Package apple.metalperformanceshaders

Class MPSGRUDescriptor

  • All Implemented Interfaces:
    NSObject
    public class MPSGRUDescriptor
extends MPSRNNDescriptor
    MPSGRUDescriptor [@dependency] This depends on Metal.framework The MPSGRUDescriptor specifies a GRU (Gated Recurrent Unit) block/layer descriptor. The RNN layer initialized with a MPSGRUDescriptor transforms the input data (image or matrix), and previous output with a set of filters, each producing one feature map in the output data according to the Gated unit formulae detailed below. The user may provide the GRU unit a single input or a sequence of inputs. The layer also supports p-norm gating (Detailed in: https://arxiv.org/abs/1608.03639 ). 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 h_i be the proposed new output. Let h1_i be the output data produced at this time step. Let Wz_ij, Uz_ij, be the input gate weights for input and recurrent input data respectively Let bi_i be the bias for the input gate Let Wr_ij, Ur_ij be the recurrent gate weights for input and recurrent input data respectively Let br_i be the bias for the recurrent gate Let Wh_ij, Uh_ij, Vh_ij, be the output gate weights for input, recurrent gate and input gate respectively Let bh_i be the bias for the output gate Let gz(x), gr(x), gh(x) be the neuron activation function for the input, recurrent and output gates Let p > 0 be a scalar variable (typicall p >= 1.0) that defines the p-norm gating norm value. Then the output of the Gated Recurrent Unit layer is computed as follows: z_i = gz( Wz_ij * x_j + Uz_ij * h0_j + bz_i ) r_i = gr( Wr_ij * x_j + Ur_ij * h0_j + br_i ) c_i = Uh_ij * (r_j h0_j) + Vh_ij * (z_j h0_j) h_i = gh( Wh_ij * x_j + c_i + bh_i ) h1_i = ( 1 - z_i ^ p)^(1/p) h_i + z_i h0_i The '*' stands for convolution (see @ref MPSRNNImageInferenceLayer) or matrix-vector/matrix multiplication (see @ref 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 all U and V matrices have to be square (ie. outputFeatureChannels == inputFeatureChannels in those). Also the bias terms are scalars wrt. spatial dimensions. The conventional GRU block is achieved by setting Vh = 0 (nil) and the so-called Minimal Gated Unit is achieved with Uh = 0. (The Minimal Gated Unit is detailed in: https://arxiv.org/abs/1603.09420 and there they call z_i the value of the forget gate).

    • Constructor Detail

      • MPSGRUDescriptor

        protected MPSGRUDescriptor​(org.moe.natj.general.Pointer peer)

    • Method Detail

      • accessInstanceVariablesDirectly

        public static boolean accessInstanceVariablesDirectly()

      • allocWithZone

        public static java.lang.Object allocWithZone​(org.moe.natj.general.ptr.VoidPtr zone)

      • automaticallyNotifiesObserversForKey

        public static boolean automaticallyNotifiesObserversForKey​(java.lang.String key)

      • cancelPreviousPerformRequestsWithTarget

        public static void cancelPreviousPerformRequestsWithTarget​(java.lang.Object aTarget)

      • cancelPreviousPerformRequestsWithTargetSelectorObject

        public static void cancelPreviousPerformRequestsWithTargetSelectorObject​(java.lang.Object aTarget,
                                                                         org.moe.natj.objc.SEL aSelector,
                                                                         java.lang.Object anArgument)

      • classFallbacksForKeyedArchiver

        public static NSArray<java.lang.String> classFallbacksForKeyedArchiver()

      • classForKeyedUnarchiver

        public static org.moe.natj.objc.Class classForKeyedUnarchiver()

      • createGRUDescriptorWithInputFeatureChannelsOutputFeatureChannels

        public static java.lang.Object createGRUDescriptorWithInputFeatureChannelsOutputFeatureChannels​(long inputFeatureChannels,
                                                                                                long outputFeatureChannels)
        Creates a GRU descriptor.
        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 MPSGRUDescriptor object or nil, if failure.

      • debugDescription_static

        public static java.lang.String debugDescription_static()

      • description_static

        public static java.lang.String description_static()

      • flipOutputGates

        public boolean flipOutputGates()
        [@property] flipOutputGates If YES then the GRU-block output formula is changed to: h1_i = ( 1 - z_i ^ p)^(1/p) h0_i + z_i h_i. Defaults to NO.

      • gatePnormValue

        public float gatePnormValue()
        [@property] gatePnormValue The p-norm gating norm value as specified by the GRU formulae. Defaults to 1.0f.

      • hash_static

        public static long hash_static()

      • inputGateInputWeights

        public MPSCNNConvolutionDataSource inputGateInputWeights()
        [@property] inputGateInputWeights Contains weights 'Wz_ij', bias 'bz_i' and neuron 'gz' from the GRU formula. If nil then assumed zero weights, bias and no neuron (identity mapping). Defaults to nil.

      • inputGateRecurrentWeights

        public MPSCNNConvolutionDataSource inputGateRecurrentWeights()
        [@property] inputGateRecurrentWeights Contains weights 'Uz_ij' from the GRU formula. If nil then assumed zero weights. Defaults to nil.

      • instanceMethodSignatureForSelector

        public static NSMethodSignature instanceMethodSignatureForSelector​(org.moe.natj.objc.SEL aSelector)

      • instancesRespondToSelector

        public static boolean instancesRespondToSelector​(org.moe.natj.objc.SEL aSelector)

      • isSubclassOfClass

        public static boolean isSubclassOfClass​(org.moe.natj.objc.Class aClass)

      • keyPathsForValuesAffectingValueForKey

        public static NSSet<java.lang.String> keyPathsForValuesAffectingValueForKey​(java.lang.String key)

      • new_objc

        public static java.lang.Object new_objc()

      • outputGateInputGateWeights

        public MPSCNNConvolutionDataSource outputGateInputGateWeights()
        [@property] outputGateInputGateWeights Contains weights 'Vh_ij' - can be used to implement the "Minimally Gated Unit". If nil then assumed zero weights. Defaults to nil.

      • outputGateInputWeights

        public MPSCNNConvolutionDataSource outputGateInputWeights()
        [@property] outputGateInputWeights Contains weights 'Wh_ij', bias 'bh_i' and neuron 'gh' from the GRU formula. If nil then assumed zero weights, bias and no neuron (identity mapping).Defaults to nil.

      • outputGateRecurrentWeights

        public MPSCNNConvolutionDataSource outputGateRecurrentWeights()
        [@property] outputGateRecurrentWeights Contains weights 'Uh_ij' from the GRU formula. If nil then assumed zero weights. Defaults to nil.

      • recurrentGateInputWeights

        public MPSCNNConvolutionDataSource recurrentGateInputWeights()
        [@property] recurrentGateInputWeights Contains weights 'Wr_ij', bias 'br_i' and neuron 'gr' from the GRU formula. If nil then assumed zero weights, bias and no neuron (identity mapping).Defaults to nil.

      • recurrentGateRecurrentWeights

        public MPSCNNConvolutionDataSource recurrentGateRecurrentWeights()
        [@property] recurrentGateRecurrentWeights Contains weights 'Ur_ij' from the GRU formula. If nil then assumed zero weights.Defaults to nil.

      • resolveClassMethod

        public static boolean resolveClassMethod​(org.moe.natj.objc.SEL sel)

      • resolveInstanceMethod

        public static boolean resolveInstanceMethod​(org.moe.natj.objc.SEL sel)

      • setFlipOutputGates

        public void setFlipOutputGates​(boolean value)
        [@property] flipOutputGates If YES then the GRU-block output formula is changed to: h1_i = ( 1 - z_i ^ p)^(1/p) h0_i + z_i h_i. Defaults to NO.

      • setGatePnormValue

        public void setGatePnormValue​(float value)
        [@property] gatePnormValue The p-norm gating norm value as specified by the GRU formulae. Defaults to 1.0f.

      • setInputGateInputWeights

        public void setInputGateInputWeights​(MPSCNNConvolutionDataSource value)
        [@property] inputGateInputWeights Contains weights 'Wz_ij', bias 'bz_i' and neuron 'gz' from the GRU formula. If nil then assumed zero weights, bias and no neuron (identity mapping). Defaults to nil.

      • setInputGateRecurrentWeights

        public void setInputGateRecurrentWeights​(MPSCNNConvolutionDataSource value)
        [@property] inputGateRecurrentWeights Contains weights 'Uz_ij' from the GRU formula. If nil then assumed zero weights. Defaults to nil.

      • setOutputGateInputGateWeights

        public void setOutputGateInputGateWeights​(MPSCNNConvolutionDataSource value)
        [@property] outputGateInputGateWeights Contains weights 'Vh_ij' - can be used to implement the "Minimally Gated Unit". If nil then assumed zero weights. Defaults to nil.

      • setOutputGateInputWeights

        public void setOutputGateInputWeights​(MPSCNNConvolutionDataSource value)
        [@property] outputGateInputWeights Contains weights 'Wh_ij', bias 'bh_i' and neuron 'gh' from the GRU formula. If nil then assumed zero weights, bias and no neuron (identity mapping).Defaults to nil.

      • setOutputGateRecurrentWeights

        public void setOutputGateRecurrentWeights​(MPSCNNConvolutionDataSource value)
        [@property] outputGateRecurrentWeights Contains weights 'Uh_ij' from the GRU formula. If nil then assumed zero weights. Defaults to nil.

      • setRecurrentGateInputWeights

        public void setRecurrentGateInputWeights​(MPSCNNConvolutionDataSource value)
        [@property] recurrentGateInputWeights Contains weights 'Wr_ij', bias 'br_i' and neuron 'gr' from the GRU formula. If nil then assumed zero weights, bias and no neuron (identity mapping).Defaults to nil.

      • setRecurrentGateRecurrentWeights

        public void setRecurrentGateRecurrentWeights​(MPSCNNConvolutionDataSource value)
        [@property] recurrentGateRecurrentWeights Contains weights 'Ur_ij' from the GRU formula. If nil then assumed zero weights.Defaults to nil.

      • setVersion_static

        public static void setVersion_static​(long aVersion)

      • superclass_static

        public static org.moe.natj.objc.Class superclass_static()

      • version_static

        public static long version_static()