Crate objc2_metal_performance_shaders

Bindings to the MetalPerformanceShaders framework

See Apple’s docs and the general docs on framework crates for more information.

Structs

MPSAccelerationStructureDeprecatedMPSAccelerationStructure and MPSRayIntersector and MPSCore and MPSKernel

A data structure built over geometry used to accelerate ray tracing

MPSAccelerationStructureGroupDeprecatedMPSAccelerationStructureGroup and MPSRayIntersector

A group of acceleration structures which may be used together in an instance acceleration structure.

MPSAccelerationStructureStatusDeprecatedMPSAccelerationStructure and MPSRayIntersector

Possible values of the acceleration structure status property

MPSAccelerationStructureUsageDeprecatedMPSAccelerationStructure and MPSRayIntersector

Options describing how an acceleration structure will be used

MPSAliasingStrategyMPSCoreTypes and MPSCore

Apple’s documentation

MPSAlphaTypeMPSImageTypes and MPSImage

Apple’s documentation

MPSBinaryImageKernelMPSImageKernel and MPSImage and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSBoundingBoxIntersectionTestTypeDeprecatedMPSRayIntersector

Options for the MPSRayIntersector bounding box intersection test type property

MPSCNNAddMPSCNNMath and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework.

MPSCNNAddGradientMPSCNNMath and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework.

MPSCNNArithmeticMPSCNNMath and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNArithmeticGradientMPSCNNMath and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNArithmeticGradientStateMPSCNNMath and MPSNeuralNetwork and MPSCore and MPSNNGradientState and MPSState

Dependencies: This depends on Metal.framework.

MPSCNNBatchNormalizationMPSCNNBatchNormalization and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNBatchNormalizationFlagsMPSNeuralNetworkTypes and MPSNeuralNetwork

Apple’s documentation

MPSCNNBatchNormalizationGradientMPSCNNBatchNormalization and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNBatchNormalizationGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

A node representing batch normalization gradient for training

MPSCNNBatchNormalizationNodeMPSNNGraphNodes and MPSNeuralNetwork

A node representing batch normalization for inference or training

MPSCNNBatchNormalizationStateMPSCNNBatchNormalization and MPSNeuralNetwork and MPSCore and MPSNNGradientState and MPSState

MPSCNNBatchNormalizationState encapsulates the data necessary to execute batch normalization.

MPSCNNBatchNormalizationStatisticsMPSCNNBatchNormalization and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNBatchNormalizationStatisticsGradientMPSCNNBatchNormalization and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNBinaryConvolutionMPSCNNConvolution and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNBinaryConvolutionFlagsMPSNeuralNetworkTypes and MPSNeuralNetwork

Apple’s documentation

MPSCNNBinaryConvolutionNodeMPSNNGraphNodes and MPSNeuralNetwork

A MPSNNFilterNode representing a MPSCNNBinaryConvolution kernel

MPSCNNBinaryConvolutionTypeMPSNeuralNetworkTypes and MPSNeuralNetwork

Apple’s documentation

MPSCNNBinaryFullyConnectedMPSCNNConvolution and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNBinaryFullyConnectedNodeMPSNNGraphNodes and MPSNeuralNetwork

A MPSNNFilterNode representing a MPSCNNBinaryFullyConnected kernel

MPSCNNBinaryKernelMPSCNNKernel and MPSNeuralNetwork and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNConvolutionMPSCNNConvolution and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNConvolutionDescriptorMPSCNNConvolution and MPSNeuralNetwork

Dependencies: This depends on Metal.framework

MPSCNNConvolutionFlagsMPSNeuralNetworkTypes and MPSNeuralNetwork

Apple’s documentation

MPSCNNConvolutionGradientMPSCNNConvolution and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNConvolutionGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSCNNConvolutionGradientOptionMPSCNNConvolution and MPSNeuralNetwork

Apple’s documentation

MPSCNNConvolutionGradientStateMPSCNNConvolution and MPSNeuralNetwork and MPSCore and MPSNNGradientState and MPSState

The MPSCNNConvolutionGradientState is returned by resultStateForSourceImage:sourceStates method on MPSCNNConvolution object. Note that resultStateForSourceImage:sourceStates:destinationImage creates the object on autoreleasepool. It will be consumed by MPSCNNConvolutionGradient. This is also used by MPSCNNConvolutionTranspose encode call that returns MPSImage on left hand side to correctly size the destination. Note that state objects are not usable across batches i.e. when batch is done you should nuke the state object and create new one for next batch.

MPSCNNConvolutionGradientStateNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSCNNConvolutionNodeMPSNNGraphNodes and MPSNeuralNetwork

A MPSNNFilterNode representing a MPSCNNConvolution kernel

MPSCNNConvolutionTransposeMPSCNNConvolution and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNConvolutionTransposeGradientMPSCNNConvolution and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNConvolutionTransposeGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSCNNConvolutionTransposeGradientStateMPSCNNConvolution and MPSNeuralNetwork and MPSCore and MPSNNGradientState and MPSState

The MPSCNNConvolutionTransposeGradientState is returned by resultStateForSourceImage:sourceStates method on MPSCNNConvolutionTranspose object. Note that resultStateForSourceImage:sourceStates:destinationImage creates the object on autoreleasepool. It will be consumed by MPSCNNConvolutionTransposeGradient. It contains reference to MPSCNNConvolutionGradientState object that connects MPSCNNConvolution and its corresponding MPSCNNConvolutionTranspose in forward pass of autoencoder. In an autoencoder forward pass, MPSCNNConvolutionGradientState is produced by MPSCNNConvolution object and is used by corresponding MPSCNNConvolutionTraspose of forward pass that “undo” the corresponding MPSCNNConvolution. It is used to correctly size destination image that is returned on left hand side by encode call MPSCNNConvolutionTranspose as well as automatically set kernelOffsetX/Y on MPSCNNConvolutionTranspose using the offset and other properties of corresponding MPSCNNConvolution object. During training, same MPSCNNConvolutionGradientState object will be consumed by MPSCNNConvolutionGradient object and the MPSCNNConvolutionTransposeGradientState produced by MPSCNNConvolutionTranspose’s resultStateForSourceImage:sourceStates:destinationImage will be consumed by MPSCNNConvolutionTransposeGradient object

MPSCNNConvolutionTransposeGradientStateNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSCNNConvolutionTransposeNodeMPSNNGraphNodes and MPSNeuralNetwork

A MPSNNFilterNode representing a MPSCNNConvolutionTranspose kernel

MPSCNNConvolutionWeightsAndBiasesStateMPSCNNConvolution and MPSNeuralNetwork and MPSCore and MPSState

The MPSCNNConvolutionWeightsAndBiasesState is returned by exportWeightsAndBiasesWithCommandBuffer: method on MPSCNNConvolution object. This is mainly used for GPU side weights/biases update process. During training, application can keep a copy of weights, velocity, momentum MTLBuffers in its data source, update the weights (in-place or out of place) with gradients obtained from MPSCNNConvolutionGradientState and call [MPSCNNConvolution reloadWeightsAndBiasesWithCommandBuffer] with resulting updated MTLBuffer. If application does not want to keep a copy of weights/biases, it can call [MPSCNNConvolution exportWeightsAndBiasesWithCommandBuffer:] to get the current weights from convolution itself, do the updated and call reloadWithCommandBuffer.

MPSCNNConvolutionWeightsLayoutMPSCNNConvolution and MPSNeuralNetwork

Apple’s documentation

MPSCNNCrossChannelNormalizationMPSCNNNormalization and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNCrossChannelNormalizationGradientMPSCNNNormalization and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNCrossChannelNormalizationGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSCNNCrossChannelNormalizationNodeMPSNNGraphNodes and MPSNeuralNetwork

Node representing MPSCNNCrossChannelNormalization

MPSCNNDepthWiseConvolutionDescriptorMPSCNNConvolution and MPSNeuralNetwork

MPSCNNDepthWiseConvolutionDescriptor can be used to create MPSCNNConvolution object that does depthwise convolution

MPSCNNDilatedPoolingMaxMPSCNNPooling and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNDilatedPoolingMaxGradientMPSCNNPooling and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNDilatedPoolingMaxGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSCNNDilatedPoolingMaxNodeMPSNNGraphNodes and MPSNeuralNetwork

A node for a MPSCNNDilatedPooling kernel

MPSCNNDivideMPSCNNMath and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework.

MPSCNNDropoutMPSCNNDropout and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNDropoutGradientMPSCNNDropout and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNDropoutGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSCNNDropoutGradientStateMPSCNNDropout and MPSNeuralNetwork and MPSCore and MPSNNGradientState and MPSState

Dependencies: This depends on Metal.framework.

MPSCNNDropoutNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSCNNFullyConnectedMPSCNNConvolution and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNFullyConnectedGradientMPSCNNConvolution and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNFullyConnectedGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSCNNFullyConnectedNodeMPSNNGraphNodes and MPSNeuralNetwork

A MPSNNFilterNode representing a MPSCNNFullyConnected kernel

MPSCNNGradientKernelMPSCNNKernel and MPSNeuralNetwork and MPSCore and MPSKernel

Gradient kernels are the backwards pass of a MPSCNNKernel used during training to calculate gradient back propagation. These take as arguments the gradient result from the next filter and the source image for the forward version of the filter. There is also a MPSNNGradientState passed from MPSCNNKernel to MPSCNNGradientKernel that contains information about the MPSCNNKernel parameters at the time it encoded and possibly also additional MTLResources to enable it to do its job.

MPSCNNGroupNormalizationMPSCNNGroupNormalization and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNGroupNormalizationGradientMPSCNNGroupNormalization and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNGroupNormalizationGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSCNNGroupNormalizationGradientStateMPSCNNGroupNormalization and MPSNeuralNetwork and MPSCore and MPSNNGradientState and MPSState

Dependencies: This depends on Metal.framework

MPSCNNGroupNormalizationNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSCNNInstanceNormalizationMPSCNNInstanceNormalization and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNInstanceNormalizationGradientMPSCNNInstanceNormalization and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNInstanceNormalizationGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSCNNInstanceNormalizationGradientStateMPSCNNInstanceNormalization and MPSNeuralNetwork and MPSCore and MPSNNGradientState and MPSState

Dependencies: This depends on Metal.framework

MPSCNNInstanceNormalizationNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSCNNKernelMPSCNNKernel and MPSNeuralNetwork and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNLocalContrastNormalizationMPSCNNNormalization and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNLocalContrastNormalizationGradientMPSCNNNormalization and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNLocalContrastNormalizationGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSCNNLocalContrastNormalizationNodeMPSNNGraphNodes and MPSNeuralNetwork

Node representing MPSCNNLocalContrastNormalization

MPSCNNLogSoftMaxMPSCNNSoftMax and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNLogSoftMaxGradientMPSCNNSoftMax and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNLogSoftMaxGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Node representing a MPSCNNLogSoftMaxGradient kernel

MPSCNNLogSoftMaxNodeMPSNNGraphNodes and MPSNeuralNetwork

Node representing a MPSCNNLogSoftMax kernel

MPSCNNLossMPSCNNLoss and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework.

MPSCNNLossDataDescriptorMPSCNNLoss and MPSNeuralNetwork

Dependencies: This depends on Metal.framework.

MPSCNNLossDescriptorMPSCNNLoss and MPSNeuralNetwork

Dependencies: This depends on Metal.framework.

MPSCNNLossLabelsMPSCNNLoss and MPSNeuralNetwork and MPSCore and MPSState

Dependencies: This depends on Metal.framework.

MPSCNNLossNodeMPSNNGraphNodes and MPSNeuralNetwork

This node calculates loss information during training typically immediately after the inference portion of network evaluation is performed. The result image of the loss operations is typically the first gradient image to be comsumed by the gradient passes that work their way back up the graph. In addition, the node will update the loss image in the MPSNNLabels with the desired estimate of correctness.

MPSCNNLossTypeMPSCNNTypes and MPSNeuralNetwork

Apple’s documentation

MPSCNNMultiaryKernelMPSCNNKernel and MPSNeuralNetwork and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNMultiplyMPSCNNMath and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework.

MPSCNNMultiplyGradientMPSCNNMath and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework.

MPSCNNNeuronMPSCNNNeuron and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNNeuronAbsoluteMPSCNNNeuron and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNNeuronAbsoluteNodeMPSNNGraphNodes and MPSNeuralNetwork

A node representing a MPSCNNNeuronAbsolute kernel

MPSCNNNeuronELUMPSCNNNeuron and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNNeuronELUNodeMPSNNGraphNodes and MPSNeuralNetwork

A node representing a MPSCNNNeuronELU kernel

MPSCNNNeuronExponentialMPSCNNNeuron and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework.

MPSCNNNeuronExponentialNodeMPSNNGraphNodes and MPSNeuralNetwork

A node representing a MPSCNNNeuronExponential kernel

MPSCNNNeuronGeLUNodeMPSNNGraphNodes and MPSNeuralNetwork

A node representing a MPSCNNNeuronGeLU kernel

MPSCNNNeuronGradientMPSCNNNeuron and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNNeuronGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

A node representing a MPSCNNNeuronGradient

MPSCNNNeuronHardSigmoidMPSCNNNeuron and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNNeuronHardSigmoidNodeMPSNNGraphNodes and MPSNeuralNetwork

A node representing a MPSCNNNeuronHardSigmoid kernel

MPSCNNNeuronLinearMPSCNNNeuron and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNNeuronLinearNodeMPSNNGraphNodes and MPSNeuralNetwork

A node representing a MPSCNNNeuronLinear kernel

MPSCNNNeuronLogarithmMPSCNNNeuron and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework.

MPSCNNNeuronLogarithmNodeMPSNNGraphNodes and MPSNeuralNetwork

A node representing a MPSCNNNeuronLogarithm kernel

MPSCNNNeuronNodeMPSNNGraphNodes and MPSNeuralNetwork

virtual base class for MPSCNNNeuron nodes

MPSCNNNeuronPReLUMPSCNNNeuron and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNNeuronPReLUNodeMPSNNGraphNodes and MPSNeuralNetwork

A ReLU node with parameter a provided independently for each feature channel

MPSCNNNeuronPowerMPSCNNNeuron and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework.

MPSCNNNeuronPowerNodeMPSNNGraphNodes and MPSNeuralNetwork

A node representing a MPSCNNNeuronPower kernel

MPSCNNNeuronReLUMPSCNNNeuron and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNNeuronReLUNMPSCNNNeuron and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNNeuronReLUNNodeMPSNNGraphNodes and MPSNeuralNetwork

A node representing a MPSCNNNeuronReLUN kernel

MPSCNNNeuronReLUNodeMPSNNGraphNodes and MPSNeuralNetwork

A node representing a MPSCNNNeuronReLU kernel

MPSCNNNeuronSigmoidMPSCNNNeuron and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNNeuronSigmoidNodeMPSNNGraphNodes and MPSNeuralNetwork

A node representing a MPSCNNNeuronSigmoid kernel

MPSCNNNeuronSoftPlusMPSCNNNeuron and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNNeuronSoftPlusNodeMPSNNGraphNodes and MPSNeuralNetwork

A node representing a MPSCNNNeuronSoftPlus kernel

MPSCNNNeuronSoftSignMPSCNNNeuron and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNNeuronSoftSignNodeMPSNNGraphNodes and MPSNeuralNetwork

A node representing a MPSCNNNeuronSoftSign kernel

MPSCNNNeuronTanHMPSCNNNeuron and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNNeuronTanHNodeMPSNNGraphNodes and MPSNeuralNetwork

A node representing a MPSCNNNeuronTanH kernel

MPSCNNNeuronTypeMPSCNNNeuronType and MPSNeuralNetwork

Apple’s documentation

MPSCNNNormalizationGammaAndBetaStateMPSCNNNormalizationWeights and MPSNeuralNetwork and MPSCore and MPSState

A state which contains gamma and beta terms used to apply a scale and bias in either an MPSCNNInstanceNormalization or MPSCNNBatchNormalization operation.

MPSCNNNormalizationMeanAndVarianceStateMPSCNNBatchNormalization and MPSNeuralNetwork and MPSCore and MPSState

A state which contains mean and variance terms used to apply a normalization in a MPSCNNBatchNormalization operation.

MPSCNNNormalizationNodeMPSNNGraphNodes and MPSNeuralNetwork

virtual base class for CNN normalization nodes

MPSCNNPoolingMPSCNNPooling and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNPoolingAverageMPSCNNPooling and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNPoolingAverageGradientMPSCNNPooling and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNPoolingAverageGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSCNNPoolingAverageNodeMPSNNGraphNodes and MPSNeuralNetwork

A node representing a MPSCNNPoolingAverage kernel

MPSCNNPoolingGradientMPSCNNPooling and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNPoolingGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSCNNPoolingL2NormMPSCNNPooling and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNPoolingL2NormGradientMPSCNNPooling and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNPoolingL2NormGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSCNNPoolingL2NormNodeMPSNNGraphNodes and MPSNeuralNetwork

A node representing a MPSCNNPoolingL2Norm kernel

MPSCNNPoolingMaxMPSCNNPooling and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNPoolingMaxGradientMPSCNNPooling and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNPoolingMaxGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSCNNPoolingMaxNodeMPSNNGraphNodes and MPSNeuralNetwork

A node representing a MPSCNNPoolingMax kernel

MPSCNNPoolingNodeMPSNNGraphNodes and MPSNeuralNetwork

A node for a MPSCNNPooling kernel

MPSCNNReductionTypeMPSCNNTypes and MPSNeuralNetwork

Apple’s documentation

MPSCNNSoftMaxMPSCNNSoftMax and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNSoftMaxGradientMPSCNNSoftMax and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNSoftMaxGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Node representing a MPSCNNSoftMaxGradient kernel

MPSCNNSoftMaxNodeMPSNNGraphNodes and MPSNeuralNetwork

Node representing a MPSCNNSoftMax kernel

MPSCNNSpatialNormalizationMPSCNNNormalization and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNSpatialNormalizationGradientMPSCNNNormalization and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNSpatialNormalizationGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSCNNSpatialNormalizationNodeMPSNNGraphNodes and MPSNeuralNetwork

Node representing MPSCNNSpatialNormalization

MPSCNNSubPixelConvolutionDescriptorMPSCNNConvolution and MPSNeuralNetwork

MPSCNNSubPixelConvolutionDescriptor can be used to create MPSCNNConvolution object that does sub pixel upsamling and reshaping opeartion as described in http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Shi_Real-Time_Single_Image_CVPR_2016_paper.pdf

MPSCNNSubtractMPSCNNMath and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework.

MPSCNNSubtractGradientMPSCNNMath and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework.

MPSCNNUpsamplingMPSCNNUpsampling and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNUpsamplingBilinearMPSCNNUpsampling and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework.

MPSCNNUpsamplingBilinearGradientMPSCNNUpsampling and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework.

MPSCNNUpsamplingBilinearGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Node representing a MPSCNNUpsamplingBilinear kernel

MPSCNNUpsamplingBilinearNodeMPSNNGraphNodes and MPSNeuralNetwork

Node representing a MPSCNNUpsamplingBilinear kernel

MPSCNNUpsamplingGradientMPSCNNUpsampling and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSCNNUpsamplingNearestMPSCNNUpsampling and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework.

MPSCNNUpsamplingNearestGradientMPSCNNUpsampling and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework.

MPSCNNUpsamplingNearestGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Node representing a MPSCNNUpsamplingNearest kernel

MPSCNNUpsamplingNearestNodeMPSNNGraphNodes and MPSNeuralNetwork

Node representing a MPSCNNUpsamplingNearest kernel

MPSCNNWeightsQuantizationTypeMPSCNNConvolution and MPSNeuralNetwork

Apple’s documentation

MPSCNNYOLOLossMPSCNNLoss and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Apple’s documentation

MPSCNNYOLOLossDescriptorMPSCNNLoss and MPSNeuralNetwork

Dependencies: This depends on Metal.framework.

MPSCNNYOLOLossNodeMPSNNGraphNodes and MPSNeuralNetwork

This node calculates loss information during training typically immediately after the inference portion of network evaluation is performed. The result image of the loss operations is typically the first gradient image to be comsumed by the gradient passes that work their way back up the graph. In addition, the node will update the loss image in the MPSNNLabels with the desired estimate of correctness.

MPSCommandBufferMPSCommandBuffer and MPSCore

Dependencies: This depends on Metal.framework

MPSCustomKernelArgumentCountMPSKernelTypes and MPSCore

Apple’s documentation

MPSCustomKernelIndexMPSKernelTypes and MPSCore

Apple’s documentation

MPSDataLayoutMPSImage and MPSCore

Apple’s documentation

MPSDataTypeMPSCoreTypes and MPSCore

Apple’s documentation

MPSDeviceCapsValuesMPSKernelTypes and MPSCore

Apple’s documentation

MPSDeviceOptions

Apple’s documentation

MPSDimensionSliceMPSCoreTypes and MPSCore

Describes a sub-region of an array dimension

MPSFloatDataTypeBitMPSCoreTypes and MPSCore

Apple’s documentation

MPSFloatDataTypeShiftMPSCoreTypes and MPSCore

Apple’s documentation

MPSGRUDescriptorMPSRNNLayer and MPSNeuralNetwork

Dependencies: This depends on Metal.framework

MPSImageMPSImage and MPSCore

Dependencies: This depends on Metal.framework

MPSImageAddMPSImageMath and MPSImage and MPSCore and MPSImageKernel and MPSKernel

Dependencies: This depends on Metal.framework.

MPSImageAreaMaxMPSImageMorphology and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageAreaMax kernel finds the maximum pixel value in a rectangular region centered around each pixel in the source image. If there are multiple channels in the source image, each channel is processed independently. The edgeMode property is assumed to always be MPSImageEdgeModeClamp for this filter.

MPSImageAreaMinMPSImageMorphology and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageAreaMin finds the minimum pixel value in a rectangular region centered around each pixel in the source image. If there are multiple channels in the source image, each channel is processed independently. It has the same methods as MPSImageAreaMax The edgeMode property is assumed to always be MPSImageEdgeModeClamp for this filter.

MPSImageArithmeticMPSImageMath and MPSImage and MPSCore and MPSImageKernel and MPSKernel

Dependencies: This depends on Metal.framework.

MPSImageBilinearScaleMPSImageResampling and MPSImage and MPSCore and MPSImageKernel and MPSKernel

Resize an image and / or change its aspect ratio

MPSImageBoxMPSImageConvolution and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageBox convolves an image with given filter of odd width and height. The kernel elements all have equal weight, achieving a blur effect. (Each result is the unweighted average of the surrounding pixels.) This allows for much faster algorithms, espcially for larger blur radii. The box height and width must be odd numbers. The box blur is a separable filter. The implementation is aware of this and will act accordingly to give best performance for multi-dimensional blurs.

MPSImageCannyMPSImageConvolution and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageCanny implements the Canny edge detection algorithm. When the color model of the source and destination textures match, the filter is applied to each channel seperately. If the destination is monochrome but source multichannel, the source will be converted to grayscale using the linear gray color transform vector (v). Luminance = v[0] * pixel.x + v[1] * pixel.y + v[2] * pixel.z;

MPSImageConversionMPSImageConversion and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageConversion filter performs a conversion from source to destination

MPSImageConvolutionMPSImageConvolution and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageConvolution convolves an image with given filter of odd width and height. The center of the kernel aligns with the MPSImageConvolution.offset. That is, the position of the top left corner of the area covered by the kernel is given by MPSImageConvolution.offset - {kernel_width>>1, kernel_height>>1, 0}

MPSImageCoordinateMPSCoreTypes and MPSCore

A unsigned coordinate with x, y and channel components

MPSImageCopyToMatrixMPSImageCopy and MPSImage and MPSCore and MPSKernel

The MPSImageCopyToMatrix copies image data to a MPSMatrix. The image data is stored in a row of a matrix. The dataLayout specifies the order in which the feature channels in the MPSImage get stored in the matrix. If MPSImage stores a batch of images, the images are copied into multiple rows, one row per image.

MPSImageDescriptorMPSImage and MPSCore

Dependencies: This depends on Metal.framework

MPSImageDilateMPSImageMorphology and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageDilate finds the maximum pixel value in a rectangular region centered around each pixel in the source image. It is like the MPSImageAreaMax, except that the intensity at each position is calculated relative to a different value before determining which is the maximum pixel value, allowing for shaped, non-rectangular morphological probes.

MPSImageDivideMPSImageMath and MPSImage and MPSCore and MPSImageKernel and MPSKernel

Dependencies: This depends on Metal.framework.

MPSImageEDLinesMPSImageEDLines and MPSImage and MPSCore and MPSKernel

The MPSImageEDLInes class implements the EDLines line segmenting algorithm using edge-drawing (ED) described here https://ieeexplore.ieee.org/document/6116138

MPSImageEdgeModeMPSCoreTypes and MPSCore

Apple’s documentation

MPSImageErodeMPSImageMorphology and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageErode filter finds the minimum pixel value in a rectangular region centered around each pixel in the source image. It is like the MPSImageAreaMin, except that the intensity at each position is calculated relative to a different value before determining which is the maximum pixel value, allowing for shaped, non-rectangular morphological probes.

MPSImageEuclideanDistanceTransformMPSImageDistanceTransform and MPSImage and MPSCore and MPSImageKernel and MPSKernel

Perform a Euclidean Distance Transform

MPSImageFeatureChannelFormatMPSCoreTypes and MPSCore

Apple’s documentation

MPSImageFindKeypointsMPSImageKeypoint and MPSImage and MPSCore and MPSKernel

The MPSImageFindKeypoints kernel is used to find a list of keypoints whose values are >= minimumPixelThresholdValue in MPSImageKeypointRangeInfo. The keypoints are generated for a specified region in the image. The pixel format of the source image must be MTLPixelFormatR8Unorm.

MPSImageGaussianBlurMPSImageConvolution and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageGaussianBlur convolves an image with gaussian of given sigma in both x and y direction.

MPSImageGaussianPyramidMPSImageConvolution and MPSImage and MPSCore and MPSImageKernel and MPSKernel

A Gaussian image pyramid is constructed as follows: The mipmap level zero is the source of the operation and is left untouched and the subsequent mipmap levels are constructed from it recursively:

MPSImageGuidedFilterMPSImageGuidedFilter and MPSImage and MPSCore and MPSKernel

Perform Guided Filter to produce a coefficients image The filter is broken into two stages:

MPSImageHistogramMPSImageHistogram and MPSImage and MPSCore and MPSKernel

The MPSImageHistogram computes the histogram of an image.

MPSImageHistogramEqualizationMPSImageHistogram and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageHistogramEqualization performs equalizes the histogram of an image. The process is divided into three steps.

MPSImageHistogramSpecificationMPSImageHistogram and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageHistogramSpecification performs a histogram specification operation on an image. It is a generalized version of histogram equalization operation. The histogram specificaiton filter converts the image so that its histogram matches the desired histogram.

MPSImageIntegralMPSImageIntegral and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageIntegral calculates the sum of pixels over a specified region in the image. The value at each position is the sum of all pixels in a source image rectangle, sumRect:

MPSImageIntegralOfSquaresMPSImageIntegral and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageIntegralOfSquares calculates the sum of squared pixels over a specified region in the image. The value at each position is the sum of all squared pixels in a source image rectangle, sumRect:

MPSImageKeypointRangeInfoMPSImageKeypoint and MPSImage

Specifies information to find the keypoints in an image.

MPSImageLanczosScaleMPSImageResampling and MPSImage and MPSCore and MPSImageKernel and MPSKernel

Resize an image and / or change its aspect ratio

MPSImageLaplacianMPSImageConvolution and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageLaplacian is an optimized variant of the MPSImageConvolution filter provided primarily for ease of use. This filter uses an optimized convolution filter with a 3 x 3 kernel with the following weights: [ 0 1 0 1 -4 1 0 1 0 ]

MPSImageLaplacianPyramidMPSImageConvolution and MPSImage and MPSCore and MPSImageKernel and MPSKernel

Laplacian pyramid levels are constructed as difference between the current source level and 2x interpolated version of the half-resolution source level immediately above it.

MPSImageLaplacianPyramidAddMPSImageConvolution and MPSImage and MPSCore and MPSImageKernel and MPSKernel

Apple’s documentation

MPSImageLaplacianPyramidSubtractMPSImageConvolution and MPSImage and MPSCore and MPSImageKernel and MPSKernel

Apple’s documentation

MPSImageMedianMPSImageMedian and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageMedian applies a median filter to an image. A median filter finds the median color value for each channel within a kernelDiameter x kernelDiameter window surrounding the pixel of interest. It is a common means of noise reduction and also as a smoothing filter with edge preserving qualities.

MPSImageMultiplyMPSImageMath and MPSImage and MPSCore and MPSImageKernel and MPSKernel

Dependencies: This depends on Metal.framework.

MPSImageNormalizedHistogramMPSImageHistogram and MPSImage and MPSCore and MPSKernel

The MPSImageNormalizedHistogram computes the normalized histogram of an image. The minimum and maximum pixel values for a given region of an image are first computed. The max(computed minimum pixel value, MPSImageHistogramInfo.minPixelValue) and the min(computed maximum pixel value, MPSImageHistogramInfo.maxPixelValue) are used to compute the normalized histogram.

MPSImagePyramidMPSImageConvolution and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImagePyramid is a base class for creating different kinds of pyramid images

MPSImageReadWriteParamsMPSImage and MPSCore

these parameters are passed in to allow user to read/write to a particular set of featureChannels in an MPSImage

MPSImageReduceColumnMaxMPSImageReduce and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageReduceColumnMax performs a reduction operation returning the maximum value for each column of an image

MPSImageReduceColumnMeanMPSImageReduce and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageReduceColumnMean performs a reduction operation returning the mean value for each column of an image

MPSImageReduceColumnMinMPSImageReduce and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageReduceColumnMin performs a reduction operation returning the mininmum value for each column of an image

MPSImageReduceColumnSumMPSImageReduce and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageReduceColumnSum performs a reduction operation returning the sum for each column of an image

MPSImageReduceRowMaxMPSImageReduce and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageReduceRowMax performs a reduction operation returning the maximum value for each row of an image

MPSImageReduceRowMeanMPSImageReduce and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageReduceRowMean performs a reduction operation returning the mean value for each row of an image

MPSImageReduceRowMinMPSImageReduce and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageReduceRowMin performs a reduction operation returning the mininmum value for each row of an image

MPSImageReduceRowSumMPSImageReduce and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageReduceRowSum performs a reduction operation returning the sum for each row of an image

MPSImageReduceUnaryMPSImageReduce and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageReduce performs a reduction operation The reduction operations supported are:

MPSImageRegionMPSCoreTypes and MPSCore

A rectangular subregion of a MPSImage

MPSImageScaleMPSImageResampling and MPSImage and MPSCore and MPSImageKernel and MPSKernel

Resize an image and / or change its aspect ratio

MPSImageSobelMPSImageConvolution and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageSobel implements the Sobel filter. When the color model (e.g. RGB, two-channel, grayscale, etc.) of source and destination textures match, the filter is applied to each channel separately. If the destination is monochrome (single channel) but source multichannel, the pixel values are converted to grayscale before applying Sobel operator using the linear gray color transform vector (v).

MPSImageStatisticsMeanMPSImageStatistics and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageStatisticsMean computes the mean for a given region of an image.

MPSImageStatisticsMeanAndVarianceMPSImageStatistics and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageStatisticsMeanAndVariance computes the mean and variance for a given region of an image. The mean and variance values are written to the destination image at the following pixel locations:

MPSImageStatisticsMinAndMaxMPSImageStatistics and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageStatisticsMinAndMax computes the minimum and maximum pixel values for a given region of an image. The min and max values are written to the destination image at the following pixel locations:

MPSImageSubtractMPSImageMath and MPSImage and MPSCore and MPSImageKernel and MPSKernel

Dependencies: This depends on Metal.framework.

MPSImageTentMPSImageConvolution and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The box filter, while fast, may yield square-ish looking blur effects. However, multiple passes of the box filter tend to smooth out with each additional pass. For example, two 3-wide box blurs produces the same effective convolution as a 5-wide tent blur:

MPSImageThresholdBinaryMPSImageThreshold and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSThreshold filter applies a fixed-level threshold to each pixel in the image. The threshold functions convert a single channel image to a binary image. If the input image is not a single channel image, convert the inputimage to a single channel luminance image using the linearGrayColorTransform and then apply the threshold. The ThresholdBinary function is: destinationPixelValue = sourcePixelValue > thresholdValue ? maximumValue : 0

MPSImageThresholdBinaryInverseMPSImageThreshold and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageThresholdBinaryInverse filter applies a fixed-level threshold to each pixel in the image. The threshold functions convert a single channel image to a binary image. If the input image is not a single channel image, convert the inputimage to a single channel luminance image using the linearGrayColorTransform and then apply the threshold. The ThresholdBinaryInverse function is: destinationPixelValue = sourcePixelValue > thresholdValue ? 0 : maximumValue

MPSImageThresholdToZeroMPSImageThreshold and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageThresholdToZero filter applies a fixed-level threshold to each pixel in the image. The threshold functions convert a single channel image to a binary image. If the input image is not a single channel image, convert the inputimage to a single channel luminance image using the linearGrayColorTransform and then apply the threshold. The ThresholdToZero function is: destinationPixelValue = sourcePixelValue > thresholdValue ? sourcePixelValue : 0

MPSImageThresholdToZeroInverseMPSImageThreshold and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageThresholdToZeroInverse filter applies a fixed-level threshold to each pixel in the image. The threshold functions convert a single channel image to a binary image. If the input image is not a single channel image, convert the inputimage to a single channel luminance image using the linearGrayColorTransform and then apply the threshold. The ThresholdToZeroINverse function is: destinationPixelValue = sourcePixelValue > thresholdValue ? 0 : sourcePixelValue

MPSImageThresholdTruncateMPSImageThreshold and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageThresholdTruncate filter applies a fixed-level threshold to each pixel in the image: The threshold functions convert a single channel image to a binary image. If the input image is not a single channel image, convert the inputimage to a single channel luminance image using the linearGrayColorTransform and then apply the threshold. The ThresholdTruncate function is: destinationPixelValue = sourcePixelValue > thresholdValue ? thresholdValue : sourcePixelValue

MPSImageTransposeMPSImageTranspose and MPSImage and MPSCore and MPSImageKernel and MPSKernel

The MPSImageTranspose transposes an image

MPSImageTypeMPSKernelTypes and MPSCore

Apple’s documentation

MPSInstanceAccelerationStructureDeprecatedMPSInstanceAccelerationStructure and MPSRayIntersector and MPSAccelerationStructure and MPSCore and MPSKernel

An acceleration structure built over instances of other acceleration structures

MPSIntegerDivisionParamsMPSKernelTypes and MPSCore

Apple’s documentation

MPSIntersectionDataTypeMPSRayIntersector

Intersection data type options

MPSIntersectionDistanceMPSRayIntersectorTypes and MPSRayIntersector

Returned intersection result which contains the distance from the ray origin to the intersection point

MPSIntersectionDistancePrimitiveIndexMPSRayIntersectorTypes and MPSRayIntersector

Intersection result which contains the distance from the ray origin to the intersection point and the index of the intersected primitive

MPSIntersectionDistancePrimitiveIndexBufferIndexMPSRayIntersectorTypes and MPSRayIntersector

Intersection result which contains the distance from the ray origin to the intersection point, the index of the intersected primitive, and the polygon buffer index of the intersected primitive.

MPSIntersectionDistancePrimitiveIndexBufferIndexInstanceIndexMPSRayIntersectorTypes and MPSRayIntersector

Intersection result which contains the distance from the ray origin to the intersection point, the index of the intersected primitive, the polygon buffer index of the intersected primitive, and the index of the intersected instance.

MPSIntersectionDistancePrimitiveIndexInstanceIndexMPSRayIntersectorTypes and MPSRayIntersector

Intersection result which contains the distance from the ray origin to the intersection point, the index of the intersected primitive, and the index of the intersected instance.

MPSIntersectionTypeMPSRayIntersector

Options for the MPSRayIntersector intersection type property

MPSKernelMPSKernel and MPSCore

Dependencies: This depends on Metal.framework

MPSKernelOptionsMPSCoreTypes and MPSCore

Apple’s documentation

MPSKeyedUnarchiverMPSKeyedUnarchiver and MPSCore

A NSKeyedArchiver that supports the MPSDeviceProvider protocol for MPSKernel decoding

MPSLSTMDescriptorMPSRNNLayer and MPSNeuralNetwork

Dependencies: This depends on Metal.framework

MPSMatrixMPSMatrix and MPSCore

Dependencies: This depends on Metal.framework

MPSMatrixBatchNormalizationMPSMatrixBatchNormalization and MPSNeuralNetwork and MPSCore and MPSKernel and MPSMatrix and MPSMatrixTypes

Dependencies: This depends on Metal.framework.

MPSMatrixBatchNormalizationGradientMPSMatrixBatchNormalization and MPSNeuralNetwork and MPSCore and MPSKernel and MPSMatrix and MPSMatrixTypes

Dependencies: This depends on Metal.framework.

MPSMatrixBinaryKernelMPSMatrixTypes and MPSMatrix and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSMatrixCopyMPSMatrixCombination and MPSMatrix and MPSCore and MPSKernel

Apple’s documentation

MPSMatrixCopyDescriptorMPSMatrixCombination and MPSMatrix

A list of copy operations

MPSMatrixCopyOffsetsMPSMatrixCombination and MPSMatrix

A description of each copy operation

MPSMatrixCopyToImageMPSImageCopy and MPSImage and MPSCore and MPSKernel

The MPSMatrixCopyToImage copies matrix data to a MPSImage. The operation is the reverse of MPSImageCopyToMatrix.

MPSMatrixDecompositionCholeskyMPSMatrixDecomposition and MPSMatrix and MPSCore and MPSKernel and MPSMatrixTypes

Dependencies: This depends on Metal.framework.

MPSMatrixDecompositionLUMPSMatrixDecomposition and MPSMatrix and MPSCore and MPSKernel and MPSMatrixTypes

Dependencies: This depends on Metal.framework.

MPSMatrixDecompositionStatusMPSMatrixDecomposition and MPSMatrix

Apple’s documentation

MPSMatrixDescriptorMPSMatrix and MPSCore

Dependencies: This depends on Metal.framework

MPSMatrixFindTopKMPSMatrixFindTopK and MPSMatrix and MPSCore and MPSKernel and MPSMatrixTypes

Dependencies: This depends on Metal.framework.

MPSMatrixFullyConnectedMPSMatrixFullyConnected and MPSNeuralNetwork and MPSCore and MPSKernel and MPSMatrix and MPSMatrixTypes

Dependencies: This depends on Metal.framework.

MPSMatrixFullyConnectedGradientMPSMatrixFullyConnected and MPSNeuralNetwork and MPSCore and MPSKernel and MPSMatrix and MPSMatrixTypes

Dependencies: This depends on Metal.framework.

MPSMatrixLogSoftMaxMPSMatrixSoftMax and MPSMatrix and MPSCore and MPSKernel and MPSMatrixTypes

Dependencies: This depends on Metal.framework.

MPSMatrixLogSoftMaxGradientMPSMatrixSoftMax and MPSMatrix and MPSCore and MPSKernel and MPSMatrixTypes

Dependencies: This depends on Metal.framework.

MPSMatrixMultiplicationMPSMatrixMultiplication and MPSMatrix and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework.

MPSMatrixNeuronMPSMatrixNeuron and MPSNeuralNetwork and MPSCore and MPSKernel and MPSMatrix and MPSMatrixTypes

Dependencies: This depends on Metal.framework.

MPSMatrixNeuronGradientMPSMatrixNeuron and MPSNeuralNetwork and MPSCore and MPSKernel and MPSMatrix and MPSMatrixTypes

Dependencies: This depends on Metal.framework.

MPSMatrixOffsetMPSKernelTypes and MPSCore

Specifies a row and column offset into an MPSMatrix.

MPSMatrixRandomMPSMatrixRandom and MPSMatrix and MPSCore and MPSKernel

Kernels that implement random number generation.

MPSMatrixRandomDistributionMPSMatrixRandom and MPSMatrix

Apple’s documentation

MPSMatrixRandomDistributionDescriptorMPSMatrixRandom and MPSMatrix

Dependencies: This depends on Metal.framework

MPSMatrixRandomMTGP32MPSMatrixRandom and MPSMatrix and MPSCore and MPSKernel

Generates random numbers using a Mersenne Twister algorithm suitable for GPU execution. It uses a period of 2**11214. For further details see: Mutsuo Saito. A Variant of Mersenne Twister Suitable for Graphic Processors. arXiv:1005.4973

MPSMatrixRandomPhiloxMPSMatrixRandom and MPSMatrix and MPSCore and MPSKernel

Generates random numbers using a counter based algorithm. For further details see: John K. Salmon, Mark A. Moraes, Ron O. Dror, and David E. Shaw. Parallel Random Numbers: As Easy as 1, 2, 3.

MPSMatrixSoftMaxMPSMatrixSoftMax and MPSMatrix and MPSCore and MPSKernel and MPSMatrixTypes

Dependencies: This depends on Metal.framework.

MPSMatrixSoftMaxGradientMPSMatrixSoftMax and MPSMatrix and MPSCore and MPSKernel and MPSMatrixTypes

Dependencies: This depends on Metal.framework.

MPSMatrixSolveCholeskyMPSMatrixSolve and MPSMatrix and MPSCore and MPSKernel and MPSMatrixTypes

Dependencies: This depends on Metal.framework.

MPSMatrixSolveLUMPSMatrixSolve and MPSMatrix and MPSCore and MPSKernel and MPSMatrixTypes

Dependencies: This depends on Metal.framework.

MPSMatrixSolveTriangularMPSMatrixSolve and MPSMatrix and MPSCore and MPSKernel and MPSMatrixTypes

Dependencies: This depends on Metal.framework.

MPSMatrixSumMPSMatrixSum and MPSNeuralNetwork and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSMatrixUnaryKernelMPSMatrixTypes and MPSMatrix and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSMatrixVectorMultiplicationMPSMatrixMultiplication and MPSMatrix and MPSCore and MPSKernel and MPSMatrixTypes

Dependencies: This depends on Metal.framework.

MPSNDArrayMPSNDArray and MPSCore

A MPSNDArray object is a MTLBuffer based storage container for multi-dimensional data.

MPSNDArrayAffineInt4DequantizeMPSNDArrayQuantizedMatrixMultiplication and MPSNDArray and MPSCore and MPSKernel and MPSNDArrayKernel

Dependencies: This depends on Metal.framework.

MPSNDArrayAffineQuantizationDescriptorMPSNDArrayQuantization and MPSNDArray

Dependencies: This depends on Metal.framework.

MPSNDArrayBinaryKernelMPSNDArrayKernel and MPSNDArray and MPSCore and MPSKernel

Apple’s documentation

MPSNDArrayBinaryPrimaryGradientKernelMPSNDArrayKernel and MPSNDArray and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework.

MPSNDArrayBinarySecondaryGradientKernelMPSNDArrayKernel and MPSNDArray and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework.

MPSNDArrayDescriptorMPSNDArray and MPSCore

Dependencies: This depends on Metal.framework

MPSNDArrayGatherMPSNDArrayGather and MPSNDArray and MPSCore and MPSKernel and MPSNDArrayKernel

Dependencies: This depends on Metal.framework.

MPSNDArrayGatherGradientMPSNDArrayGather and MPSNDArray and MPSCore and MPSKernel and MPSNDArrayKernel

Dependencies: This depends on Metal.framework.

MPSNDArrayGatherGradientStateMPSNDArrayGather and MPSNDArray and MPSCore and MPSNDArrayGradientState and MPSState

at the time an -encode call was made.

MPSNDArrayGradientStateMPSNDArrayGradientState and MPSNDArray and MPSCore and MPSState

at the time an -encode call was made. The contents are opaque.

MPSNDArrayIdentityMPSNDArrayIdentity and MPSNDArray and MPSCore and MPSKernel and MPSNDArrayKernel

Dependencies: This depends on Metal.framework.

MPSNDArrayLUTDequantizeMPSNDArrayQuantizedMatrixMultiplication and MPSNDArray and MPSCore and MPSKernel and MPSNDArrayKernel

Dependencies: This depends on Metal.framework.

MPSNDArrayLUTQuantizationDescriptorMPSNDArrayQuantization and MPSNDArray

Dependencies: This depends on Metal.framework.

MPSNDArrayMatrixMultiplicationMPSNDArrayMatrixMultiplication and MPSNDArray and MPSCore and MPSKernel and MPSNDArrayKernel

Dependencies: This depends on Metal.framework.

MPSNDArrayMultiaryBaseMPSNDArrayKernel and MPSNDArray and MPSCore and MPSKernel

Apple’s documentation

MPSNDArrayMultiaryGradientKernelMPSNDArrayKernel and MPSNDArray and MPSCore and MPSKernel

Apple’s documentation

MPSNDArrayMultiaryKernelMPSNDArrayKernel and MPSNDArray and MPSCore and MPSKernel

Apple’s documentation

MPSNDArrayOffsetsMPSNDArrayTypes and MPSNDArray

Apple’s documentation

MPSNDArrayQuantizationDescriptorMPSNDArrayQuantization and MPSNDArray

Dependencies: This depends on Metal.framework.

MPSNDArrayQuantizationSchemeMPSNDArrayQuantization and MPSNDArray

Apple’s documentation

MPSNDArrayQuantizedMatrixMultiplicationMPSNDArrayQuantizedMatrixMultiplication and MPSNDArray and MPSCore and MPSKernel and MPSNDArrayKernel and MPSNDArrayMatrixMultiplication

Dependencies: This depends on Metal.framework.

MPSNDArraySizesMPSNDArrayTypes and MPSNDArray

Apple’s documentation

MPSNDArrayStridedSliceMPSNDArrayStridedSlice and MPSNDArray and MPSCore and MPSKernel and MPSNDArrayKernel

Dependencies: This depends on Metal.framework.

MPSNDArrayStridedSliceGradientMPSNDArrayStridedSlice and MPSNDArray and MPSCore and MPSKernel and MPSNDArrayKernel

Dependencies: This depends on Metal.framework.

MPSNDArrayUnaryGradientKernelMPSNDArrayKernel and MPSNDArray and MPSCore and MPSKernel

Apple’s documentation

MPSNDArrayUnaryKernelMPSNDArrayKernel and MPSNDArray and MPSCore and MPSKernel

Apple’s documentation

MPSNDArrayVectorLUTDequantizeMPSNDArrayQuantizedMatrixMultiplication and MPSNDArray and MPSCore and MPSKernel and MPSNDArrayKernel

Dependencies: This depends on Metal.framework.

MPSNNAdditionGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

returns gradient for either primary or secondary source image from the inference pass. Use the isSecondarySourceFilter property to indicate whether this filter is computing the gradient for the primary or secondary source image from the inference pass.

MPSNNAdditionNodeMPSNNGraphNodes and MPSNeuralNetwork

returns elementwise sum of left + right

MPSNNArithmeticGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSNNArithmeticGradientStateNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSNNBilinearScaleNodeMPSNNGraphNodes and MPSNeuralNetwork

A MPSNNScale object that uses bilinear interpolation for resampling

MPSNNBinaryArithmeticNodeMPSNNGraphNodes and MPSNeuralNetwork

virtual base class for basic arithmetic nodes

MPSNNBinaryGradientStateMPSNNGradientState and MPSNeuralNetwork and MPSCore and MPSState

at the time an -encode call was made. The contents are opaque.

MPSNNBinaryGradientStateNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSNNCompareMPSCNNMath and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework.

MPSNNComparisonNodeMPSNNGraphNodes and MPSNeuralNetwork

returns elementwise comparison of left and right

MPSNNComparisonTypeMPSCNNMath and MPSNeuralNetwork

Apple’s documentation

MPSNNConcatenationGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

A MPSNNSlice filter that operates as the conjugate computation for concatentation operators during training

MPSNNConcatenationNodeMPSNNGraphNodes and MPSNeuralNetwork

Node representing a the concatenation (in the feature channel dimension) of the results from one or more kernels

MPSNNConvolutionAccumulatorPrecisionOptionMPSNeuralNetworkTypes and MPSNeuralNetwork

Apple’s documentation

MPSNNCropAndResizeBilinearMPSNNResize and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSNNDefaultPaddingMPSNeuralNetworkTypes and MPSNeuralNetwork

This class provides some pre-rolled padding policies for common tasks

MPSNNDivisionNodeMPSNNGraphNodes and MPSNeuralNetwork

returns elementwise quotient of left / right

MPSNNFilterNodeMPSNNGraphNodes and MPSNeuralNetwork

A placeholder node denoting a neural network filter stage

MPSNNForwardLossMPSCNNLoss and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework.

MPSNNForwardLossNodeMPSNNGraphNodes and MPSNeuralNetwork

Node representing a MPSNNForwardLosskernel

MPSNNGradientFilterNodeMPSNNGraphNodes and MPSNeuralNetwork

For each MPSNNFilterNode, there is a corresponding MPSNNGradientFilterNode used for training that back propagates image gradients to refine the various parameters in each node. Generally, it takes as input a gradient corresponding to the result image from the MPSNNFilterNode and returns a gradient image corresponding to the source image of the MPSNNFilterNode. In addition, there is generally a MPSNNState produced by the MPSNNFilterNode that is consumed by the MPSNNGradientNode and the MPSNNGradientNode generally needs to look at the MPSNNFilterNode source image.

MPSNNGradientStateMPSNNGradientState and MPSNeuralNetwork and MPSCore and MPSState

at the time an -encode call was made. The contents are opaque.

MPSNNGradientStateNodeMPSNNGraphNodes and MPSNeuralNetwork

During training, each MPSNNFilterNode has a corresponding MPSNNGradientFilterNode for the gradient computation for trainable parameter update. The two communicate through a MPSNNGradientStateNode or subclass which carries information about the inference pass settings to the gradient pass. You can avoid managing these – there will be many! – by using -[MPSNNFilterNode gradientFilterWithSources:] to make the MPSNNGradientFilterNodes. That method will append the necessary extra information like MPSNNGradientState nodes and inference filter source image nodes to the object as needed.

MPSNNGramMatrixCalculationMPSCNNConvolution and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSNNGramMatrixCalculationGradientMPSCNNConvolution and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSNNGramMatrixCalculationGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Node representing a MPSNNGramMatrixCalculationGradientkernel

MPSNNGramMatrixCalculationNodeMPSNNGraphNodes and MPSNeuralNetwork

Node representing a MPSNNGramMatrixCalculationkernel

MPSNNGraphMPSNNGraph and MPSNeuralNetwork and MPSCore and MPSKernel

Optimized representation of a graph of MPSNNImageNodes and MPSNNFilterNodes

MPSNNGridSampleMPSNNGridSample and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Apple’s documentation

MPSNNImageNodeMPSNNGraphNodes and MPSNeuralNetwork

A placeholder node denoting the position of a MPSImage in a graph

MPSNNInitialGradientMPSCNNLoss and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSNNInitialGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

A node for a MPSNNInitialGradient kernel

MPSNNLabelsNodeMPSNNGraphNodes and MPSNeuralNetwork

The labels and weights for each MPSImage are passed in separately to the graph in a MPSNNLabels object. If the batch interface is used then there will be a MPSStateBatch of these of the same size as the MPSImageBatch that holds the images. The MPSNNLabelsNode is a place holder in the graph for these nodes. The MPSNNLabels node is taken as an input to the Loss node

MPSNNLanczosScaleNodeMPSNNGraphNodes and MPSNeuralNetwork

A MPSNNScale object that uses the Lanczos resampling filter

MPSNNLocalCorrelationMPSNNReduce and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

The MPSNNLocalCorrelation filter computes the correlation between two images locally with a varying offset on x-y plane between the two source images (controlled by the window and stride properties) and the end result is summed over the feature channels. The results are stored in the different feature channels of the destination image, ordered such that the offset in the x direction is the faster running index.

MPSNNLossGradientMPSCNNLoss and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework.

MPSNNLossGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Node representing a MPSNNLossGradientkernel

MPSNNMultiaryGradientStateMPSNNGradientState and MPSNeuralNetwork and MPSCore and MPSState

Apple’s documentation

MPSNNMultiaryGradientStateNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSNNMultiplicationGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

returns gradient for either primary or secondary source image from the inference pass. Use the isSecondarySourceFilter property to indicate whether this filter is computing the gradient for the primary or secondary source image from the inference pass.

MPSNNMultiplicationNodeMPSNNGraphNodes and MPSNeuralNetwork

returns elementwise product of left * right

MPSNNNeuronDescriptorMPSCNNNeuron and MPSNeuralNetwork

Dependencies: This depends on Metal.framework

MPSNNOptimizerMPSNNOptimizers and MPSNeuralNetwork and MPSCore and MPSKernel

The MPSNNOptimizer base class, use one of the child classes, not to be directly used. Optimizers are generally used to update trainable neural network parameters. Users are usually expected to call these MPSKernels from the update methods on their Convolution or BatchNormalization data sources.

MPSNNOptimizerAdamMPSNNOptimizers and MPSNeuralNetwork and MPSCore and MPSKernel

The MPSNNOptimizerAdam performs an Adam Update

MPSNNOptimizerDescriptorMPSNNOptimizers and MPSNeuralNetwork

The MPSNNOptimizerDescriptor base class. Optimizers are generally used to update trainable neural network parameters. Users are usually expected to call these MPSKernels from the update methods on their Convolution or BatchNormalization data sources.

MPSNNOptimizerRMSPropMPSNNOptimizers and MPSNeuralNetwork and MPSCore and MPSKernel

The MPSNNOptimizerRMSProp performs an RMSProp Update RMSProp is also known as root mean square propagation.

MPSNNOptimizerStochasticGradientDescentMPSNNOptimizers and MPSNeuralNetwork and MPSCore and MPSKernel

The MPSNNOptimizerStochasticGradientDescent performs a gradient descent with an optional momentum Update RMSProp is also known as root mean square propagation.

MPSNNPadMPSNNReshape and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Apple’s documentation

MPSNNPadGradientMPSNNReshape and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSNNPadGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSNNPadNodeMPSNNGraphNodes and MPSNeuralNetwork

A node for a MPSNNPad kernel

MPSNNPaddingMethodMPSNeuralNetworkTypes and MPSNeuralNetwork

Apple’s documentation

MPSNNReduceBinaryMPSNNReduce and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

The MPSNNReduce performs a reduction operation The reduction operations supported are:

MPSNNReduceColumnMaxMPSNNReduce and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

The MPSNNReduceColumnMax performs a reduction operation returning the maximum value for each column of an image

MPSNNReduceColumnMeanMPSNNReduce and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

The MPSNNReduceColumnMean performs a reduction operation returning the mean value for each column of an image

MPSNNReduceColumnMinMPSNNReduce and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

The MPSNNReduceColumnMin performs a reduction operation returning the mininmum value for each column of an image

MPSNNReduceColumnSumMPSNNReduce and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

The MPSNNReduceColumnSum performs a reduction operation returning the sum for each column of an image

MPSNNReduceFeatureChannelsAndWeightsMeanMPSNNReduce and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Apple’s documentation

MPSNNReduceFeatureChannelsAndWeightsSumMPSNNReduce and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Apple’s documentation

MPSNNReduceFeatureChannelsArgumentMaxMPSNNReduce and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

The MPSNNReduceFeatureChannelsArgumentMax performs returns the argument index that is the location of the maximum value for feature channels of an image

MPSNNReduceFeatureChannelsArgumentMinMPSNNReduce and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

The MPSNNReduceFeatureChannelsArgumentMin returns the argument index that is the location of the minimum value for feature channels of an image

MPSNNReduceFeatureChannelsMaxMPSNNReduce and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

The MPSNNReduceFeatureChannelsMax performs a reduction operation returning the maximum value for feature channels of an image

MPSNNReduceFeatureChannelsMeanMPSNNReduce and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

The MPSNNReduceFeatureChannelsMean performs a reduction operation returning the mean value for each column of an image

MPSNNReduceFeatureChannelsMinMPSNNReduce and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

The MPSNNReduceFeatureChannelsMin performs a reduction operation returning the mininmum value for feature channels of an image

MPSNNReduceFeatureChannelsSumMPSNNReduce and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

The MPSNNReduceFeatureChannelsSum performs a reduction operation returning the sum for each column of an image

MPSNNReduceRowMaxMPSNNReduce and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

The MPSNNReduceRowMax performs a reduction operation returning the maximum value for each row of an image

MPSNNReduceRowMeanMPSNNReduce and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

The MPSNNReduceRowMean performs a reduction operation returning the mean value for each row of an image

MPSNNReduceRowMinMPSNNReduce and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

The MPSNNReduceRowMin performs a reduction operation returning the mininmum value for each row of an image

MPSNNReduceRowSumMPSNNReduce and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

The MPSNNReduceRowSum performs a reduction operation returning the sum for each row of an image

MPSNNReduceUnaryMPSNNReduce and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

The MPSNNReduce performs a reduction operation The reduction operations supported are:

MPSNNReductionColumnMaxNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSNNReductionColumnMeanNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSNNReductionColumnMinNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSNNReductionColumnSumNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSNNReductionFeatureChannelsArgumentMaxNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSNNReductionFeatureChannelsArgumentMinNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSNNReductionFeatureChannelsMaxNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSNNReductionFeatureChannelsMeanNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSNNReductionFeatureChannelsMinNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSNNReductionFeatureChannelsSumNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSNNReductionRowMaxNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSNNReductionRowMeanNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSNNReductionRowMinNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSNNReductionRowSumNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSNNReductionSpatialMeanGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSNNReductionSpatialMeanNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSNNRegularizationTypeMPSNNOptimizers and MPSNeuralNetwork

Apple’s documentation

MPSNNReshapeMPSNNReshape and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Apple’s documentation

MPSNNReshapeGradientMPSNNReshape and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSNNReshapeGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSNNReshapeNodeMPSNNGraphNodes and MPSNeuralNetwork

A node for a MPSNNReshape kernel

MPSNNResizeBilinearMPSNNResize and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSNNScaleNodeMPSNNGraphNodes and MPSNeuralNetwork

Abstract Node representing a image resampling operation

MPSNNSliceMPSNNSlice and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Apple’s documentation

MPSNNStateNodeMPSNNGraphNodes and MPSNeuralNetwork

A placeholder node denoting the position in the graph of a MPSState object

MPSNNSubtractionGradientNodeMPSNNGraphNodes and MPSNeuralNetwork

returns gradient for either primary or secondary source image from the inference pass. Use the isSecondarySourceFilter property to indicate whether this filter is computing the gradient for the primary or secondary source image from the inference pass.

MPSNNSubtractionNodeMPSNNGraphNodes and MPSNeuralNetwork

returns elementwise difference of left - right

MPSNNTrainingStyleMPSNeuralNetworkTypes and MPSNeuralNetwork

Apple’s documentation

MPSNNUnaryReductionNodeMPSNNGraphNodes and MPSNeuralNetwork

A node for a unary MPSNNReduce node.

MPSOffsetMPSCoreTypes and MPSCore

A signed coordinate with x, y and z components

MPSOriginMPSCoreTypes and MPSCore

A position in an image

MPSPackedFloat3MPSRayIntersectorTypes

Apple’s documentation

MPSPolygonAccelerationStructureDeprecatedMPSPolygonAccelerationStructure and MPSRayIntersector and MPSAccelerationStructure and MPSCore and MPSKernel

An acceleration structure built over polygonal shapes

MPSPolygonBufferDeprecatedMPSPolygonBuffer and MPSRayIntersector

A vertex buffer and optional index and mask buffer for a set of polygons

MPSPolygonTypeDeprecatedMPSPolygonAccelerationStructure and MPSRayIntersector

Apple’s documentation

MPSPredicateMPSCommandBuffer and MPSCore

Dependencies: This depends on Metal.framework

MPSPurgeableStateMPSImage and MPSCore

Apple’s documentation

MPSQuadrilateralAccelerationStructureDeprecatedMPSQuadrilateralAccelerationStructure and MPSRayIntersector and MPSAccelerationStructure and MPSCore and MPSKernel and MPSPolygonAccelerationStructure

An acceleration structure built over quadrilaterals

MPSRNNBidirectionalCombineModeMPSRNNLayer and MPSNeuralNetwork

Apple’s documentation

MPSRNNDescriptorMPSRNNLayer and MPSNeuralNetwork

Dependencies: This depends on Metal.framework

MPSRNNImageInferenceLayerMPSRNNLayer and MPSNeuralNetwork and MPSCNNKernel and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSRNNMatrixIdMPSRNNLayer and MPSNeuralNetwork

Apple’s documentation

MPSRNNMatrixInferenceLayerMPSRNNLayer and MPSNeuralNetwork and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSRNNMatrixTrainingLayerMPSRNNLayer and MPSNeuralNetwork and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSRNNMatrixTrainingStateMPSRNNLayer and MPSNeuralNetwork and MPSCore and MPSState

Dependencies: This depends on Metal.framework

MPSRNNRecurrentImageStateMPSRNNLayer and MPSNeuralNetwork and MPSCore and MPSState

Dependencies: This depends on Metal.framework

MPSRNNRecurrentMatrixStateMPSRNNLayer and MPSNeuralNetwork and MPSCore and MPSState

Dependencies: This depends on Metal.framework

MPSRNNSequenceDirectionMPSRNNLayer and MPSNeuralNetwork

Apple’s documentation

MPSRNNSingleGateDescriptorMPSRNNLayer and MPSNeuralNetwork

Dependencies: This depends on Metal.framework

MPSRayDataTypeMPSRayIntersector

Options for the MPSRayIntersector ray data type property

MPSRayIntersectorDeprecatedMPSCore and MPSKernel and MPSRayIntersector

Performs intersection tests between rays and the geometry in an MPSAccelerationStructure

MPSRayMaskOperatorDeprecatedMPSRayIntersector

Options for the MPSRayIntersector ray mask operator property

MPSRayMaskOptionsDeprecatedMPSRayIntersector

Options for the MPSRayIntersector ray mask options property

MPSRayOriginMaskDirectionMaxDistanceMPSRayIntersectorTypes and MPSRayIntersector

Represents a 3D ray with an origin, a direction, and a mask to filter out intersections

MPSRayOriginMinDistanceDirectionMaxDistanceMPSRayIntersectorTypes and MPSRayIntersector

Represents a 3D ray with an origin, a direction, and an intersection distance range from the origin

MPSRayPackedOriginDirectionMPSRayIntersectorTypes and MPSRayIntersector

Represents a 3D ray with an origin and a direction

MPSRegionMPSCoreTypes and MPSCore

A region of an image

MPSSVGFMPSSVGF and MPSRayIntersector and MPSCore and MPSKernel

Reduces noise in images rendered with Monte Carlo ray tracing methods

MPSSVGFDefaultTextureAllocatorMPSSVGF and MPSRayIntersector

A default implementation of the MPSSVGFTextureAllocator protocol. Maintains a cache of textures which is checked first when a texture is requested. If there is no suitable texture in the cache, allocates a texture directly from the Metal device.

MPSSVGFDenoiserMPSSVGF and MPSRayIntersector

A convenience object which uses an MPSSVGF object to manage the denoising process

MPSScaleTransformMPSCoreTypes and MPSCore

Transform matrix for explict control over resampling in MPSImageScale.

MPSSizeMPSCoreTypes and MPSCore

A size of a region in an image

MPSStateMPSState and MPSCore

Dependencies: This depends on Metal Framework

MPSStateResourceListMPSState and MPSCore

Apple’s documentation

MPSStateResourceTypeMPSState and MPSCore

Apple’s documentation

MPSStateTextureInfoMPSState and MPSCore

Apple’s documentation

MPSTemporalAAMPSTemporalAA and MPSRayIntersector and MPSCore and MPSKernel

Reduces aliasing in an image by accumulating samples over multiple frames

MPSTemporalWeightingMPSSVGF and MPSRayIntersector

Controls how samples are weighted over time

MPSTemporaryImageMPSImage and MPSCore

Dependencies: MPSImage

MPSTemporaryMatrixMPSMatrix and MPSCore

A MPSMatrix allocated on GPU private memory.

MPSTemporaryNDArrayMPSNDArray and MPSCore

A MPSNDArray that uses command buffer specific memory to store the array data

MPSTemporaryVectorMPSMatrix and MPSCore

A MPSVector allocated on GPU private memory.

MPSTransformTypeMPSInstanceAccelerationStructure and MPSRayIntersector

Instance transformation type options

MPSTriangleAccelerationStructureDeprecatedMPSTriangleAccelerationStructure and MPSRayIntersector and MPSAccelerationStructure and MPSCore and MPSKernel and MPSPolygonAccelerationStructure

An acceleration structure built over triangles

MPSTriangleIntersectionTestTypeDeprecatedMPSRayIntersector

Options for the MPSRayIntersector triangle intersection test type property

MPSUnaryImageKernelMPSImageKernel and MPSImage and MPSCore and MPSKernel

Dependencies: This depends on Metal.framework

MPSVectorMPSMatrix and MPSCore

Dependencies: This depends on Metal.framework

MPSVectorDescriptorMPSMatrix and MPSCore

Dependencies: This depends on Metal.framework

Constants

MPSBatchSizeIndexMPSFunctionConstantIndices and MPSCore

Apple’s documentation

MPSDeviceCapsIndexMPSFunctionConstantIndices and MPSCore

Apple’s documentation

MPSFunctionConstantIndexMPSFunctionConstantIndices and MPSCore

Apple’s documentation

MPSFunctionConstantIndexReservedMPSFunctionConstantIndices and MPSCore

Apple’s documentation

MPSNDArrayConstantIndexMPSFunctionConstantIndices and MPSCore

Apple’s documentation

MPSNDArrayConstantMultiDestDstAddressingIndexMPSFunctionConstantIndices and MPSCore

Apple’s documentation

MPSNDArrayConstantMultiDestIndexMPSFunctionConstantIndices and MPSCore

Apple’s documentation

MPSNDArrayConstantMultiDestIndex0MPSFunctionConstantIndices and MPSCore

Apple’s documentation

MPSNDArrayConstantMultiDestIndex1MPSFunctionConstantIndices and MPSCore

Apple’s documentation

MPSNDArrayConstantMultiDestSrcAddressingIndexMPSFunctionConstantIndices and MPSCore

Apple’s documentation

MPSTextureLinkingConstantIndexMPSFunctionConstantIndices and MPSCore

Apple’s documentation

MPSUserAvailableFunctionConstantStartIndexMPSFunctionConstantIndices and MPSCore

Apple’s documentation

MPSUserConstantIndexMPSFunctionConstantIndices and MPSCore

Apple’s documentation

Statics

MPSFunctionConstantNoneMPSKernelTypes and MPSCore

Apple’s documentation

MPSRectNoClip^⚠MPSCoreTypes and MPSCore

This is a special constant to indicate no clipping is to be done. The entire image will be used. This is the default clipping rectangle or the input extent for MPSKernels.

Traits

MPSCNNBatchNormalizationDataSourceMPSCNNBatchNormalization and MPSNeuralNetwork

The MPSCNNBatchNormalizationDataSource protocol declares the methods that an instance of MPSCNNBatchNormalizationState uses to initialize the scale factors, bias terms, and batch statistics.

MPSCNNConvolutionDataSourceMPSCNNConvolution and MPSNeuralNetwork

Provides convolution filter weights and bias terms

MPSCNNGroupNormalizationDataSourceMPSCNNGroupNormalization and MPSNeuralNetwork

The MPSCNNGroupNormalizationDataSource protocol declares the methods that an group of MPSCNNGroupNormalization uses to initialize the scale factors (gamma) and bias terms (beta).

MPSCNNInstanceNormalizationDataSourceMPSCNNInstanceNormalization and MPSNeuralNetwork

The MPSCNNInstanceNormalizationDataSource protocol declares the methods that an instance of MPSCNNInstanceNormalization uses to initialize the scale factors (gamma) and bias terms (beta).

MPSDeviceProviderMPSCoreTypes and MPSCore

A way of extending a NSCoder to enable the setting of MTLDevice for unarchived objects

MPSHandleMPSNNGraphNodes and MPSNeuralNetwork

MPS resource identification

MPSHeapProviderMPSCommandBuffer and MPSCore

Apple’s documentation

MPSImageAllocatorMPSImage and MPSCore

A class that allocates new MPSImage or MPSTemporaryImage

MPSImageSizeEncodingStateMPSNeuralNetworkTypes and MPSNeuralNetwork

MPSStates conforming to this protocol contain information about a image size elsewhere in the graph

MPSImageTransformProviderMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSNDArrayAllocatorMPSNDArray and MPSCore

Apple’s documentation

MPSNNGramMatrixCallbackMPSNNGraphNodes and MPSNeuralNetwork

MPSNNGramMatrixCallback Defines a callback protocol for MPSNNGramMatrixCalculationNodeto set the ‘alpha’ scaling value dynamically just before encoding the underlying MPSNNGramMatrixCalculation kernel.

MPSNNLossCallbackMPSNNGraphNodes and MPSNeuralNetwork

MPSNNLossCallback Defines a callback protocol for MPSNNForwardLossNodeand MPSNNLossGradientNodeto set the scalar weight value just before encoding the underlying kernels.

MPSNNPaddingMPSNeuralNetworkTypes and MPSNeuralNetwork

A method to describe how MPSCNNKernels should pad images when data outside the image is needed

MPSNNTrainableNodeMPSNNGraphNodes and MPSNeuralNetwork

Apple’s documentation

MPSSVGFTextureAllocatorMPSSVGF and MPSRayIntersector

Protocol dictating how texture allocator objects should operate so that they can be used by an MPSSVGFDenoiser object to allocate and reuse intermediate and output textures during the denoising process.

Functions

MPSGetImageType^⚠MPSKernelTypes and MPSCore and MPSImage

MPSGetPreferredDevice^⚠

Identify the preferred device for MPS computation

MPSHintTemporaryMemoryHighWaterMark^⚠

Hint to MPS how much memory your application expects to need for the command buffer

MPSImageBatchIncrementReadCount^⚠DeprecatedMPSImage and MPSCore

MPSImageBatchIterate^⚠DeprecatedMPSImage and MPSCore and block2

MPSImageBatchResourceSize^⚠DeprecatedMPSImage and MPSCore

MPSImageBatchSynchronize^⚠DeprecatedMPSImage and MPSCore

MPSSetHeapCacheDuration^⚠

Set the timeout after which unused cached MTLHeaps are released

MPSStateBatchIncrementReadCount^⚠DeprecatedMPSState and MPSCore

MPSStateBatchResourceSize^⚠DeprecatedMPSState and MPSCore

MPSStateBatchSynchronize^⚠DeprecatedMPSState and MPSCore

MPSSupportsMTLDevice^⚠

MPSSupportsMTLDevice

Type Aliases

MPSAccelerationStructureCompletionHandlerMPSAccelerationStructure and MPSRayIntersector and MPSCore and MPSKernel and block2

A block of code invoked when an operation on an MPSAccelerationStructure is completed

MPSCNNArithmeticGradientStateBatchMPSCNNMath and MPSNeuralNetwork and MPSCore and MPSNNGradientState and MPSState

Apple’s documentation

MPSCNNConvolutionGradientStateBatchMPSCNNConvolution and MPSNeuralNetwork and MPSCore and MPSNNGradientState and MPSState

Apple’s documentation

MPSCNNConvolutionTransposeGradientStateBatchMPSCNNConvolution and MPSNeuralNetwork and MPSCore and MPSNNGradientState and MPSState

Apple’s documentation

MPSCNNDropoutGradientStateBatchMPSCNNDropout and MPSNeuralNetwork and MPSCore and MPSNNGradientState and MPSState

Apple’s documentation

MPSCNNGroupNormalizationGradientStateBatchMPSCNNGroupNormalization and MPSNeuralNetwork and MPSCore and MPSNNGradientState and MPSState

Apple’s documentation

MPSCNNInstanceNormalizationGradientStateBatchMPSCNNInstanceNormalization and MPSNeuralNetwork and MPSCore and MPSNNGradientState and MPSState

Apple’s documentation

MPSCNNLossLabelsBatchMPSCNNLoss and MPSNeuralNetwork and MPSCore and MPSState

Apple’s documentation

MPSCopyAllocatorMPSImageKernel and MPSImage and MPSCore and MPSKernel and block2

Apple’s documentation

MPSDeviceCapsMPSKernelTypes and MPSCore

Apple’s documentation

MPSFunctionConstantMPSKernelTypes and MPSCore

Apple’s documentation

MPSFunctionConstantInMetalMPSKernelTypes and MPSCore

Apple’s documentation

MPSGradientNodeBlockMPSNNGraphNodes and MPSNeuralNetwork and block2

Block callback for customizing gradient nodes as they are constructed

MPSImageBatchMPSImage and MPSCore

Apple’s documentation

MPSNNBinaryGradientStateBatchMPSNNGradientState and MPSNeuralNetwork and MPSCore and MPSState

Apple’s documentation

MPSNNGradientStateBatchMPSNNGradientState and MPSNeuralNetwork and MPSCore and MPSState

Apple’s documentation

MPSNNGraphCompletionHandlerMPSNNGraph and MPSNeuralNetwork and MPSCore and MPSImage and block2

A notification when computeAsyncWithSourceImages:completionHandler: has finished

MPSNNMultiaryGradientStateBatchMPSNNGradientState and MPSNeuralNetwork and MPSCore and MPSState

Apple’s documentation

MPSShapeMPSCoreTypes and MPSCore

An array of NSNumbers where dimension lengths provided by the user goes from slowest moving to fastest moving dimension. This is same order as MLMultiArray in coreML and most frameworks in Python.

MPSStateBatchMPSState and MPSCore

Apple’s documentation