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)
}

我的数据如下所示：

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 命令来尝试训练模型时，出现以下异常。

发生异常：文件内部：矩阵.cpp行：1323 函数：Microsoft：：MSR：：CNTK：：矩阵：：设置值 ->功能未实现。

我错过了什么？

Answer 1

以下是一些建议：

• 首先，输入应与读取器中所述的数据类型匹配。因此，特征变量不应是稀疏变量，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对应一个输出序列。您需要忽略除最后一个之外的所有内容。

    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
                       )