BNNS

Declaration

enum BNNS

Topics

Base Classes

• BNNS.Layer
• BNNS.UnaryLayer
• BNNS.BinaryLayer

Classes

• BNNS.ActivationLayer
• BNNS.BinaryArithmeticLayer
• BNNS.BroadcastMatrixMultiplyLayer
• BNNS.ConvolutionLayer
• BNNS.CropResizeLayer
• BNNS.DropoutLayer
• BNNS.EmbeddingLayer
• BNNS.FullyConnectedLayer
• BNNS.FusedConvolutionNormalizationLayer
• BNNS.FusedFullyConnectedNormalizationLayer
• BNNS.FusedLayer
• BNNS.FusedParametersLayer
• BNNS.GramLayer
• BNNS.LossLayer
• BNNS.NormalizationLayer
• BNNS.PaddingLayer
• BNNS.PermuteLayer
• BNNS.PoolingLayer
• BNNS.RandomGenerator
• BNNS.RandomGeneratorState
• BNNS.ReductionLayer
• BNNS.ResizeLayer
• BNNS.TernaryArithmeticLayer
• BNNS.UnaryArithmeticLayer

Structures

• BNNS.AdamOptimizer
• BNNS.AdamWOptimizer
• BNNS.FusedBinaryArithmeticParameters
• BNNS.FusedConvolutionParameters
• BNNS.FusedDequantizationParameters
• BNNS.FusedFullyConnectedParameters
• BNNS.FusedNormalizationParameters
• BNNS.FusedQuantizationParameters
• BNNS.FusedTernaryArithmeticParameters
• BNNS.FusedUnaryArithmeticParameters
• BNNS.NearestNeighbors
• BNNS.Norm
• BNNS.RMSPropOptimizer
• BNNS.RelationalOperator
• BNNS.SGDMomentumOptimizer
• BNNS.SparseParameters

Type Methods

• applyActivation(activation:axes:input:output:batchSize:filterParameters:)
• applyActivation(activation:input:output:batchSize:filterParameters:)
• applyInTopK(k:input:testIndices:output:axis:batchSize:filterParameters:)
• applyMatrixMultiplication(inputA:transposed:inputB:transposed:output:alpha:workspace:filterParameters:)
• applyReduction(_:input:output:weights:filterParameters:)
• applyTopK(k:input:bestValues:bestIndices:axis:batchSize:filterParameters:)
• clip(to:input:output:)
• clipByGlobalNorm(threshold:inputs:outputs:globalNorm:)
• clipByNorm(threshold:input:output:axes:)
• compare(_:_:using:output:)
• computeNorm(input:output:axes:)
• computeNormBackward(input:output:axes:outputGradient:generatingInputGradient:)
• copy(_:to:filterParameters:)
• copyBandPart(_:to:lowerBandCount:upperBandCount:filterParameters:)
• dequantize(batchSize:input:output:axis:scale:bias:filterParameters:)
• gather(input:indices:output:axis:filterParameters:)
• gatherND(input:indices:output:filterParameters:)
• matrixMultiplicationWorkspaceSize(inputA:transposed:inputB:transposed:output:alpha:filterParameters:)
• quantize(batchSize:input:output:axis:scale:bias:filterParameters:)
• scatter(input:indices:output:axis:filterParameters:)
• scatter(input:indices:output:axis:reductionFunction:filterParameters:)
• scatterND(input:indices:output:filterParameters:)
• scatterND(input:indices:output:reductionFunction:filterParameters:)
• shuffle(_:input:output:filterParameters:)
• tile(input:output:filterParameters:)
• tileBackward(outputGradient:generatingInputGradient:filterParameters:)
• transpose(input:output:firstTransposeAxis:secondTransposeAxis:filterParameters:)

Enumerations

• BNNS.ActivationFunction
• BNNS.ArithmeticBinaryFunction
• BNNS.ArithmeticTernaryFunction
• BNNS.ArithmeticUnaryFunction
• BNNS.ConvolutionPadding
• BNNS.ConvolutionType
• BNNS.DataLayout
• BNNS.DescriptorType
• BNNS.Error
• BNNS.GradientClipping
• BNNS.InterpolationMethod
• BNNS.LearningPhase
• BNNS.LossFunction
• BNNS.LossReduction
• BNNS.NormalizationType
• BNNS.PaddingMode
• BNNS.PoolingType
• BNNS.RandomGeneratorMethod
• BNNS.ReductionFunction
• BNNS.Shape
• BNNS.ShuffleType
• BNNS.SparseLayout
• BNNS.SparsityType

See Also

Enumerations

• BNNSGraph