通过

你当前正在访问 Microsoft Azure Global Edition 技术文档网站。 如果需要访问由世纪互联运营的 Microsoft Azure 中国技术文档网站，请访问 https://docs.azure.cn。

BrainScript 完整函数参考

本部分提供有关 BrainScript 内置函数的信息。

可以在 CNTK 二进制文件旁边的 CNTK.core.bs 中找到所有内置函数的声明。

基元操作和层在全局命名空间中声明。 其他操作在命名空间中声明，并带有相应的前缀（例如 BS.RNN.LSTMP）。

层

层构建

激活函数

元素运算，一元运算

元素操作，二进制

元素运算，三元运算

矩阵产品和卷积运算

  • Times(A, B, outputRank=1)
    A * B
  • TransposeTimes(A, B, outputRank=1)
  • Convolution(weights, x, kernelShape, mapDims=(0), stride=(1), sharing=(true), autoPadding=(true), lowerPadding=(0), upperPadding=(0), imageLayout='CHW', maxTempMemSizeInSamples=0)
  • Pooling(x, poolKind/*'max'|'average'*/, kernelShape, stride=(1), autoPadding=(true), lowerPadding=(0), upperPadding=(0), imageLayout='CHW')
  • ROIPooling(x, rois, roiOutputShape, spatialScale=1.0/16.0)

可学习的参数和常量

  • ParameterTensor {shape, learningRateMultiplier=1.0, init='uniform'/*|gaussian*/, initValueScale=1.0, initValue=0.0, randomSeed=-1, initFromFilePath=''}
  • Constant {scalarValue, rows = 1, cols = 1}
  • BS.Constants.Zero，BS.Constants.One
    BS.Constants.True、BS.Constants.False、BS.Constants.None
  • BS.Constants.OnesTensor (shape)
  • BS.Constants.ZeroSequenceLike (x)

输入

  • Input (shape, dynamicAxis='', sparse=false, tag='feature')
  • DynamicAxis{}
  • EnvironmentInput (propertyName)
    Mean (x)，InvStdDev (x)

丢失函数和指标

减少

训练操作

  • BatchNormalization (input, scale, bias, runMean, runInvStdDev, spatial, normalizationTimeConstant = 0, blendTimeConstant = 0, epsilon = 0.00001, useCntkEngine = true, imageLayout='CHW')
  • Dropout (x)
  • Stabilize (x, enabled=true)
    StabilizeElements (x, inputDim=x.dim, enabled=true)
  • CosDistanceWithNegativeSamples (x, y, numShifts, numNegSamples)

重塑操作

  • CNTK2.Reshape (x, shape, beginAxis=0, endAxis=0)
    ReshapeDimension (x, axis, shape) = CNTK2.Reshape (x, shape, beginAxis=axis, endAxis=axis + 1)
    FlattenDimensions (x, axis, num) = CNTK2.Reshape (x, 0, beginAxis=axis, endAxis=axis + num)
    SplitDimension (x, axis, N) = ReshapeDimension (x, axis, 0:N)
  • Slice (beginIndex, endIndex, input, axis=1)
    BS.Sequences.First (x) = Slice (0, 1, x, axis=-1)
    BS.Sequences.Last (x) = Slice (-1, 0, x, axis=-1)
  • Splice (inputs, axis=1)
  • TransposeDimensions (x, axis1, axis2)
    Transpose (x) = TransposeDimensions (x, 1, 2)
  • BS.Sequences.BroadcastSequenceAs (type, data1)
  • BS.Sequences.Gather (where, x)
    BS.Sequences.Scatter (where, y)
    BS.Sequences.IsFirst (x)
    BS.Sequences.IsLast (x)

复发

  • OptimizedRNNStack(weights, input, hiddenDims, numLayers=1, bidirectional=false, recurrentOp='lstm')
  • BS.Loop.Previous (x, timeStep=1, defaultHiddenActivation=0)
    PastValue (shape, x, defaultHiddenActivation=0.1, ...) = BS.Loop.Previous (0, shape, ...)
  • BS.Loop.Next (x, timeStep=1, defaultHiddenActivation=0)
    FutureValue (shape, x, defaultHiddenActivation=0.1, ...) = BS.Loop.Next (0, shape, ...)
  • LSTMP (outputDim, cellDim=outputDim, x, inputDim=x.shape, aux=BS.Constants.None, auxDim=aux.shape, prevState, enableSelfStabilization=false)
  • BS.Boolean.Toggle (clk, initialValue=BS.Constants.False)
  • BS.RNNs.RecurrentLSTMP (outputDim, cellDim=outputDim, x, inputDim=x.shape, previousHook=BS.RNNs.PreviousHC, augmentInputHook=NoAuxInputHook, augmentInputDim=0, layerIndex=0, enableSelfStabilization=false)
  • BS.RNNs.RecurrentLSTMPStack (layerShapes, cellDims=layerShapes, input, inputShape=input.shape, previousHook=PreviousHC, augmentInputHook=NoAuxInputHook, augmentInputShape=0, enableSelfStabilization=false)
  • BS.RNNs.RecurrentBirectionalLSTMPStack (layerShapes, cellDims=layerShapes, input, inputShape=input.dim, previousHook=PreviousHC, nextHook=NextHC, enableSelfStabilization=false)

序列到序列支持

  • BS.Seq2Seq.CreateAugmentWithFixedWindowAttentionHook (attentionDim, attentionSpan, decoderDynamicAxis, encoderOutput, enableSelfStabilization=false)
  • BS.Seq2Seq.GreedySequenceDecoderFrom (modelAsTrained)
  • BS.Seq2Seq.BeamSearchSequenceDecoderFrom (modelAsTrained, beamDepth)

特殊用途操作

  • ClassBasedCrossEntropyWithSoftmax (labelClassDescriptorVectorSequence, mainInputInfo, mainWeight, classLogProbsBeforeSoftmax)

模型编辑

其他

  • Fail (what)
  • IsSameObject (a, b)
  • Trace (node, say='', logFrequency=traceFrequency, logFirst=10, logGradientToo=false, onlyUpToRow=100000000, onlyUpToT=100000000, format=[])

荒废的

  • ErrorPrediction (labels, nonNormalizedLogClassPosteriors)
  • ColumnElementTimes (...) = ElementTimes (...)
  • DiagTimes (...) = ElementTimes (...)
  • LearnableParameter(...) = Parameter(...)
  • LookupTable (embeddingMatrix, inputTensor)
  • RowRepeat (input, numRepeats)
  • RowSlice (beginIndex, numRows, input) = Slice(beginIndex, beginIndex + numRows, input, axis = 1)
  • RowStack (inputs)
  • RowElementTimes (...) = ElementTimes (...)
  • Scale (...) = ElementTimes (...)
  • ConstantTensor (scalarVal, shape)
    Parameter (outputDim, inputDim, ...) = ParameterTensor ((outputDim:input), ...)
    WeightParam (outputDim, inputDim) = Parameter (outputDim, inputDim, init='uniform', initValueScale=1, initOnCPUOnly=true, randomSeed=1)
    DiagWeightParam (outputDim) = ParameterTensor ((outputDim), init='uniform', initValueScale=1, initOnCPUOnly=true, randomSeed=1)
    BiasParam (dim) = ParameterTensor ((dim), init='fixedValue', value=0.0)
    ScalarParam() = BiasParam (1)
  • SparseInput (shape, dynamicAxis='', tag='feature')
    ImageInput (imageWidth, imageHeight, imageChannels, imageLayout='CHW', dynamicAxis='', tag='feature')
    SparseImageInput (imageWidth, imageHeight, imageChannels, imageLayout='CHW', dynamicAxis='', tag='feature')
  • MeanVarNorm(feat) = PerDimMeanVarNormalization(feat, Mean (feat), InvStdDev (feat))
    PerDimMeanVarNormalization (x, mean, invStdDev)，
    PerDimMeanVarDeNormalization (x, mean, invStdDev)
  • ReconcileDynamicAxis (dataInput, layoutInput)
  • Last updated on