss:
SDVariable label = sd.var("label", labelArr.dup());
SDVariable diff = label.sub("diff", out);
SDVariable sqDiff = diff.mul("sqDiff", diff);
SDVariable totSum = sd.sum("totSum", sqDiff, Integer.MAX_VALUE); //Loss function...
sd.exec();
INDArray outAct = sd.getVariable("out").getArr();
assertEquals(a.toString(), outExp, outAct);
// L = sum_i (label - out)^2
//dL/dOut = 2(out - label)
INDArray dLdOutExp = outExp.sub(labelArr).mul(2);
INDArray dLdInExp = a.getActivationFunction().backprop(inArr.dup(), dLdOutExp.dup()).getFirst();
sd.execBackwards();
SameDiff gradFn = sd.getFunction("grad");
INDArray dLdOutAct = gradFn.getVariable("out-grad").getArr();
INDArray dLdInAct = gradFn.getVariable("in-grad").getArr();
assertEquals(a.toString(), dLdOutExp, dLdOutAct);
assertEquals(a.toString(), dLdInExp, dLdInAct);
}
}
Example 3
| Source File: SameDiffTests.java From deeplearning4j with Apache License 2.0 | 4 votes |
|
@Test
public void testActivationBackprop() {
Activation[] afns = new Activation[]{
Activation.TANH,
Activation.SIGMOID,
Activation.ELU,
Activation.SOFTPLUS,
Activation.SOFTSIGN,
Activation.HARDTANH,
Activation.CUBE,
//WRONG output - see issue https://github.com/deeplearning4j/nd4j/issues/2426
Activation.RELU, //JVM crash
Activation.LEAKYRELU //JVM crash
};
for (Activation a : afns) {
SameDiff sd = SameDiff.create();
INDArray inArr = Nd4j.linspace(-3, 3, 7);
INDArray labelArr = Nd4j.linspace(-3, 3, 7).muli(0.5);
SDVariable in = sd.var("in", inArr.dup());
// System.out.println("inArr: " + inArr);
INDArray outExp;
SDVariable out;
switch (a) {
case ELU:
out = sd.nn().elu("out", in);
outExp = Transforms.elu(inArr, true);
break;
case HARDTANH:
out = sd.nn().hardTanh("out", in);
outExp = Transforms.hardTanh(inArr, true);
break;
case LEAKYRELU:
out = sd.nn().leakyRelu("out", in, 0.01);
outExp = Transforms.leakyRelu(inArr, true);
break;
case RELU:
out = sd.nn().relu("out", in, 0.0);
outExp = Transforms.relu(inArr, true);
break;
case SIGMOID:
out = sd.nn().sigmoid("out", in);
outExp = Transforms.sigmoid(inArr, true);
break;
case SOFTPLUS:
out = sd.nn().softplus("out", in);
outExp = Transforms.softPlus(inArr, true);
break;
case SOFTSIGN:
out = sd.nn().softsign("out", in);
outExp = Transforms.softsign(inArr, true);
break;
case TANH:
out = sd.math().tanh("out", in);
outExp = Transforms.tanh(inArr, true);
break;
case CUBE:
out = sd.math().cube("out", in);
outExp = Transforms.pow(inArr, 3, true);
break;
default:
throw new RuntimeException(a.toString());
}
//Sum squared error loss:
SDVariable label = sd.var("label", labelArr.dup());
SDVariable diff = label.sub("diff", out);
SDVariable sqDiff = diff.mul("sqDiff", diff);
SDVariable totSum = sd.sum("totSum", sqDiff, Integer.MAX_VALUE); //Loss function...
Map<String,INDArray> m = sd.output(Collections.emptyMap(), "out");
INDArray outAct = m.get("out");
assertEquals(a.toString(), outExp, outAct);
// L = sum_i (label - out)^2
//dL/dOut = 2(out - label)
INDArray dLdOutExp = outExp.sub(labelArr).mul(2);
INDArray dLdInExp = a.getActivationFunction().backprop(inArr.dup(), dLdOutExp.dup()).getFirst();
Map<String,INDArray> grads = sd.calculateGradients(null, "out", "in");
// sd.execBackwards(Collections.emptyMap());
// SameDiff gradFn = sd.getFunction("grad");
INDArray dLdOutAct = grads.get("out");
INDArray dLdInAct = grads.get("in");
assertEquals(a.toString(), dLdOutExp, dLdOutAct);
assertEquals(a.toString(), dLdInExp, dLdInAct);
}
}
Example 4
| Source File: CNNGradientCheckTest.java From deeplearning4j with Apache License 2.0 | 4 votes |
|
@Test
public void testGradientCNNL1L2MLN() {
if(this.format != CNN2DFormat.NCHW) //Only test NCHW due to flat input format...
return;
//Parameterized test, testing combinations of:
// (a) activation function
// (b) Whether to test at random initialization, or after some learning (i.e., 'characteristic mode of operation')
// (c) Loss function (with specified output activations)
DataSet ds = new IrisDataSetIterator(150, 150).next();
ds.normalizeZeroMeanZeroUnitVariance();
INDArray input = ds.getFeatures();
INDArray labels = ds.getLabels();
//use l2vals[i] with l1vals[i]
double[] l2vals = {0.4, 0.0, 0.4, 0.4};
double[] l1vals = {0.0, 0.0, 0.5, 0.0};
double[] biasL2 = {0.0, 0.0, 0.0, 0.2};
double[] biasL1 = {0.0, 0.0, 0.6, 0.0};
Activation[] activFns = {Activation.SIGMOID, Activation.TANH, Activation.ELU, Activation.SOFTPLUS};
boolean[] characteristic = {false, true, false, true}; //If true: run some backprop steps first
LossFunctions.LossFunction[] lossFunctions =
{LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD, LossFunctions.LossFunction.MSE, LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD, LossFunctions.LossFunction.MSE};
Activation[] outputActivations = {Activation.SOFTMAX, Activation.TANH, Activation.SOFTMAX, Activation.IDENTITY}; //i.e., lossFunctions[i] used with outputActivations[i] here
for( int i=0; i<l2vals.length; i++ ){
Activation afn = activFns[i];
boolean doLearningFirst = characteristic[i];
LossFunctions.LossFunction lf = lossFunctions[i];
Activation outputActivation = outputActivations[i];
double l2 = l2vals[i];
double l1 = l1vals[i];
MultiLayerConfiguration.Builder builder = new NeuralNetConfiguration.Builder()
.dataType(DataType.DOUBLE)
.l2(l2).l1(l1).l2Bias(biasL2[i]).l1Bias(biasL1[i])
.optimizationAlgo(
OptimizationAlgorithm.CONJUGATE_GRADIENT)
.seed(12345L).list()
.layer(0, new ConvolutionLayer.Builder(new int[]{1, 1}).nIn(1).nOut(6)
.weightInit(WeightInit.XAVIER).activation(afn)
.updater(new NoOp()).build())
.layer(1, new OutputLayer.Builder(lf).activation(outputActivation).nOut(3)
.weightInit(WeightInit.XAVIER).updater(new NoOp()).build())
.setInputType(InputType.convolutionalFlat(1, 4, 1));
MultiLayerConfiguration conf = builder.build();
MultiLayerNetwork mln = new MultiLayerNetwork(conf);
mln.init();
String testName = new Object() {
}.getClass().getEnclosingMethod().getName();
if (doLearningFirst) {
//Run a number of iterations of learning
mln.setInput(ds.getFeatures());
mln.setLabels(ds.getLabels());
mln.computeGradientAndScore();
double scoreBefore = mln.score();
for (int j = 0; j < 10; j++)
mln.fit(ds);
mln.computeGradientAndScore();
double scoreAfter = mln.score();
//Can't test in 'characteristic mode of operation' if not learning
String msg = testName
+ "- score did not (sufficiently) decrease during learning - activationFn="
+ afn + ", lossFn=" + lf + ", outputActivation=" + outputActivation
+ ", doLearningFirst=" + doLearningFirst + " (before=" + scoreBefore
+ ", scoreAfter=" + scoreAfter + ")";
assertTrue(msg, scoreAfter < 0.8 * scoreBefore);
}
if (PRINT_RESULTS) {
System.out.println(testName + "- activationFn=" + afn + ", lossFn=" + lf
+ ", outputActivation=" + outputActivation + ", doLearningFirst="
+ doLearningFirst);
// for (int j = 0; j < mln.getnLayers(); j++)
// System.out.println("Layer " + j + " # params: " + mln.getLayer(j).numParams());
}
boolean gradOK = GradientCheckUtil.checkGradients(mln, DEFAULT_EPS, DEFAULT_MAX_REL_ERROR,
DEFAULT_MIN_ABS_ERROR, PRINT_RESULTS, RETURN_ON_FIRST_FAILURE, input, labels);
assertTrue(gradOK);
TestUtils.testModelSerialization(mln);
}
}
Example 5
| Source File: TestSameDiffDense.java From deeplearning4j with Apache License 2.0 | 4 votes |
|
@Test
public void testSameDiffDenseForward() {
for(WorkspaceMode wsm : new WorkspaceMode[]{WorkspaceMode.ENABLED, WorkspaceMode.NONE}) {
for (int minibatch : new int[]{5, 1}) {
int nIn = 3;
int nOut = 4;
Activation[] afns = new Activation[]{
Activation.TANH,
Activation.SIGMOID,
Activation.ELU,
Activation.IDENTITY,
Activation.SOFTPLUS,
Activation.SOFTSIGN,
Activation.CUBE,
Activation.HARDTANH,
Activation.RELU
};
for (Activation a : afns) {
log.info("Starting test - " + a + ", workspace = " + wsm);
MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
.inferenceWorkspaceMode(wsm)
.trainingWorkspaceMode(wsm)
.list()
.layer(new SameDiffDense.Builder().nIn(nIn).nOut(nOut)
.activation(a)
.build())
.build();
MultiLayerNetwork net = new MultiLayerNetwork(conf);
net.init();
assertNotNull(net.paramTable());
MultiLayerConfiguration conf2 = new NeuralNetConfiguration.Builder()
.list()
.layer(new DenseLayer.Builder().activation(a).nIn(nIn).nOut(nOut).build())
.build();
MultiLayerNetwork net2 = new MultiLayerNetwork(conf2);
net2.init();
net.params().assign(net2.params());
//Check params:
assertEquals(net2.params(), net.params());
Map<String, INDArray> params1 = net.paramTable();
Map<String, INDArray> params2 = net2.paramTable();
assertEquals(params2, params1);
INDArray in = Nd4j.rand(minibatch, nIn);
INDArray out = net.output(in);
INDArray outExp = net2.output(in);
assertEquals(outExp, out);
//Also check serialization:
MultiLayerNetwork netLoaded = TestUtils.testModelSerialization(net);
INDArray outLoaded = netLoaded.output(in);
assertEquals(outExp, outLoaded);
//Sanity check on different minibatch sizes:
INDArray newIn = Nd4j.vstack(in, in);
INDArray outMbsd = net.output(newIn);
INDArray outMb = net2.output(newIn);
assertEquals(outMb, outMbsd);
}
}
}
}
Example 6
| Source File: TestSameDiffDense.java From deeplearning4j with Apache License 2.0 | 4 votes |
|
@Test
public void testSameDiffDenseForwardMultiLayer() {
for(WorkspaceMode wsm : new WorkspaceMode[]{WorkspaceMode.ENABLED, WorkspaceMode.NONE}) {
for (int minibatch : new int[]{5, 1}) {
int nIn = 3;
int nOut = 4;
Activation[] afns = new Activation[]{
Activation.TANH,
Activation.SIGMOID,
Activation.ELU,
Activation.IDENTITY,
Activation.SOFTPLUS,
Activation.SOFTSIGN,
Activation.CUBE, //https://github.com/deeplearning4j/nd4j/issues/2426
Activation.HARDTANH,
Activation.RELU //JVM crash
};
for (Activation a : afns) {
log.info("Starting test - " + a + " - workspace=" + wsm);
MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
.seed(12345)
.list()
.layer(new SameDiffDense.Builder().nIn(nIn).nOut(nOut)
.weightInit(WeightInit.XAVIER)
.activation(a).build())
.layer(new SameDiffDense.Builder().nIn(nOut).nOut(nOut)
.weightInit(WeightInit.XAVIER)
.activation(a).build())
.layer(new OutputLayer.Builder().nIn(nOut).nOut(nOut)
.weightInit(WeightInit.XAVIER)
.activation(a).build())
.validateOutputLayerConfig(false)
.build();
MultiLayerNetwork net = new MultiLayerNetwork(conf);
net.init();
assertNotNull(net.paramTable());
MultiLayerConfiguration conf2 = new NeuralNetConfiguration.Builder()
.seed(12345)
.weightInit(WeightInit.XAVIER)
.list()
.layer(new DenseLayer.Builder().activation(a).nIn(nIn).nOut(nOut).build())
.layer(new DenseLayer.Builder().activation(a).nIn(nOut).nOut(nOut).build())
.layer(new OutputLayer.Builder().nIn(nOut).nOut(nOut)
.activation(a).build())
.validateOutputLayerConfig(false)
.build();
MultiLayerNetwork net2 = new MultiLayerNetwork(conf2);
net2.init();
assertEquals(net2.params(), net.params());
//Check params:
assertEquals(net2.params(), net.params());
Map<String, INDArray> params1 = net.paramTable();
Map<String, INDArray> params2 = net2.paramTable();
assertEquals(params2, params1);
INDArray in = Nd4j.rand(minibatch, nIn);
INDArray out = net.output(in);
INDArray outExp = net2.output(in);
assertEquals(outExp, out);
//Also check serialization:
MultiLayerNetwork netLoaded = TestUtils.testModelSerialization(net);
INDArray outLoaded = netLoaded.output(in);
assertEquals(outExp, outLoaded);
//Sanity check different minibatch sizes
in = Nd4j.rand(2 * minibatch, nIn);
out = net.output(in);
outExp = net2.output(in);
assertEquals(outExp, out);
}
}
}
}
Example 7
| Source File: TestSameDiffDense.java From deeplearning4j with Apache License 2.0 | 4 votes |
|
@Test
public void testSameDiffDenseBackward() {
int nIn = 3;
int nOut = 4;
for (boolean workspaces : new boolean[]{false, true}) {
for (int minibatch : new int[]{5, 1}) {
Activation[] afns = new Activation[]{
Activation.TANH,
Activation.SIGMOID,
Activation.ELU,
Activation.IDENTITY,
Activation.SOFTPLUS,
Activation.SOFTSIGN,
Activation.HARDTANH,
Activation.CUBE,
Activation.RELU
};
for (Activation a : afns) {
log.info("Starting test - " + a + " - minibatch " + minibatch + ", workspaces: " + workspaces);
MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
.trainingWorkspaceMode(workspaces ? WorkspaceMode.ENABLED : WorkspaceMode.NONE)
.inferenceWorkspaceMode(workspaces ? WorkspaceMode.ENABLED : WorkspaceMode.NONE)
.list()
.layer(new SameDiffDense.Builder().nIn(nIn).nOut(nOut)
.activation(a)
.build())
.layer(new OutputLayer.Builder().nIn(nOut).nOut(nOut).activation(Activation.SOFTMAX)
.lossFunction(LossFunctions.LossFunction.MCXENT).build())
.build();
MultiLayerNetwork netSD = new MultiLayerNetwork(conf);
netSD.init();
MultiLayerConfiguration conf2 = new NeuralNetConfiguration.Builder()
.list()
.layer(new DenseLayer.Builder().activation(a).nIn(nIn).nOut(nOut).build())
.layer(new OutputLayer.Builder().nIn(nOut).nOut(nOut).activation(Activation.SOFTMAX)
.lossFunction(LossFunctions.LossFunction.MCXENT).build())
.build();
MultiLayerNetwork netStandard = new MultiLayerNetwork(conf2);
netStandard.init();
netSD.params().assign(netStandard.params());
//Check params:
assertEquals(netStandard.params(), netSD.params());
assertEquals(netStandard.paramTable(), netSD.paramTable());
INDArray in = Nd4j.rand(minibatch, nIn);
INDArray l = TestUtils.randomOneHot(minibatch, nOut, 12345);
netSD.setInput(in);
netStandard.setInput(in);
netSD.setLabels(l);
netStandard.setLabels(l);
netSD.computeGradientAndScore();
netStandard.computeGradientAndScore();
Gradient gSD = netSD.gradient();
Gradient gStd = netStandard.gradient();
Map<String, INDArray> m1 = gSD.gradientForVariable();
Map<String, INDArray> m2 = gStd.gradientForVariable();
assertEquals(m2.keySet(), m1.keySet());
for (String s : m1.keySet()) {
INDArray i1 = m1.get(s);
INDArray i2 = m2.get(s);
assertEquals(s, i2, i1);
}
assertEquals(gStd.gradient(), gSD.gradient());
//Sanity check: different minibatch size
in = Nd4j.rand(2 * minibatch, nIn);
l = TestUtils.randomOneHot(2 * minibatch, nOut, 12345);
netSD.setInput(in);
netStandard.setInput(in);
netSD.setLabels(l);
netStandard.setLabels(l);
netSD.computeGradientAndScore();
// netStandard.computeGradientAndScore();
// assertEquals(netStandard.gradient().gradient(), netSD.gradient().gradient());
//Sanity check on different minibatch sizes:
INDArray newIn = Nd4j.vstack(in, in);
INDArray outMbsd = netSD.output(newIn);
INDArray outMb = netStandard.output(newIn);
assertEquals(outMb, outMbsd);
}
}
}
}
Example 8
| Source File: CNNGradientCheckTest.java From deeplearning4j with Apache License 2.0 | 4 votes |
|
@Test
public void testGradientCNNL1L2MLN() {
//Parameterized test, testing combinations of:
// (a) activation function
// (b) Whether to test at random initialization, or after some learning (i.e., 'characteristic mode of operation')
// (c) Loss function (with specified output activations)
DataSet ds = new IrisDataSetIterator(150, 150).next();
ds.normalizeZeroMeanZeroUnitVariance();
INDArray input = ds.getFeatures();
INDArray labels = ds.getLabels();
//use l2vals[i] with l1vals[i]
double[] l2vals = {0.4, 0.0, 0.4, 0.4};
double[] l1vals = {0.0, 0.0, 0.5, 0.0};
double[] biasL2 = {0.0, 0.0, 0.0, 0.2};
double[] biasL1 = {0.0, 0.0, 0.6, 0.0};
Activation[] activFns = {Activation.SIGMOID, Activation.TANH, Activation.ELU, Activation.SOFTPLUS};
boolean[] characteristic = {false, true, false, true}; //If true: run some backprop steps first
LossFunctions.LossFunction[] lossFunctions =
{LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD, LossFunctions.LossFunction.MSE, LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD, LossFunctions.LossFunction.MSE};
Activation[] outputActivations = {Activation.SOFTMAX, Activation.TANH, Activation.SOFTMAX, Activation.IDENTITY}; //i.e., lossFunctions[i] used with outputActivations[i] here
for( int i=0; i<l2vals.length; i++ ){
Activation afn = activFns[i];
boolean doLearningFirst = characteristic[i];
LossFunctions.LossFunction lf = lossFunctions[i];
Activation outputActivation = outputActivations[i];
double l2 = l2vals[i];
double l1 = l1vals[i];
MultiLayerConfiguration.Builder builder = new NeuralNetConfiguration.Builder()
.dataType(DataType.DOUBLE)
.l2(l2).l1(l1).l2Bias(biasL2[i]).l1Bias(biasL1[i])
.optimizationAlgo(
OptimizationAlgorithm.CONJUGATE_GRADIENT)
.seed(12345L).list()
.layer(0, new ConvolutionLayer.Builder(new int[]{1, 1}).nIn(1).nOut(6)
.weightInit(WeightInit.XAVIER).activation(afn)
.updater(new NoOp()).build())
.layer(1, new OutputLayer.Builder(lf).activation(outputActivation).nOut(3)
.weightInit(WeightInit.XAVIER).updater(new NoOp()).build())
.setInputType(InputType.convolutionalFlat(1, 4, 1));
MultiLayerConfiguration conf = builder.build();
MultiLayerNetwork mln = new MultiLayerNetwork(conf);
mln.init();
String testName = new Object() {
}.getClass().getEnclosingMethod().getName();
if (doLearningFirst) {
//Run a number of iterations of learning
mln.setInput(ds.getFeatures());
mln.setLabels(ds.getLabels());
mln.computeGradientAndScore();
double scoreBefore = mln.score();
for (int j = 0; j < 10; j++)
mln.fit(ds);
mln.computeGradientAndScore();
double scoreAfter = mln.score();
//Can't test in 'characteristic mode of operation' if not learning
String msg = testName
+ "- score did not (sufficiently) decrease during learning - activationFn="
+ afn + ", lossFn=" + lf + ", outputActivation=" + outputActivation
+ ", doLearningFirst=" + doLearningFirst + " (before=" + scoreBefore
+ ", scoreAfter=" + scoreAfter + ")";
assertTrue(msg, scoreAfter < 0.8 * scoreBefore);
}
if (PRINT_RESULTS) {
System.out.println(testName + "- activationFn=" + afn + ", lossFn=" + lf
+ ", outputActivation=" + outputActivation + ", doLearningFirst="
+ doLearningFirst);
// for (int j = 0; j < mln.getnLayers(); j++)
// System.out.println("Layer " + j + " # params: " + mln.getLayer(j).numParams());
}
boolean gradOK = GradientCheckUtil.checkGradients(mln, DEFAULT_EPS, DEFAULT_MAX_REL_ERROR,
DEFAULT_MIN_ABS_ERROR, PRINT_RESULTS, RETURN_ON_FIRST_FAILURE, input, labels);
assertTrue(gradOK);
TestUtils.testModelSerialization(mln);
}
}
