MPSRNNSingleGateDescriptor(3)

NAME

       MPSRNNSingleGateDescriptor

SYNOPSIS

       #import <MPSRNNLayer.h>

       Inherits MPSRNNDescriptor.

   Class Methods
       (nonnull instancetype) +
           createRNNSingleGateDescriptorWithInputFeatureChannels:outputFeatureChannels:

   Properties
       id< MPSCNNConvolutionDataSource > inputWeights
       id< MPSCNNConvolutionDataSource > recurrentWeights

Detailed Description

       This depends on Metal.framework  The MPSRNNSingleGateDescriptor
       specifies a simple recurrent block/layer descriptor. The RNN layer
       initialized with a MPSRNNSingleGateDescriptor transforms the input data
       (image or matrix), and previous output with a set of filters, each
       producing one feature map in the new output data. The user may provide
       the RNN unit a single input or a sequence of inputs.

       Description of operation:



       Let x_j be the input data (at time index t of sequence, j index
       containing quadruplet: batch index, x,y and feature index (x=y=0 for
       matrices)). Let h0_j be the recurrent input (previous output) data from
       previous time step (at time index t-1 of sequence). Let h1_i be the
       output data produced at this time step.

       Let W_ij, U_ij be the weights for input and recurrent input data
       respectively Let b_i be a bias term

       Let gi(x) be a neuron activation function

       Then the new output image h1_i data is computed as follows:

       h1_i = gi( W_ij * x_j + U_ij * h0_j  + b_i )



       The '*' stands for convolution (see MPSRNNImageInferenceLayer) or
       matrix-vector/matrix multiplication (see MPSRNNMatrixInferenceLayer).
       Summation is over index j (except for the batch index), but there is no
       summation over repeated index i - the output index. Note that for
       validity all intermediate images have to be of same size and the U
       matrix has to be square (ie. outputFeatureChannels ==
       inputFeatureChannels in those). Also the bias terms are scalars wrt.
       spatial dimensions.

Method Documentation

   + (nonnull instancetype)
       createRNNSingleGateDescriptorWithInputFeatureChannels: (NSUInteger)
       inputFeatureChannels(NSUInteger) outputFeatureChannels
       Creates a MPSRNNSingleGateDescriptor

       Parameters:
           inputFeatureChannels The number of feature channels in the input
           image/matrix. Must be >= 1.
           outputFeatureChannels The number of feature channels in the output
           image/matrix. Must be >= 1.

       Returns:
           A valid MPSRNNSingleGateDescriptor object or nil, if failure.

Property Documentation

   - inputWeights [read],  [write],  [nonatomic],  [retain]
       Contains weights 'W_ij', bias 'b_i' and neuron 'gi' from the simple RNN
       layer formula. If nil then assumed zero weights, bias and no neuron
       (identity mapping). Defaults to nil.

   - recurrentWeights [read],  [write],  [nonatomic],  [retain]
       Contains weights 'U_ij' from the simple RNN layer formula. If nil then
       assumed zero weights. Defaults to nil.

Author

       Generated automatically by Doxygen for
       MetalPerformanceShaders.framework from the source code.





Version MetalPerformanceShaders-Thu2Jul 13 2017  MPSRNNSingleGateDescriptor(3)


Mac OS X 10.12.6 - Generated Tue Oct 31 19:56:11 CDT 2017