An object that stores mean and variance terms used to execute batch normalization.
SDKs
- iOS 12.0+
- macOS 10.14+
- Mac Catalyst 13.0+
- tvOS 12.0+
Framework
- Metal Performance Shaders
Declaration
class MPSCNNNormalizationMeanAndVarianceState : MPSState
ClassMPSCNNNormalization
MPSCNNNormalization
Topics
Initializers
Instance Properties
See Also
Normalization Layers
class MPSCNNCrossA normalization kernel applied across feature channels.
class MPSCNNCrossA gradient normalization kernel applied across feature channels.
class MPSCNNLocalA local-contrast normalization kernel.
class MPSCNNLocalA gradient local-contrast normalization kernel.
class MPSCNNSpatialA spatial normalization kernel.
class MPSCNNSpatialA gradient spatial normalization kernel.
class MPSCNNBatchA batch normalization kernel.
class MPSCNNBatchA gradient batch normalization kernel.
class MPSCNNBatchAn object that stores data required to execute batch normalization.
class MPSCNNBatchAn object that stores statistics required to execute batch normalization.
class MPSCNNBatchAn object that stores the gradient of the loss function with respect to the batch statistics and batch normalization weights.
class MPSCNNInstanceAn instance normalization kernel.
class MPSCNNInstanceA gradient instance normalization kernel.
class MPSCNNInstanceAn object that stores information required to execute a gradient pass for instance normalization.
class MPSCNNNormalizationAn object that stores gamma and beta terms used to apply a scale and bias in instance- or batch-normalization operations.