get reshapeFrequency(): MLOptimizationHints_ReshapeFrequency
Swift declaration
var reshapeFrequency: MLOptimizationHints.ReshapeFrequency
The anticipated reshape frequency
CoreML framework needs to reshape the model with new shapes for models with flexible input.
Specify the anticipated reshape frequency (frequent or infrequent), so that the framework can optimize for
fast shape switching or fast prediction on seen shapes.
The default value is frequent, which means CoreML tries to switch to new shapes as fast as possible
set · iOS 17.4+
reshapeFrequency
TypeScript
set reshapeFrequency(value: MLOptimizationHints_ReshapeFrequency)
Swift declaration
var reshapeFrequency: MLOptimizationHints.ReshapeFrequency
The anticipated reshape frequency
CoreML framework needs to reshape the model with new shapes for models with flexible input.
Specify the anticipated reshape frequency (frequent or infrequent), so that the framework can optimize for
fast shape switching or fast prediction on seen shapes.
The default value is frequent, which means CoreML tries to switch to new shapes as fast as possible
get · iOS 18.0+
specializationStrategy
TypeScript
get specializationStrategy(): MLOptimizationHints_SpecializationStrategy
Swift declaration
var specializationStrategy: MLOptimizationHints.SpecializationStrategy
Optimization strategy for the model specialization.
Core ML segments the model's compute graph and specializes each segment for the
target compute device. This process can affect the model loading time and the prediction latency.
Use this option to tailor the specialization strategy for your model.
set · iOS 18.0+
specializationStrategy
TypeScript
set specializationStrategy(value: MLOptimizationHints_SpecializationStrategy)
Swift declaration
var specializationStrategy: MLOptimizationHints.SpecializationStrategy
Optimization strategy for the model specialization.
Core ML segments the model's compute graph and specializes each segment for the
target compute device. This process can affect the model loading time and the prediction latency.
Use this option to tailor the specialization strategy for your model.
