我正在尝试使用DeepLearning4j将0x到32x32图像分类为数字。我查看了许多示例和教程,但是在将数据集拟合到网络时总是遇到一些异常。
我目前正在尝试将ImageRecordReader与ParentPathLabelGenerator和RecordReaderDataSetIterator一起使用。
图像似乎可以很好地加载,但是安装时我总是遇到DL4JInvalidInputException。
File parentDir = new File(dataPath);
FileSplit filesInDir = new FileSplit(parentDir, NativeImageLoader.ALLOWED_FORMATS);
ParentPathLabelGenerator labelMaker = new ParentPathLabelGenerator();
BalancedPathFilter pathFilter = new BalancedPathFilter(new Random(), labelMaker, 100);
InputSplit[] filesInDirSplit = filesInDir.sample(pathFilter, 80, 20);
InputSplit trainData = filesInDirSplit[0];
InputSplit testData = filesInDirSplit[1];
ImageRecordReader recordReader = new ImageRecordReader(numRows, numColumns, 3, labelMaker);
recordReader.initialize(trainData);
DataSetIterator dataIter = new RecordReaderDataSetIterator(recordReader, 1, 1, outputNum);
使用DenseLayer时:
Exception in thread "main" org.deeplearning4j.exception.DL4JInvalidInputException: Input that is not a matrix; expected matrix (rank 2), got rank 4 array with shape [1, 3, 32, 32]. Missing preprocessor or wrong input type? (layer name: layer0, layer index: 0, layer type: DenseLayer)
使用ConvolutionLayer时,错误发生在OutputLayer:
Exception in thread "main" org.deeplearning4j.exception.DL4JInvalidInputException: Input that is not a matrix; expected matrix (rank 2), got rank 4 array with shape [1, 1000, 28, 28]. Missing preprocessor or wrong input type? (layer name: layer1, layer index: 1, layer type: OutputLayer)
我加载图像的尝试是否正确或我的网络配置不正确?
配置:
MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
.list()
.layer(0, new ConvolutionLayer.Builder()
.nIn(3) // Number of input datapoints.
.nOut(1000) // Number of output datapoints.
.activation(Activation.RELU) // Activation function.
.weightInit(WeightInit.XAVIER) // Weight initialization.
.build())
.layer(1, new OutputLayer.Builder(LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD)
.nIn(1000)
.nOut(outputNum)
.activation(Activation.SOFTMAX)
.weightInit(WeightInit.XAVIER)
.build())
.build();
最简单的方法是在定义网络时使用.setInputType
配置选项。它将为您设置所有必要的预处理器,并且还将计算所有正确的.nIn
值。
[当您使用.setInputType
方式设置网络时,您根本不需要设置任何.nIn
值-仍然可以,如我所链接的示例所示,但是通常存在没有充分的理由这样做。