---
title: BNNS
framework: accelerate
role: symbol
role_heading: Enumeration
path: accelerate/bnns
---

# BNNS

An enumeration that acts as a namespace for Swift overlays to BNNS.

## Declaration

```swift
enum BNNS
```

## Topics

### Base Classes

- [BNNS.Layer](accelerate/bnns/layer.md)
- [BNNS.UnaryLayer](accelerate/bnns/unarylayer.md)
- [BNNS.BinaryLayer](accelerate/bnns/binarylayer.md)

### Classes

- [BNNS.ActivationLayer](accelerate/bnns/activationlayer.md)
- [BNNS.BinaryArithmeticLayer](accelerate/bnns/binaryarithmeticlayer.md)
- [BNNS.BroadcastMatrixMultiplyLayer](accelerate/bnns/broadcastmatrixmultiplylayer.md)
- [BNNS.ConvolutionLayer](accelerate/bnns/convolutionlayer.md)
- [BNNS.CropResizeLayer](accelerate/bnns/cropresizelayer.md)
- [BNNS.DropoutLayer](accelerate/bnns/dropoutlayer.md)
- [BNNS.EmbeddingLayer](accelerate/bnns/embeddinglayer.md)
- [BNNS.FullyConnectedLayer](accelerate/bnns/fullyconnectedlayer.md)
- [BNNS.FusedConvolutionNormalizationLayer](accelerate/bnns/fusedconvolutionnormalizationlayer.md)
- [BNNS.FusedFullyConnectedNormalizationLayer](accelerate/bnns/fusedfullyconnectednormalizationlayer.md)
- [BNNS.FusedLayer](accelerate/bnns/fusedlayer.md)
- [BNNS.FusedParametersLayer](accelerate/bnns/fusedparameterslayer.md)
- [BNNS.GramLayer](accelerate/bnns/gramlayer.md)
- [BNNS.LossLayer](accelerate/bnns/losslayer.md)
- [BNNS.NormalizationLayer](accelerate/bnns/normalizationlayer.md)
- [BNNS.PaddingLayer](accelerate/bnns/paddinglayer.md)
- [BNNS.PermuteLayer](accelerate/bnns/permutelayer.md)
- [BNNS.PoolingLayer](accelerate/bnns/poolinglayer.md)
- [BNNS.RandomGenerator](accelerate/bnns/randomgenerator.md)
- [BNNS.RandomGeneratorState](accelerate/bnns/randomgeneratorstate.md)
- [BNNS.ReductionLayer](accelerate/bnns/reductionlayer.md)
- [BNNS.ResizeLayer](accelerate/bnns/resizelayer.md)
- [BNNS.TernaryArithmeticLayer](accelerate/bnns/ternaryarithmeticlayer.md)
- [BNNS.UnaryArithmeticLayer](accelerate/bnns/unaryarithmeticlayer.md)

### Structures

- [BNNS.AdamOptimizer](accelerate/bnns/adamoptimizer.md)
- [BNNS.AdamWOptimizer](accelerate/bnns/adamwoptimizer.md)
- [BNNS.FusedBinaryArithmeticParameters](accelerate/bnns/fusedbinaryarithmeticparameters.md)
- [BNNS.FusedConvolutionParameters](accelerate/bnns/fusedconvolutionparameters.md)
- [BNNS.FusedDequantizationParameters](accelerate/bnns/fuseddequantizationparameters.md)
- [BNNS.FusedFullyConnectedParameters](accelerate/bnns/fusedfullyconnectedparameters.md)
- [BNNS.FusedNormalizationParameters](accelerate/bnns/fusednormalizationparameters.md)
- [BNNS.FusedQuantizationParameters](accelerate/bnns/fusedquantizationparameters.md)
- [BNNS.FusedTernaryArithmeticParameters](accelerate/bnns/fusedternaryarithmeticparameters.md)
- [BNNS.FusedUnaryArithmeticParameters](accelerate/bnns/fusedunaryarithmeticparameters.md)
- [BNNS.NearestNeighbors](accelerate/bnns/nearestneighbors.md)
- [BNNS.Norm](accelerate/bnns/norm.md)
- [BNNS.RMSPropOptimizer](accelerate/bnns/rmspropoptimizer.md)
- [BNNS.RelationalOperator](accelerate/bnns/relationaloperator.md)
- [BNNS.SGDMomentumOptimizer](accelerate/bnns/sgdmomentumoptimizer.md)
- [BNNS.SparseParameters](accelerate/bnns/sparseparameters.md)

### Type Methods

- [applyActivation(activation:axes:input:output:batchSize:filterParameters:)](accelerate/bnns/applyactivation(activation:axes:input:output:batchsize:filterparameters:).md)
- [applyActivation(activation:input:output:batchSize:filterParameters:)](accelerate/bnns/applyactivation(activation:input:output:batchsize:filterparameters:).md)
- [applyInTopK(k:input:testIndices:output:axis:batchSize:filterParameters:)](accelerate/bnns/applyintopk(k:input:testindices:output:axis:batchsize:filterparameters:).md)
- [applyMatrixMultiplication(inputA:transposed:inputB:transposed:output:alpha:workspace:filterParameters:)](accelerate/bnns/applymatrixmultiplication(inputa:transposed:inputb:transposed:output:alpha:workspace:filterparameters:).md)
- [applyReduction(_:input:output:weights:filterParameters:)](accelerate/bnns/applyreduction(_:input:output:weights:filterparameters:).md)
- [applyTopK(k:input:bestValues:bestIndices:axis:batchSize:filterParameters:)](accelerate/bnns/applytopk(k:input:bestvalues:bestindices:axis:batchsize:filterparameters:).md)
- [clip(to:input:output:)](accelerate/bnns/clip(to:input:output:).md)
- [clipByGlobalNorm(threshold:inputs:outputs:globalNorm:)](accelerate/bnns/clipbyglobalnorm(threshold:inputs:outputs:globalnorm:).md)
- [clipByNorm(threshold:input:output:axes:)](accelerate/bnns/clipbynorm(threshold:input:output:axes:).md)
- [compare(_:_:using:output:)](accelerate/bnns/compare(_:_:using:output:).md)
- [computeNorm(input:output:axes:)](accelerate/bnns/computenorm(input:output:axes:).md)
- [computeNormBackward(input:output:axes:outputGradient:generatingInputGradient:)](accelerate/bnns/computenormbackward(input:output:axes:outputgradient:generatinginputgradient:).md)
- [copy(_:to:filterParameters:)](accelerate/bnns/copy(_:to:filterparameters:).md)
- [copyBandPart(_:to:lowerBandCount:upperBandCount:filterParameters:)](accelerate/bnns/copybandpart(_:to:lowerbandcount:upperbandcount:filterparameters:).md)
- [dequantize(batchSize:input:output:axis:scale:bias:filterParameters:)](accelerate/bnns/dequantize(batchsize:input:output:axis:scale:bias:filterparameters:).md)
- [gather(input:indices:output:axis:filterParameters:)](accelerate/bnns/gather(input:indices:output:axis:filterparameters:).md)
- [gatherND(input:indices:output:filterParameters:)](accelerate/bnns/gathernd(input:indices:output:filterparameters:).md)
- [matrixMultiplicationWorkspaceSize(inputA:transposed:inputB:transposed:output:alpha:filterParameters:)](accelerate/bnns/matrixmultiplicationworkspacesize(inputa:transposed:inputb:transposed:output:alpha:filterparameters:).md)
- [quantize(batchSize:input:output:axis:scale:bias:filterParameters:)](accelerate/bnns/quantize(batchsize:input:output:axis:scale:bias:filterparameters:).md)
- [scatter(input:indices:output:axis:filterParameters:)](accelerate/bnns/scatter(input:indices:output:axis:filterparameters:).md)
- [scatter(input:indices:output:axis:reductionFunction:filterParameters:)](accelerate/bnns/scatter(input:indices:output:axis:reductionfunction:filterparameters:).md)
- [scatterND(input:indices:output:filterParameters:)](accelerate/bnns/scatternd(input:indices:output:filterparameters:).md)
- [scatterND(input:indices:output:reductionFunction:filterParameters:)](accelerate/bnns/scatternd(input:indices:output:reductionfunction:filterparameters:).md)
- [shuffle(_:input:output:filterParameters:)](accelerate/bnns/shuffle(_:input:output:filterparameters:).md)
- [tile(input:output:filterParameters:)](accelerate/bnns/tile(input:output:filterparameters:).md)
- [tileBackward(outputGradient:generatingInputGradient:filterParameters:)](accelerate/bnns/tilebackward(outputgradient:generatinginputgradient:filterparameters:).md)
- [transpose(input:output:firstTransposeAxis:secondTransposeAxis:filterParameters:)](accelerate/bnns/transpose(input:output:firsttransposeaxis:secondtransposeaxis:filterparameters:).md)

### Enumerations

- [BNNS.ActivationFunction](accelerate/bnns/activationfunction.md)
- [BNNS.ArithmeticBinaryFunction](accelerate/bnns/arithmeticbinaryfunction.md)
- [BNNS.ArithmeticTernaryFunction](accelerate/bnns/arithmeticternaryfunction.md)
- [BNNS.ArithmeticUnaryFunction](accelerate/bnns/arithmeticunaryfunction.md)
- [BNNS.ConvolutionPadding](accelerate/bnns/convolutionpadding.md)
- [BNNS.ConvolutionType](accelerate/bnns/convolutiontype.md)
- [BNNS.DataLayout](accelerate/bnns/datalayout.md)
- [BNNS.DescriptorType](accelerate/bnns/descriptortype.md)
- [BNNS.Error](accelerate/bnns/error.md)
- [BNNS.GradientClipping](accelerate/bnns/gradientclipping.md)
- [BNNS.InterpolationMethod](accelerate/bnns/interpolationmethod.md)
- [BNNS.LearningPhase](accelerate/bnns/learningphase.md)
- [BNNS.LossFunction](accelerate/bnns/lossfunction.md)
- [BNNS.LossReduction](accelerate/bnns/lossreduction.md)
- [BNNS.NormalizationType](accelerate/bnns/normalizationtype.md)
- [BNNS.PaddingMode](accelerate/bnns/paddingmode.md)
- [BNNS.PoolingType](accelerate/bnns/poolingtype.md)
- [BNNS.RandomGeneratorMethod](accelerate/bnns/randomgeneratormethod.md)
- [BNNS.ReductionFunction](accelerate/bnns/reductionfunction.md)
- [BNNS.Shape](accelerate/bnns/shape.md)
- [BNNS.ShuffleType](accelerate/bnns/shuffletype.md)
- [BNNS.SparseLayout](accelerate/bnns/sparselayout.md)
- [BNNS.SparsityType](accelerate/bnns/sparsitytype.md)

## See Also

### Enumerations

- [BNNSGraph](accelerate/bnnsgraph.md)