---
title: MPSGRUDescriptor
framework: metalperformanceshaders
role: symbol
role_heading: Class
path: metalperformanceshaders/mpsgrudescriptor
---

# MPSGRUDescriptor

A description of a gated recurrent unit block or layer.

## Declaration

```swift
class MPSGRUDescriptor
```

## Overview

Overview The recurrent neural network (RNN) layer initialized with a MPSGRUDescriptor transforms the input data (image or matrix) and previous output with a set of filters. Each produces one feature map in the output data according to the gated recurrent unit (GRU) unit formula detailed below. You may provide the GRU unit with a single input or a sequence of inputs. The layer also supports p-norm gating. 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 (typical p >= 1.0) that defines the p-norm gating norm value. The output of the GRU 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) h0_i + z_i h_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’s no summation over repeated index i, the output index. Note that for validity, all intermediate images must be of same size, and all U and V matrices must be square (that is, outputFeatureChannels == inputFeatureChannels). Also, the bias terms are scalars with regard to spatial dimensions. The conventional GRU block is achieved by setting Vh = 0 (nil), and the Minimal Gated Unit is achieved with Uh = 0.

## Topics

### Instance Properties

- [flipOutputGates](metalperformanceshaders/mpsgrudescriptor/flipoutputgates.md)
- [gatePnormValue](metalperformanceshaders/mpsgrudescriptor/gatepnormvalue.md)
- [inputGateInputWeights](metalperformanceshaders/mpsgrudescriptor/inputgateinputweights.md)
- [inputGateRecurrentWeights](metalperformanceshaders/mpsgrudescriptor/inputgaterecurrentweights.md)
- [outputGateInputGateWeights](metalperformanceshaders/mpsgrudescriptor/outputgateinputgateweights.md)
- [outputGateInputWeights](metalperformanceshaders/mpsgrudescriptor/outputgateinputweights.md)
- [outputGateRecurrentWeights](metalperformanceshaders/mpsgrudescriptor/outputgaterecurrentweights.md)
- [recurrentGateInputWeights](metalperformanceshaders/mpsgrudescriptor/recurrentgateinputweights.md)
- [recurrentGateRecurrentWeights](metalperformanceshaders/mpsgrudescriptor/recurrentgaterecurrentweights.md)
- [MPSCNNConvolutionDataSource](metalperformanceshaders/mpscnnconvolutiondatasource.md)

### Type Methods

- [createGRUDescriptor(withInputFeatureChannels:outputFeatureChannels:)](metalperformanceshaders/mpsgrudescriptor/creategrudescriptor(withinputfeaturechannels:outputfeaturechannels:).md)

## Relationships

### Inherits From

- [MPSRNNDescriptor](metalperformanceshaders/mpsrnndescriptor.md)

### Conforms To

- [CVarArg](swift/cvararg.md)
- [CustomDebugStringConvertible](swift/customdebugstringconvertible.md)
- [CustomStringConvertible](swift/customstringconvertible.md)
- [Equatable](swift/equatable.md)
- [Hashable](swift/hashable.md)
- [NSObjectProtocol](objectivec/nsobjectprotocol.md)

## See Also

### Recurrent Neural Networks

- [MPSRNNImageInferenceLayer](metalperformanceshaders/mpsrnnimageinferencelayer.md)
- [MPSRNNMatrixInferenceLayer](metalperformanceshaders/mpsrnnmatrixinferencelayer.md)
- [MPSRNNSingleGateDescriptor](metalperformanceshaders/mpsrnnsinglegatedescriptor.md)
- [MPSLSTMDescriptor](metalperformanceshaders/mpslstmdescriptor.md)
- [MPSRNNSequenceDirection](metalperformanceshaders/mpsrnnsequencedirection.md)
- [MPSRNNMatrixTrainingLayer](metalperformanceshaders/mpsrnnmatrixtraininglayer.md)
- [MPSRNNMatrixTrainingState](metalperformanceshaders/mpsrnnmatrixtrainingstate.md)