DeepLearning4J 맞춤 매트릭스가있는 CNN의 경우 IllegalArgumentException

Question

교육에 사용할 사용자 지정 7 (높이) 및 24 (너비) 행렬 입력이 있습니다. 출력은 Age (Young, Mature, Old) 레이블이 있습니다. Deeplearning4J Convolutional Neural Networks와 함께 가고 싶습니다.

매우 기본적인 컨볼 루션 신경망을 구축 한 후에 매우 첫 번째 훈련 항목에 다음과 같은 오류가 발생하며 이에 대한 단서가 없습니다.

Exception in thread "main" java.lang.IllegalArgumentException: Invalid size index 2 wher it's >= rank 2 
at org.nd4j.linalg.api.ndarray.BaseNDArray.size(BaseNDArray.java:4066) 
at org.deeplearning4j.nn.layers.convolution.ConvolutionLayer.preOutput(ConvolutionLayer.java:192) 
at org.deeplearning4j.nn.layers.convolution.ConvolutionLayer.activate(ConvolutionLayer.java:247) 
at org.deeplearning4j.nn.graph.vertex.impl.LayerVertex.doForward(LayerVertex.java:88) 
at org.deeplearning4j.nn.graph.ComputationGraph.feedForward(ComputationGraph.java:983) 
at org.deeplearning4j.nn.graph.ComputationGraph.computeGradientAndScore(ComputationGraph.java:889) 

내 DL4J 코드

//Model Config here 
MultiLayerConfiguration.Builder builder = new NeuralNetConfiguration.Builder() 
    .seed(seed) 
    .iterations(iterations) 
    .regularization(true).l2(0.0005) 
    .learningRate(0.01)//.biasLearningRate(0.02) 
    //.learningRateDecayPolicy(LearningRatePolicy.Inverse).lrPolicyDecayRate(0.001).lrPolicyPower(0.75) 
    .weightInit(WeightInit.XAVIER) 
    .optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT) 
    .updater(Updater.NESTEROVS).momentum(0.9) 
    .list() 
    .layer(0, new ConvolutionLayer.Builder(4, 1) 
     //nIn and nOut specify depth. nIn here is the nChannels and nOut is the number of filters to be applied 
      .name("hzvt1") 
     .nIn(nChannels) 
     .stride(1, 1) 
     .nOut(26) 
     .activation("relu")//.activation("identity") 
     .build()) 
    .layer(1, new OutputLayer.Builder(LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD) 
     .nOut(outputNum) 
     .activation("softmax") 
     .build()) 
    .setInputType(InputType.convolutional(nChannels,height,width)) 
    .backprop(true).pretrain(false); 

//Model build here    
model.fit(wmTrain);MultiLayerConfiguration conf = builder.build(); 
model.fit(wmTrain);MultiLayerNetwork model = new MultiLayerNetwork(conf); 
model.init();    

//Training data creation here 
INDArray weekMatrix = Nd4j.ones(DLAgeGender.nChannels,DLAgeGender.height*DLAgeGender.width);  
double[] vector = new double[] { 0.0, 1.0, 0.0 }; 
INDArray intLabels = Nd4j.create(vector); 
DataSet ds=new DataSet(weekMatrix,intLabels); 
//Train the first item 
model.fit(wmTrain); 

내가 DL4J 버전 0.6을 사용하고, 자바 버전 1.8, Maven은 3.3 이상

나는 도서관에서 버그를 생각한다.

Answer 1

거터 지원을 통해 모델과 입력이 일치하지 않는다는 것을 알았습니다. 올바른 작업 코드는 다음과 같습니다.

다음 릴리스에서 DL4J 오류/예외 메시지가 더 명확 해지기를 바랍니다.

log.info("Build model...."); 
System.out.println("Building model..."); 
MultiLayerConfiguration.Builder builder = new NeuralNetConfiguration.Builder() 
     .seed(seed) 
     .iterations(iterations) 
     .regularization(true).l2(0.0005) 
     .learningRate(0.01)//.biasLearningRate(0.02) 
     //.learningRateDecayPolicy(LearningRatePolicy.Inverse).lrPolicyDecayRate(0.001).lrPolicyPower(0.75) 
     .weightInit(WeightInit.XAVIER) 
     .optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT) 
     .updater(Updater.NESTEROVS).momentum(0.9) 
     .list() 
     .layer(0, new ConvolutionLayer.Builder(4, 1) 
      //nIn and nOut specify depth. nIn here is the nChannels and nOut is the number of filters to be applied 
      .name("hzvt1") 
      .nIn(nChannels) 
      .stride(1, 1) 
      .nOut(26) 
      .activation("relu")//.activation("identity") 
      .build()) 
     .layer(1, new OutputLayer.Builder(LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD) 
      .nOut(classes) 
      .activation("softmax") 
      .build()) 
     .setInputType(InputType.convolutional(height,width,nChannels)) 
     .backprop(true).pretrain(false); 

//Model build here    
model.fit(wmTrain);MultiLayerConfiguration conf = builder.build(); 
model.fit(wmTrain);MultiLayerNetwork model = new MultiLayerNetwork(conf); 
model.init();    

//Training data creation here 
    INDArray weekMatrix = Nd4j.ones(new int[]{1,DLAgeGender.nChannels,DLAgeGender.height,DLAgeGender.width}); 
    INDArray intLabels; 
    double[] vector = new double[] { 0.0, 1.0, }; 
    intLabels = Nd4j.create(vector); 
DataSet ds=new DataSet(weekMatrix,intLabels); 

log.info("Train model...."); 
model.setListeners(new ScoreIterationListener(1)); 
model.fit(wmTrain); 
System.out.println("Data train OK.");