CNTK 抱怨功能未实现

Question

我在 Brainscript 中有以下网络。

BrainScriptNetworkBuilder = {
    inputDim = 4
    labelDim = 1
    embDim = 20
    hiddenDim = 40

    model = Sequential (
        EmbeddingLayer {embDim} :                            # embedding
        RecurrentLSTMLayer {hiddenDim, goBackwards=false} :  # LSTM
        DenseLayer {labelDim}                                # output layer
    )

    # features
    t = DynamicAxis{}
    features = SparseInput {inputDim, tag="feature", dynamicAxis=t}
    anomaly  = Input {labelDim, tag="label"}

    # model application
    z = model (features)

    zp = ReconcileDynamicAxis(z, anomaly)

    # loss and metric
    ce   = CrossEntropyWithSoftmax (anomaly, zp)
    errs = ClassificationError     (anomaly, zp)

    featureNodes    = (features)
    labelNodes      = (anomaly)
    criterionNodes  = (ce)
    evaluationNodes = (errs)
    outputNodes     = (z)
}

我的数据是这样的：

2 |Features -0.08169 -0.07840 -0.09580 -0.08748 
2 |Features 0.00354 -0.00089 0.02832 0.00364 
2 |Features -0.18999 -0.12783 -0.02612 0.00474 
2 |Features 0.16097 0.11350 -0.01656 -0.05995 
2 |Features 0.09638 0.07632 -0.04359 0.02183 
2 |Features -0.12585 -0.08926 0.02879 -0.00414 
2 |Features -0.10224 -0.18541 -0.16963 -0.05655 
2 |Features 0.08327 0.15853 0.02869 -0.17020 
2 |Features -0.25388 -0.25438 -0.08348 0.13638 
2 |Features 0.20168 0.19566 -0.11165 -0.40739 |IsAnomaly 0

当我运行 cntk 命令尝试训练模型时，出现以下异常。

发生异常：内部文件：Matrix.cpp 行：1323 函数：Microsoft::MSR::CNTK::Matrix::SetValue -> 功能未实现。

我错过了什么？

Answer 1

这里有一些建议：

首先，输入应与 reader 中描述的数据类型相匹配。所以特征变量不应该是稀疏的，因为数据中的输入是密集的。

其次，LSTM 将输出一系列输出，输入序列中的每个样本一个。除了最后一个，你需要忽略所有。

  model = Sequential ( DenseLayer {embDim} :  # embedding
                       RecurrentLSTMLayer {hiddenDim, goBackwards=false} :  # LSTM
                       BS.Sequences.Last :    #Use only the last in the LSTM sequence
                       DenseLayer {labelDim, activation=Sigmoid}  # output layer
                     )

CNTK 抱怨功能未实现

CNTK complains about Feature Not Implemented

cntk