Loading TOC...

cntk functions

The table below lists all the cntk built-in functions (in this namespace: ).

CNTK library integration, providing machine learning features for MarkLogic server.

328 functions
Function name Description
cntk.abs Create an instance of the CNTK built-in elementwise abs operation on the input operands.
cntk.acos Create an instance of the CNTK built-in elementwise acos operation on the input operands.
cntk.adaDeltaLearner Constructs an AdaDelta learner.
cntk.adaGradLearner Constructs an AdaGrad learner.
cntk.adamLearner Constructs an Adam learner.
cntk.alias Create a new Function instance which just aliases the specified ‘x’ Function/Variable such that the ‘Output’ of the new ‘Function’ is same as the ‘Output’ of the specified ‘x’ Function/Variable, and has the newly specified name.
cntk.allAxes Axis object representing all the axes (static and dynamic) of an operand.
cntk.allStaticAxes Axis object representing all the static axes of an operand.
cntk.argmax Create an instance of the CNTK built-in argmax operation on specified tensor input operand along the specified axis
cntk.argmin Computes the argmin of the input tensor’s elements across the specified axis.
cntk.asBlock Create a new block Function instance which just encapsulates the specified composite Function to create a new Function that appears to be a primitive.
cntk.asComposite Creates a composite Function that has the specified rootFunction as its root.
cntk.asin Create an instance of the CNTK built-in elementwise asin operation on the input operands.
cntk.asinh Create an instance of the CNTK built-in elementwise asinh operation on the input operands.
cntk.assign Assign the value in operand to ref and return the new value, ref need to be the same layout as operand.
cntk.atan Create an instance of the CNTK built-in elementwise atan operation on the input operands.
cntk.atanh Create an instance of the CNTK built-in elementwise atanh operation on the input operands.
cntk.averagePoolingLayer Layer factory function to create a average-pooling layer.
cntk.axis Construct an Axis object denoting a static axis with the specified index.
cntk.axisIsBatch Returns true if the axis is of type batch and false otherwise.
cntk.axisIsDynamic Returns true if the axis is of type dynamic and false otherwise.
cntk.axisIsOrdered Returns True if the axis is ordered; i.e.
cntk.axisIsSequence Returns true if the axis is of type sequence and false otherwise.
cntk.axisIsStatic Returns true if the axis is of type static and false otherwise.
cntk.axisName Returns the name of this axis.
cntk.axisStaticIndex Returns True if the axis is of type static and False otherwise
cntk.batch Constructs a batch of cntk:value as a cntk:value.
cntk.batchNormalization Normalizes layer outputs for every minibatch for each output (feature) independently and applies affine transformation to preserve representation of the layer.
cntk.batchNormalizationLayer Layer factory function to create a batch-normalization layer.
cntk.batchOfSequences Constructs a batch of CNTK sequences as a cntk:value.
cntk.bernoulliRandom Create an instance of a Bernoulli random operation.
cntk.bernoulliRandomLike Create an instance of a Bernoulli random operation.
cntk.bilinearInitializer Returns a bilinear parameter initializer.
cntk.binaryCrossEntropy Computes the binary cross entropy (aka logistic loss) between the output and target.
cntk.broadcastAs Creates a sequence out of a non-sequence by endowing the operand with dynamic axes of the same type as the broadcast_as_operand and broadcasting the value of the operand along those dynamic axes.
cntk.ceil Create an instance of the CNTK built-in elementwise ceil operation on the input operands.
cntk.classificationError This operation computes the classification error.
cntk.clip Computes a tensor with all of its values clipped to fall between min_value and max_value, i.e.
cntk.combine Create a new Function instance which just combines the outputs of the specified list of ‘operands’ Functions such that the ‘Outputs’ of the new ‘Function’ are union of the ‘Outputs’ of each of the specified ‘operands’ Functions.
cntk.concatenateShape Creates a new shape, concatenating the two supplied shapes.
cntk.constant Constructs a constant from a scalar value.
cntk.constantCloneAs Clone the constant as a different data type.
cntk.constantFromValue Constructs a constant from a cntk:value, that is not a sequence or batch.
cntk.constantInitializer Returns a constant parameter initializer.
cntk.constantRecordValueUpdate After setting the value of constant, update the record.
cntk.constantSetValue Sets the value of the constant using a cntk:value that is not a sequence or batch.
cntk.constantValue Returns the value of the constant.
cntk.convolution Computes the convolution of convolution_map (typically a tensor of learnable parameters) with operand (commonly an image or output of a previous convolution/pooling operation).
cntk.convolution1dLayer Layer factory function to create a convolution-1D layer.
cntk.convolution2dLayer Layer factory function to create a convolution-2D layer.
cntk.convolution3dLayer Layer factory function to create a convolution-3D layer.
cntk.convolutionLayer Layer factory function to create a convolution layer.
cntk.convolutionTranspose Layer factory function to create a convolution transpose layer.
cntk.convolutionTranspose1dLayer Layer factory function to create a convolution-transpose-1D layer.
cntk.convolutionTranspose2dLayer Layer factory function to create a convolution-transpose-2D layer.
cntk.convolutionTranspose3dLayer Layer factory function to create a convolution-transpose-3D layer.
cntk.convolutionTransposeLayer Layer factory function to create a convolution-transpose layer.
cntk.convolutionTransposeWithExplicitPadding Convolution transpose with explicit lower and upper pad values
cntk.cos Create an instance of the CNTK built-in elementwise cos operation on the input operands.
cntk.cosh Create an instance of the CNTK built-in elementwise cosh operation on the input operands.
cntk.cosineDistance Create an instance of the CNTK built-in operation to compute the cosine distance for the specified input operands.
cntk.cosineDistanceWithNegativeSamples Given minibatches for x and y, this function computes for each element in x the cosine distance between it and the corresponding y and additionally the cosine distance between x and some other elements of y (referred to a negative samples).
cntk.cpu Returns the CPU device.
cntk.crossEntropyWithSoftmax This operation computes the cross entropy between the target_vector and the softmax of the output_vector.
cntk.customProxyOp A proxy node that helps saving a model with different number of operands.
cntk.defaultBatchAxis Returns an Axis object representing the batch axis
cntk.defaultDevice Returns the default device.
cntk.defaultInputVariableDynamicAxes Returns the default input variable dynamic axes.
cntk.denseLayer The creates a dense layer and apply it to operand.
cntk.depthToSpace Rearranges elements in the input tensor from the depth dimension into spatial blocks.
cntk.dropout Each element of the input is independently set to 0 with probability dropout_rate or to 1 / (1 - dropout_rate) times its original value (with probability 1-dropout_rate).
cntk.dropoutLayer Layer factory function to create a dropout layer.
cntk.dynamicAxis Creates a dynamic axis.
cntk.editDistanceError Edit distance error evaluation function with the option of specifying penalty of substitution, deletion and insertion, as well as squashing the input sequences and ignoring certain samples.
cntk.elementAnd Create an instance of the CNTK built-in elementwise AND logical operation on the input operands.
cntk.elementDivide Create an instance of the CNTK built-in elementwise division operation on specified tensor input operands.
cntk.elementMax Compute the element wise maximum operation between the given operands.
cntk.elementMin Compute the element wise minimum operation between the given operands.
cntk.elementNot Create an instance of the CNTK built-in elementwise NOT logical operation on the input operands.
cntk.elementOr Create an instance of the CNTK built-in elementwise OR logical operation on the input operands.
cntk.elementSelect Return either value_if_true or value_if_false based on the value of flag.
cntk.elementTimes Create an instance of the CNTK built-in elementwise multiplication operation on specified tensor input operands.
cntk.elementXor Create an instance of the CNTK built-in elementwise XOR logical operation on the input operands.
cntk.elu Create an instance of the CNTK built-in elementwise exponential linear unit operation with the specified input operand.
cntk.eluWithAlpha Exponential linear unit operation.
cntk.embeddingLayer Construct an embedding layer based and apply on operand.
cntk.endStaticAxis Returns an axis representing the default end static axis.
cntk.equal Create an instance of the CNTK built-in elementwise equality comparison operation on specified tensor input operands.
cntk.evaluate Evaluate a CNTK model/function using specified input values.
cntk.exp Create an instance of the CNTK built-in elementwise exp operation on the input operands.
cntk.expandDims Adds a singleton (size 1) axis at position axis.
cntk.eyeLike Create an instance of a eye-like operation.
cntk.flatten Create an instance of a flatten operation that reshape the specified tensor into 2D tensor.
cntk.flattenOnAxis Create an instance of a flatten operation that reshape the specified tensor into 2D tensor.
cntk.floor Create an instance of the CNTK built-in elementwise floor operation on the input operands.
cntk.forwardBackward Criterion node for training methods that rely on forward-backward Viterbi-like passes, e.g.
cntk.fsAdaGradLearner Constructs an FSAdaGrad learner.
cntk.function Constructs a CNTK model/function from the binary node.
cntk.functionArguments Returns all arguments of a CNTK model, as a sequence of cntk:variable.
cntk.functionConstants Returns the constants of a CNTK model, as a sequence of cntk:constant
cntk.functionFromVariable Creates a pass-through function of the specified variable.
cntk.functionIsBlock Returns a boolean indicating if this Function is a block Function
cntk.functionIsComposite Returns a boolean indicating if this Function is a composite Function
cntk.functionIsPrimitive Returns a boolean indicating if this Function is a primitive Function
cntk.functionName Returns the name of this function.
cntk.functionOpName Returns the name of the operation that this function denotes.
cntk.functionOutput Returns the output variable of a CNTK model.
cntk.functionOutputs Returns the output variables of a CNTK model, as a sequence of cntk:variable
cntk.functionParameters Returns the parameters of a CNTK model, as a sequence of cntk:parameter
cntk.functionSave Serializes a cntk:function as a node.
cntk.futureValue This function returns the future value w.r.t.
cntk.gatherOp Create an instance of the CNTK build-in operation to get a tensor that is gathered from reference tensor by indices.
cntk.gatherOpOnAxis Create an instance of the CNTK build-in operation to get a tensor that is gathered from reference tensor by indices.
cntk.globalAveragePoolingLayer Layer factory function to create a global-average-pooling layer.
cntk.globalMaxPoolingLayer Layer factory function to create a global-max-pooling layer.
cntk.glorotNormalInitializer Returns a glorot normal parameter initializer.
cntk.glorotUniformInitializer Returns a glorot uniform parameter initializer.
cntk.gpu Returns the GPU device based on provided CUDA device ID.
cntk.greater Create an instance of the CNTK built-in elementwise greater than comparison operation on specified tensor input operands.
cntk.greaterEqual Create an instance of the CNTK built-in elementwise greater than or equal to comparison operation on specified tensor input operands.
cntk.gruBlock Layer factory function to create a gru block.
cntk.gruLayer Layer factory function to create a GRU layer.
cntk.gumbelRandom Create an instance of a Gumbel random operation.
cntk.gumbelRandomLike Create an instance of a Gumbel random operation.
cntk.hardmax Create an instance of the CNTK built-in elementwise hardmax operation on the input operands.
cntk.hardSigmoid Create an instance of hard sigmoid operation: f(x) = max(0,min(alpha*x+beta,1))
cntk.heNormalInitializer Returns a He normal parameter initializer.
cntk.heUniformInitializer Returns a He uniform parameter initializer.
cntk.imageScaler Alteration of image by scaling its individual values.
cntk.inputVariable Constructs an input variable.
cntk.labelLayer Layer factory function to create a label layer.
cntk.labelsToGraph Conversion node from labels to graph.
cntk.lambdaRank Groups samples according to group, sorts them within each group based on output and computes the Normalized Discounted Cumulative Gain (NDCG) at infinity for each group.
cntk.latticeSequenceWithSoftmax lattice-sequence-with-softmax.
cntk.layerNormalizationLayer Layer factory function to create a layer-normalization layer.
cntk.leakyReLu Leaky Rectified linear operation.
cntk.learningRateScheduleFromConstant Returns a learning rate schedule, where the learning rate is fixed throughout the whole training process.
cntk.learningRateScheduleFromPairs Returns a learning rate schedule, based on a sequence of pairs of "number of epochs" and "their learning rate".
cntk.learningRateScheduleFromSequence Returns a learning rate schedule, based on a sequence of learning rates.
cntk.less Create an instance of the CNTK built-in elementwise less than comparison operation on specified tensor input operands.
cntk.lessEqual Create an instance of the CNTK built-in elementwise less than or equal to comparison operation on specified tensor input operands.
cntk.localResponseNormalization Local Response Normalization layer.
cntk.log Create an instance of the CNTK built-in elementwise log operation on the input operands.
cntk.logAddExp Create an instance of the CNTK built-in elementwise tensor operation that computes the log of the sum of the exponentials of the specified input operands.
cntk.logSoftmax Create an instance of the CNTK built-in log softmax operation on a specified tensor input operand
cntk.logSoftmaxOnAxis Create an instance of the CNTK built-in log softmax operation on specified axis on a specified tensor input operand
cntk.lstmBlock Layer factory function to create a lstm block.
cntk.lstmLayer Layer factory function to create a LSTM layer.
cntk.maxPoolingLayer Layer factory function to create a max-pooling layer.
cntk.maxUnpoolingLayer Layer factory function to create a global-average-pooling layer.
cntk.mean Create a new Function instance that computes element-wise mean of input tensors.
cntk.meanVarianceNormalization Computes mean-variance normalization of the specified input operand.
cntk.minibatchSizeScheduleFromConstant Returns a minibatch size schedule, where the minibatch size remains the same.
cntk.minibatchSizeScheduleFromPairs Returns a minibatch size schedule.
cntk.minibatchSizeScheduleFromSequence Returns a minibatch size schedule, based on a sequence of minibatch sizes.
cntk.minus Create an instance of the CNTK built-in elementwise tensor subtraction operation with the specified input operands.
cntk.momentumScheduleFromConstant Returns a momentum schedule where the momentum decay rate is fixed.
cntk.momentumScheduleFromPairs Returns a momentum schedule.
cntk.momentumScheduleFromSequence Returns a momentum schedule, based on a sequence of momentum decay rates.
cntk.momentumSgdLearner Constructs an momentum SGD learner.
cntk.ndcgat1 Create an instance of the CNTK built-in operation for evaluating the NDCG at 1 metric
cntk.negate Create an instance of the CNTK built-in elementwise negate operation on the input operands.
cntk.nesterovLearner Constructs an Nesterov learner.
cntk.newUniqueDynamicAxis Creates an Axis object representing a new unique dynamic axis.
cntk.normalInitializer Returns a normal parameter initializer.
cntk.normalRandom Create an instance of a uniform random operation.
cntk.normalRandomLike Create an instance of a normal random operation.
cntk.notEqual Create an instance of the CNTK built-in elementwise not-equal comparison operation on specified tensor input operands.
cntk.oneHotOp Create one hot tensor based on the input tensor.
cntk.onesLike Create an instance of a ones-like operation.
cntk.operandSequenceAxis Returns an axis representing the sequence axis (ordered dynamic axis) of an operand whose dynamic axes have not yet been inferred/resolved (i.e.
cntk.optimizedRnnstack An RNN implementation that uses the primitives in cuDNN.
cntk.outputVariable Constructs an output variable.
cntk.pad Pads a tensor according to the specified patterns.
cntk.parameter Constructs a parameter from a parameter initializer.
cntk.parameterFromScalar Constructs a parameter from a scalar value.
cntk.parameterFromValue Constructs a parameter from a cntk:value that is not a sequence or batch.
cntk.parameterRecordValueUpdate After setting the value of parameter, update the record.
cntk.parameterSetValue Sets the value of the parameter, using a cntk:value that is not a sequence or batch.
cntk.parameterValue Returns the value of the parameter.
cntk.pastValue This function returns the past value w.r.t.
cntk.perDimMeanVarianceNormalize Computes per dimension mean-variance normalization of the specified input operand.
cntk.placeholderVariable Constructs a placeholder variable.
cntk.plus Create an instance of the CNTK built-in elementwise tensor addition operation with the specified input operands.
cntk.pooling The pooling operations compute a new tensor by selecting the maximum or average value in the pooling input.
cntk.poolingWithExplicitPadding The pooling operations compute a new tensor by selecting the maximum or average value in the pooling input.
cntk.pow Create an instance of the CNTK built-in elementwise tensor operation that computes the leftOperand raised to the power of the right operand.
cntk.preLu Create an instance of the CNTK built-in elementwise parametric rectified linear Unit operation with the specified input operand and learning parameter alpha.
cntk.previousMinibatchEvaluationAverage Average evaluation function value of the previous minibatch.
cntk.previousMinibatchLossAverage Average loss function value of the previous minibatch.
cntk.previousMinibatchSampleCount Number of sample encountered in the previous minibatch.
cntk.randomInitializerWithRank Overrides $output-rank and $filter-rank specification in a random initializer constructed without an explicit rank specification.
cntk.randomSample Estimates inclusion frequencies for random sampling with or without replacement.
cntk.randomSampleInclusionFrequency For weighted sampling with the specified sample size (num_samples) this operation computes the expected number of occurrences of each class in the sampled set.
cntk.reciprocal Create an instance of the CNTK built-in elementwise reciprocal operation on the input operands.
cntk.reconcileDynamicAxes Create a new Function instance which reconciles the dynamic axes of the specified tensor operands.
cntk.reduceL1 Computes the L1 norm of the input tensor’s element along the provided axes.
cntk.reduceL2 Computes the L2 norm of the input tensor’s element along the provided axes.
cntk.reduceLogSum Create an instance of the CNTK built-in LogSum reduction operation on specified tensor input operand along the specified axis
cntk.reduceLogSumOnAxes Create an instance of the CNTK built-in LogSum reduction operation on specified tensor input operand along the specified axis
cntk.reduceMax Create an instance of the CNTK built-in Max reduction operation on specified tensor input operand along the specified axis
cntk.reduceMaxOnAxes Create an instance of the CNTK built-in Max reduction operation on specified tensor input operand along the specified axis
cntk.reduceMean Computes the mean of the input tensor’s elements across a specified axis or a list of specified axes.
cntk.reduceMeanOnAxes Create an instance of the CNTK built-in Mean reduction operation on specified tensor input operand along the specified axis
cntk.reduceMin Create an instance of the CNTK built-in Min reduction operation on specified tensor input operand along the specified axis
cntk.reduceMinOnAxes Create an instance of the CNTK built-in Mean reduction operation on specified tensor input operand along the specified axis
cntk.reduceProd Computes the min of the input tensor’s elements across the specified axis.
cntk.reduceProdOnAxes Create an instance of the CNTK built-in Prod reduction operation on specified tensor input operand along the specified axis
cntk.reduceSum Computes the sum of the input tensor’s elements across one axis or a list of axes.
cntk.reduceSumOnAxes Computes the sum of the input tensor’s elements across one axis or a list of axes.
cntk.reduceSumSquare Computes the sum square of the input tensor’s element along the provided axes.
cntk.relu Create an instance of the CNTK built-in elementwise relu operation on the input operands.
cntk.reshape Reinterpret input samples as having different tensor dimensions One dimension may be specified as 0 and will be inferred.
cntk.rmsPropLearner Constructs an RMSProp learner.
cntk.rnnStepBlock Layer factory function to create a rnn-step block.
cntk.rnnStepLayer Layer factory function to create a RNN Step layer.
cntk.ROIPooling The ROI-pooling operation computes a new matrix by selecting the maximum (max pooling) value in the pooling input for each region of interest (ROI).
cntk.round Create an instance of the CNTK built-in elementwise round operation on the input operands.
cntk.scalar Constructs a scalar, which is a zero dimensional constant.
cntk.selu Scaled exponential linear unit operation.
cntk.sequence Constructs a CNTK sequence as a cntk:value type.
cntk.sequenceDelay This function combines past_value() and future_value() into a single function.
cntk.sequenceFirst Returns the first element of its symbolic input sequence
cntk.sequenceGather Takes two sequences of the same length and returns a new sequence whose elements are those elements of sequence whose corresponding element in condition is True, preserving the ordering of sequence.
cntk.sequenceGatherWithFactor Takes two sequences of the same length and returns a new sequence whose elements are those elements of sequence whose corresponding element in condition is True, preserving the ordering of sequence.
cntk.sequenceIsFirst Returns a symbolic sequence of booleans with the same length as ``seq``.
cntk.sequenceIsLast Returns a symbolic sequence of booleans with the same length as ``seq``.
cntk.sequenceLast Returns the last element of its symbolic input sequence
cntk.sequenceReduceMax Create an instance of the CNTK built-in max reduction operation on specified tensor input operand along the operands lone dynamic sequence axis
cntk.sequenceReduceSum Computes the sum of the input sequence’s elements across the sequence axis.
cntk.sequenceScatter Performs the inverse of gather.
cntk.sequenceScatterWithFactor Performs the inverse of gather.
cntk.sequenceSlice Slice the input sequence.
cntk.sequenceSoftmax Create an instance of the CNTK built-in softmax operation on specified tensor input operand along the operands lone dynamic sequence axis
cntk.sequenceUnpack Create an instance of the CNTK built-in operator for unpacking the specified sequence operand along the most significant static axis [-1] and padding any gaps with the specified padding value.
cntk.sequenceWhere Given a symbolic sequence condition of boolean-like (1/0) values, it will return a new sequence containing the indices for which the values were true.
cntk.sgdLearner Constructs an SGD learner.
cntk.shape Returns a shape object recognized by CNTK.
cntk.shapeDimensions Returns the dimensions represented by a cntk:shape object, as a sequence of unsigned long interger.
cntk.shapeFreeDimension Returns a placeholder value to use for an axis whose dimension is unbound and is only determined when actual data is bound to the variable.
cntk.shapeHasFreeDimension Returns a boolean value indicating if the dimension size for any of the axes of this shape is free.
cntk.shapeHasInferredDimension Returns a boolean value indicating if the dimension size for any of the axes of this shape is unknown/inferred.
cntk.shapeHasUnboundDimension Returns a boolean value indicating if the dimension size for any of the axes of this shape is free or inferred.
cntk.shapeInferredDimension Returns a placeholder value to use for an axis whose dimension is unknown and is to be inferred by the system.
cntk.shapeIsScalar Returns true if the shape represents a scalar.
cntk.shapeIsUnknown Returns true if the shape is an unknown shape.
cntk.shapeRank Returns the rank of the shape.
cntk.shapeTotalSize Returns the total size of the rectangular shape that this shape denotes.
cntk.sigmoid Create an instance of the CNTK built-in elementwise sigmoid operation on the input operands.
cntk.sin Create an instance of the CNTK built-in elementwise sin operation on the input operands.
cntk.sinh Create an instance of the CNTK built-in elementwise sinh operation on the input operands.
cntk.slice Create an instance of the slice operation on specified tensor input operand
cntk.sliceWithStrides Create an instance of the slice operation on specified tensor input operand
cntk.softmax Create an instance of the CNTK built-in softmax operation on specified tensor input operand
cntk.softmaxOnAxis Create an instance of the CNTK built-in softmax operation on specified axis on a specified tensor input operand
cntk.softplus Softplus operation.
cntk.softsign Computes the element-wise softsign of x.
cntk.spaceToDepth Rearranges elements in the input tensor from the spatial dimensions to the depth dimension.
cntk.splice Concatenate the input tensors along an axis.
cntk.sqrt Create an instance of the CNTK built-in elementwise sqrt operation on the input operands.
cntk.square Create an instance of the CNTK built-in elementwise square operation on the input operands.
cntk.squaredError This operation computes the sum of the squared difference between elements in the two input matrices.
cntk.squeeze Removes axes whose size is 1.
cntk.squeezeAxes Create an instance of the squeeze operation on specified tensor input operand, for the specified axis
cntk.stopGradient Outputs its input as it is and prevents any gradient contribution from its output to its input.
cntk.straightThrough Element-wise binarization node using the straight through estimator
cntk.subshape Constructs and returns a new cntk:shape object that is a subshape of $shape.
cntk.sum Create a new Function instance that computes element-wise sum of input tensors.
cntk.tan Create an instance of the CNTK built-in elementwise tan operation on the input operands.
cntk.tanh Create an instance of the CNTK built-in elementwise tanh operation on the input operands.
cntk.times The output of this operation is the matrix product of the two input matrices.
cntk.toBatch Create an instance of attach dynamic axis operation that convert the input's first static axis to dynamic axis.
cntk.topK Create an instance of the CNTK built-in top k operation over the first static axis on a specified tensor input operand
cntk.topKOnAxis Create an instance of the CNTK built-in top k operation over the first static axis on a specified tensor input operand
cntk.toSequence Create an instance of the CNTK built-in operator for converting the specified tensor operand into a sequence
cntk.toSequenceLike Create an instance of the CNTK built-in operator for converting the specified tensor operand into a sequence.
cntk.toSequenceWithLengths Create an instance of the CNTK built-in operator for converting the specified tensor operand into a sequence This overload allows specifying an additional operand containing the lengths of individual sequences
cntk.totalNumberOfSampleSeen The total number of samples seen by this trainer.
cntk.trainer Constructs a trainer, used for training a model.
cntk.trainerGetModel Returns the model being trained by this trainer.
cntk.trainMinibatch Optimize model parameter using a minibatch of training data.
cntk.transpose Create an instance of the CNTK built-in log softmax operation on specified axis on a specified tensor input operand
cntk.transposeAxes Create an instance of the CNTK built-in transpose dimensions operation on specified tensor input operand.
cntk.transposeOnAxes Permutes the axes of the tensor.
cntk.transposeTimes The output of this operation is the product of the first (left) argument with the second (right) argument transposed.
cntk.truncatedNormalInitializer Truncated normal initializer.
cntk.uniformInitializer Returns a uniform parameter initializer.
cntk.uniformRandom Create an instance of a uniform random operation.
cntk.uniformRandomLike Create an instance of a uniform random operation.
cntk.unknownDynamicAxes Returns unknown dynamic axes.
cntk.unknownShape Returns a placeholder representing an unknown shape.
cntk.unpackBatch Create an instance of detach dynamic axis operation that convert the input's last dynamic axis to static axis.
cntk.unpooling Unpools the operand using information from pooling_input.
cntk.value Constructs a cntk:value.
cntk.valueAlias Creates a new value which is an alias of this value.
cntk.valueCopyFrom Copies the contents of the source value to this Value.
cntk.valueDataType Returns the data type of this value's contents.
cntk.valueDeepClone Creates a new Value with newly allocated storage on the same device as this value and copies this value's contents into the newly allocated Value.
cntk.valueDevice Returns the descriptor of the device that this value resides on
cntk.valueErase Erase the data of the value.
cntk.valueIsReadonly Returns true if the value is readonly.
cntk.valueIsValid Returns whether this object has been invalidated (by another forward and/or backward pass)
cntk.valueShape Returns the shape of this value's contents.
cntk.valueToArray Returns a json:array object representing the actual numeric values inside the cntk:value.
cntk.variableAsString Returns the string representation of the variable.
cntk.variableCurrentValueTimeStamp Returns the timestamp of current value held by the variable.
cntk.variableDataType Returns the data type of the variable.
cntk.variableDynamicAxes Returns dynamic axes of the variable, as a sequence.
cntk.variableFromFunction Constructs an output variable aliasing the output of the specified function.
cntk.variableHasBatchAxis Returns if the variable has batch axis.
cntk.variableHasSequenceAxis Returns if the variable has sequence axis.
cntk.variableIsConstant Returns if the variable is a constant variable.
cntk.variableIsInitialized Returns if the variable is initialized.
cntk.variableIsInput Returns if the variable is an input variable.
cntk.variableIsOutput Returns if the variable is an output variable.
cntk.variableIsParameter Returns if the variable is a parameter variable.
cntk.variableIsPlaceholder Returns if the variable is a placeholder variable.
cntk.variableIsSparse Returns if the variable is sparse.
cntk.variableKind Returns the variable-kind of the variable (input, output, etc).
cntk.variableName Returns the name of the variable.
cntk.variableNeedsGradient Returns if the variable needs gradient.
cntk.variableOwner Returns the function of which the specified variable is an output.
cntk.variableShape Returns the shape of the variable.
cntk.variableUid Returns the uid of the variable, as a string.
cntk.variableValue Returns the value of the variable.
cntk.weightedBinaryCrossEntropy This operation computes the weighted binary cross entropy (aka logistic loss) between the output and target.
cntk.xavierInitializer Returns a xavier parameter initializer.
cntk.zerosLike Create an instance of a zeros-like operation.