An object that stores the gradient of the loss function with respect to the batch statistics and batch normalization weights.
SDKs
Framework
@interface MPSCNNBatchNormalizationStatisticsGradient : MPSCNNGradientMPSCNNCrossA normalization kernel applied across feature channels.
MPSCNNCrossA gradient normalization kernel applied across feature channels.
MPSCNNLocalA local-contrast normalization kernel.
MPSCNNLocalA gradient local-contrast normalization kernel.
MPSCNNSpatialA spatial normalization kernel.
MPSCNNSpatialA gradient spatial normalization kernel.
MPSCNNBatchA batch normalization kernel.
MPSCNNBatchA gradient batch normalization kernel.
MPSCNNBatchAn object that stores data required to execute batch normalization.
MPSCNNNormalizationAn object that stores mean and variance terms used to execute batch normalization.
MPSCNNBatchAn object that stores statistics required to execute batch normalization.
MPSCNNInstanceAn instance normalization kernel.
MPSCNNInstanceA gradient instance normalization kernel.
MPSCNNInstanceAn object that stores information required to execute a gradient pass for instance normalization.
MPSCNNNormalizationAn object that stores gamma and beta terms used to apply a scale and bias in instance- or batch-normalization operations.
Beta Software
This documentation contains preliminary information about an API or technology in development. This information is subject to change, and software implemented according to this documentation should be tested with final operating system software.
Learn more about using Apple's beta software