Class

MPSCNNBinaryFullyConnectedNode

A representation of a fully connected convolution layer with binary weights and optionally binarized input image.

Declaration

class MPSCNNBinaryFullyConnectedNode : MPSCNNBinaryConvolutionNode

Topics

Initializers

init(source: MPSNNImageNode, weights: MPSCNNConvolutionDataSource, scaleValue: Float, type: MPSCNNBinaryConvolutionType, flags: MPSCNNBinaryConvolutionFlags)
protocol MPSCNNConvolutionDataSource

The protocol that provides convolution filter weights and bias terms.

init(source: MPSNNImageNode, weights: MPSCNNConvolutionDataSource, outputBiasTerms: UnsafePointer<Float>?, outputScaleTerms: UnsafePointer<Float>?, inputBiasTerms: UnsafePointer<Float>?, inputScaleTerms: UnsafePointer<Float>?, type: MPSCNNBinaryConvolutionType, flags: MPSCNNBinaryConvolutionFlags)

Relationships

Inherits From

Conforms To

See Also

Fully Connected Layer Nodes

class MPSCNNFullyConnectedNode

A representation of a fully connected convolution layer, also known as an inner product layer.