|
|
CNN: Hans Reiser Convicted
|
|
MPSCNNFullyConnected(3) MetalPerformanceShaders.framework MPSCNNFullyConnected(3) NAME
MPSCNNFullyConnected SYNOPSIS
#import <MPSCNNConvolution.h> Inherits MPSCNNConvolution. Instance Methods (nonnull instancetype) - initWithDevice:convolutionDescriptor:kernelWeights:biasTerms:flags: (nonnull instancetype) - initWithDevice:weights: (nullable instancetype) - initWithCoder:device: (nonnull instancetype) - initWithDevice: Additional Inherited Members Detailed Description This depends on Metal.framework The MPSCNNFullyConnected specifies a fully connected convolution layer a.k.a. Inner product layer. A fully connected CNN layer is one where every input channel is connected to every output channel. The kernel width is equal to width of source image and the kernel height is equal to the height of source image. Width and height of the output is 1x1. Thus, it takes a srcW x srcH x Ni MPSCNNImage, convolves it with Weights[No][SrcW][srcH][Ni] and produces a 1 x 1 x No output. The following must be true: kernelWidth == source.width kernelHeight == source.height clipRect.size.width == 1 clipRect.size.height == 1 One can think of a fully connected layer as a matrix multiplication that flattens an image into a vector of length srcW*srcH*Ni. The weights are arragned in a matrix of dimension No x (srcW*srcH*Ni) for product output vectors of length No. The strideInPixelsX, strideInPixelsY, and group must be 1. Offset is not applicable and is ignored. Since clipRect is clamped to the destination image bounds, if the destination is 1x1, one doesn't need to set the clipRect. Note that one can implement an inner product using MPSCNNConvolution by setting offset = (kernelWidth/2,kernelHeight/2) clipRect.origin = (ox,oy), clipRect.size = (1,1) strideX = strideY = group = 1 However, using the MPSCNNFullyConnected for this is better for performance as it lets us choose the most performant method which may not be possible when using a general convolution. For example, we may internally use matrix multiplication or special reduction kernels for a specific platform. Method Documentation - (nullable instancetype) initWithCoder: (NSCoder *__nonnull) aDecoder(nonnull id< MTLDevice >) device NSSecureCoding compatability While the standard NSSecureCoding/NSCoding method -initWithCoder: should work, since the file can't know which device your data is allocated on, we have to guess and may guess incorrectly. To avoid that problem, use initWithCoder:device instead. Parameters: aDecoder The NSCoder subclass with your serialized MPSKernel device The MTLDevice on which to make the MPSKernel Returns: A new MPSKernel object, or nil if failure. Reimplemented from MPSCNNConvolution. - (nonnull instancetype) initWithDevice: (nonnull id< MTLDevice >) device Standard init with default properties per filter type Parameters: device The device that the filter will be used on. May not be NULL. Returns: A pointer to the newly initialized object. This will fail, returning nil if the device is not supported. Devices must be MTLFeatureSet_iOS_GPUFamily2_v1 or later. Reimplemented from MPSCNNConvolution. - (nonnull instancetype) initWithDevice: (nonnull id< MTLDevice >) device(const MPSCNNConvolutionDescriptor *__nonnull) fullyConnectedDescriptor(const float *__nonnull) kernelWeights(const float *__nullable) biasTerms(MPSCNNConvolutionFlags) flags Initializes a fully connected kernel. Parameters: device The MTLDevice on which this MPSCNNFullyConnected filter will be used fullyConnectedDescriptor A pointer to a MPSCNNConvolutionDescriptor. strideInPixelsX, strideInPixelsY and group properties of fullyConnectedDescriptor must be set to 1 (default). kernelWeights A pointer to a weights array. Each entry is a float value. The number of entries is = inputFeatureChannels * outputFeatureChannels * kernelHeight * kernelWidth The layout of filter weight is so that it can be reinterpreted as 4D tensor (array) weight[ outputChannels ][ kernelHeight ][ kernelWidth ][ inputChannels / groups ] Weights are converted to half float (fp16) internally for best performance. biasTerms A pointer to bias terms to be applied to the convolution output. Each entry is a float value. The number of entries is = numberOfOutputFeatureMaps flags Currently unused. Pass MPSCNNConvolutionFlagsNone Returns: A valid MPSCNNConvolution object or nil, if failure. - (nonnull instancetype) initWithDevice: (nonnull id< MTLDevice >) device(nonnull id< MPSCNNConvolutionDataSource >) weights Initializes a fully connected kernel Parameters: device The MTLDevice on which this MPSCNNFullyConnected filter will be used weights A pointer to a object that conforms to the MPSCNNConvolutionDataSource protocol. The MPSCNNConvolutionDataSource protocol declares the methods that an instance of MPSCNNFullyConnected uses to obtain the weights and bias terms for the CNN fully connected filter. Returns: A valid MPSCNNFullyConnected object or nil, if failure. Reimplemented from MPSCNNConvolution. Author Generated automatically by Doxygen for MetalPerformanceShaders.framework from the source code. Version MetalPerformanceShaders-100 Thu Feb 8 2018 MPSCNNFullyConnected(3)
