Linux and UNIX Man Pages

Linux & Unix Commands - Search Man Pages

mpsnnreducefeaturechannelsandweightssum(3) [mojave man page]

MPSNNReduceFeatureChannelsAndWeightsSum(3)		 MetalPerformanceShaders.framework		MPSNNReduceFeatureChannelsAndWeightsSum(3)

NAME
MPSNNReduceFeatureChannelsAndWeightsSum SYNOPSIS
#import <MPSNNReduce.h> Inherits MPSNNReduceBinary. Instance Methods (nonnull instancetype) - initWithDevice: (nonnull instancetype) - initWithDevice:doWeightedSumByNonZeroWeights: Properties bool doWeightedSumByNonZeroWeights Additional Inherited Members Method Documentation - (nonnull instancetype) initWithDevice: (nonnull id< MTLDevice >) device Specifies information to apply the reduction operation on an image. Parameters: device The device the filter will run on Returns: A valid MPSNNReduceFeatureChannelsAndWeightsMean object or nil, if failure. Reimplemented from MPSNNReduceBinary. - (nonnull instancetype) initWithDevice: (nonnull id< MTLDevice >) device(bool) doWeightedSumByNonZeroWeights Specifies information to apply the reduction operation on an image. Parameters: device The device the filter will run on doWeightedSumByNonZeroWeights A boolean to indicate whether to compute a weighted sum or weighted sum divided by the number of non-zero weights Returns: A valid MPSNNReduceFeatureChannelsAndWeightsSum object or nil, if failure. Property Documentation - (bool) doWeightedSumByNonZeroWeights [read], [nonatomic], [assign] A boolean to indicate whether the reduction should perform a weighted sum of feature channels with non-zero weights If false, computes a dot product of the feature channels and weights. If true, computes a dot product of the feature channels and weights divided by the number of non-zero weights Author Generated automatically by Doxygen for MetalPerformanceShaders.framework from the source code. Version MetalPerformanceShaders-100 Thu Feb 8 2018 MPSNNReduceFeatureChannelsAndWeightsSum(3)

Check Out this Related Man Page

MPSCNNNeuronSoftPlus(3) 				 MetalPerformanceShaders.framework				   MPSCNNNeuronSoftPlus(3)

NAME
MPSCNNNeuronSoftPlus SYNOPSIS
#import <MPSCNNNeuron.h> Inherits MPSCNNNeuron. Instance Methods (nonnull instancetype) - initWithDevice:a:b: (nonnull instancetype) - initWithDevice: Additional Inherited Members Detailed Description This depends on Metal.framework Specifies the parametric softplus neuron filter. For each pixel, applies the following function: f(x) = a * log(1 + e^(b * x)) Method Documentation - (nonnull instancetype) initWithDevice: (nonnull id< MTLDevice >) device Standard init with default properties per filter type Parameters: device The device that the filter will be used on. May not be NULL. Returns: A pointer to the newly initialized object. This will fail, returning nil if the device is not supported. Devices must be MTLFeatureSet_iOS_GPUFamily2_v1 or later. Reimplemented from MPSCNNNeuron. - (nonnull instancetype) initWithDevice: (nonnull id< MTLDevice >) device(float) a(float) b Initialize a parametric softplus neuron filter Parameters: device The device the filter will run on a Filter property 'a'. See class discussion. b Filter property 'b'. See class discussion. Returns: A valid MPSCNNNeuronSoftPlus object or nil, if failure. Author Generated automatically by Doxygen for MetalPerformanceShaders.framework from the source code. Version MetalPerformanceShaders-100 Thu Feb 8 2018 MPSCNNNeuronSoftPlus(3)
Man Page