问题

我正在尝试使用DeepLearning4j将32x32像素的图像分类为0-9之间的数字。
我查阅了许多示例和教程，但在将数据集适配到网络时总是遇到一些异常情况。

我目前正在尝试使用一个带有ParentPathLabelGenerator的ImageRecordReader和RecordReaderDataSetIterator。

图像似乎加载得很好，但在适配时我总是遇到DL4JInvalidInputException异常。

    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);

当使用DenseLayer时：

Exception in thread "main" org.deeplearning4j.exception.DL4JInvalidInputException: 非矩阵输入；预期矩阵（秩为2），但得到秩为4的数组，形状为[1, 3, 32, 32]。缺少预处理器或错误的输入类型？（图层名称：layer0，图层索引：0，图层类型：DenseLayer）

当使用ConvolutionLayer时，错误出现在OutputLayer：

Exception in thread "main" org.deeplearning4j.exception.DL4JInvalidInputException: 非矩阵输入；预期矩阵（秩为2），但得到秩为4的数组，形状为[1, 1000, 28, 28]。缺少预处理器或错误的输入类型？（图层名称：layer1，图层索引：1，图层类型：OutputLayer）

是我加载图像的尝试有问题，还是我的网络配置有误？

配置：

MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
.list()
.layer(0, new ConvolutionLayer.Builder()
.nIn(3) // 输入数据点数。
.nOut(1000) // 输出数据点数。
.activation(Activation.RELU) // 激活函数。
.weightInit(WeightInit.XAVIER) // 权重初始化。
.build())
.layer(1, new OutputLayer.Builder(LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD)
.nIn(1000)
.nOut(outputNum)
.activation(Activation.SOFTMAX)
.weightInit(WeightInit.XAVIER)
.build())
.build();

<details>
<summary>英文:</summary>

I&#39;m trying to use DeepLearning4j to categorize 32x32 images in numbers from 0-9.
I&#39;ve looked up a number of examples and tutorials, but always run into some exception when fitting the dataset to a network.

Im currently trying to use a ImageRecordReader with ParentPathLabelGenerator and RecordReaderDataSetIterator.

The images seem to load fine but i always run into a DL4JInvalidInputException when fitting.

    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);

When using DenseLayer:

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)

When using ConvolutionLayer the error occures at the 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)

Is my attempt at loading the images incorrect or is my network misconfigured?

Configuration:

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();

</details>


# 答案1
**得分**: 0

使用`.setInputType`配置选项来定义网络是最简单的方法。它将为您设置所有必要的预处理器，并且还会计算所有正确的`.nIn`值。

再次查看这个示例：https://github.com/eclipse/deeplearning4j-examples/blob/master/dl4j-examples/src/main/java/org/deeplearning4j/examples/convolution/mnist/MnistClassifier.java#L156

当您使用`.setInputType`的方式来设置网络时，您无需设置任何`.nIn`值 - 但您仍然可以在我链接的示例中看到这一点，但通常没有充分的理由这样做。

<details>
<summary>英文:</summary>

The easiest way is to use the `.setInputType` configuration option when defining the network. It will set up all the necessary pre-processors for you, and it will calculate all the correct `.nIn` values too.

Take another look at this example https://github.com/eclipse/deeplearning4j-examples/blob/master/dl4j-examples/src/main/java/org/deeplearning4j/examples/convolution/mnist/MnistClassifier.java#L156

When you use the `.setInputType` way of setting up your network, you don&#39;t have to set any `.nIn` values at all - you still can, as is evident in the example I&#39;ve linked, but usually there is no good reason to do so. 

</details>