Class

MPSCNNBinaryFullyConnected

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

Declaration

@interface MPSCNNBinaryFullyConnected : MPSCNNBinaryConvolution

Topics

Initializers

- initWithCoder:device:

Initializes a fully connected convolution layer with binary weights.

- initWithDevice:convolutionData:scaleValue:type:flags:

Initializes a fully connected convolution layer with binary weights.

MPSCNNConvolutionDataSource

The protocol that provides convolution filter weights and bias terms.

MPSCNNBinaryConvolutionType

Options that defines what operations are used to perform binary convolution.

MPSCNNBinaryConvolutionFlags

Options used to control binary convolution kernels.

Relationships

See Also

Fully Connected Layers

MPSCNNFullyConnected

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

MPSCNNFullyConnectedGradient

A gradient fully connected convolution layer.

Beta Software

This documentation contains preliminary information about an API or technology in development. This information is subject to change, and software implemented according to this documentation should be tested with final operating system software.

Learn more about using Apple's beta software